chore: update changelog, bump SDK and package versions to 3.0.8 and 2.0.6

.gitmodules

@@ -1,4 +0,0 @@
-[submodule "evaluation"]
-	path = evaluation
-	url = https://github.com/mem0ai/memory-benchmarks
-	branch = main

AGENTS.md

@@ -12,7 +12,7 @@ This file provides context for AI coding assistants (Claude Code, Cursor, GitHub
 
 ## Repository Structure
 
-This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs, servers, plugins, and documentation.
+This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs, servers, plugins, documentation, and evaluation tooling.
 
 ### Key Directories
 
@@ -32,7 +32,7 @@ This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs,
 | `skills/` | Claude Code skill definitions. Reference skills (SDK knowledge, always-on): `mem0/`, `mem0-cli/`, `mem0-vercel-ai-sdk/`. Pipeline skills (run on demand): `mem0-integrate/`, `mem0-test-integration/`, `mem0-oss-to-platform/` |
 | `docs/` | Documentation site (Mintlify) |
 | `tests/` | Python SDK tests (pytest) |
-| `evaluation/` | Submodule → [`mem0ai/memory-benchmarks`](https://github.com/mem0ai/memory-benchmarks) — benchmarking (LOCOMO, LongMemEval, BEAM) lives in that repo |
+| `evaluation/` | Benchmarking framework — LOCOMO evals, experiment runner, score generation |
 | `examples/` | Sample projects & runnable demos — apps, Chrome extension, multi-agent patterns, and Jupyter notebooks (`notebooks/`) |
 | `pr-reviews/` | Pull request review materials |
 | `scripts/` | Repo-wide utility scripts (e.g., `check-llms-txt-coverage.py` for docs/llms.txt sync) |
@@ -246,19 +246,18 @@ make docs                          # or: cd docs && mintlify dev
 - **API spec:** `docs/openapi.json`
 - **Structure:** `api-reference/`, `open-source/`, `platform/`, `integrations/`, `cookbooks/`, `core-concepts/`
 
-### Evaluation / Benchmarking
-
-Benchmarking lives in the external [`mem0ai/memory-benchmarks`](https://github.com/mem0ai/memory-benchmarks) repo (LOCOMO + LongMemEval + BEAM). The in-repo `evaluation/` path is a **git submodule** pinned to that repo's `main` — populate it with `git submodule update --init evaluation` (or clone mem0 with `--recurse-submodules`), or clone the benchmarks repo standalone:
+### Evaluation (`evaluation/`)
 
 ```bash
-git clone https://github.com/mem0ai/memory-benchmarks.git
-cd memory-benchmarks
-pip install -r requirements.txt
-
-# Run a benchmark (Mem0 Cloud; use docker compose for OSS)
-python -m benchmarks.locomo.run --project-name my-test --backend cloud --mem0-api-key $MEM0_API_KEY
-python -m benchmarks.longmemeval.run --project-name my-test --backend cloud --mem0-api-key $MEM0_API_KEY --all-questions
-python -m benchmarks.beam.run --project-name my-test --backend cloud --mem0-api-key $MEM0_API_KEY --chat-sizes 100K --conversations 0-9
+cd evaluation
+make run-mem0-add                  # Run mem0 add experiments
+make run-mem0-search               # Run mem0 search experiments
+make run-mem0-plus-add             # With graph memory
+make run-mem0-plus-search          # With graph memory
+make run-rag                       # RAG baseline
+make run-full-context              # Full context baseline
+make run-langmem                   # LangMem comparison
+make run-openai                    # OpenAI comparison
 ```
 
 ## Core APIs

evaluation/Makefile

@@ -0,0 +1,31 @@
+
+# Run the experiments
+run-mem0-add:
+	python run_experiments.py --technique_type mem0 --method add
+
+run-mem0-search:
+	python run_experiments.py --technique_type mem0 --method search --output_folder results/ --top_k 30
+
+run-mem0-plus-add:
+	python run_experiments.py --technique_type mem0 --method add --is_graph
+
+run-mem0-plus-search:
+	python run_experiments.py --technique_type mem0 --method search --is_graph --output_folder results/ --top_k 30
+
+run-rag:
+	python run_experiments.py --technique_type rag --chunk_size 500 --num_chunks 1 --output_folder results/
+
+run-full-context:
+	python run_experiments.py --technique_type rag --chunk_size -1 --num_chunks 1 --output_folder results/
+
+run-langmem:
+	python run_experiments.py --technique_type langmem --output_folder results/
+
+run-zep-add:
+	python run_experiments.py --technique_type zep --method add --output_folder results/
+
+run-zep-search:
+	python run_experiments.py --technique_type zep --method search --output_folder results/
+
+run-openai:
+	python run_experiments.py --technique_type openai --output_folder results/

evaluation/README.md

@@ -0,0 +1,198 @@
+# Mem0: Building Production‑Ready AI Agents with Scalable Long‑Term Memory
+
+[![arXiv](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://arxiv.org/abs/2504.19413)
+[![Website](https://img.shields.io/badge/Website-Project-blue)](https://mem0.ai/research)
+
+This repository contains the code and dataset for our paper: **Mem0: Building Production‑Ready AI Agents with Scalable Long‑Term Memory**.
+
+## 📋 Overview
+
+This project evaluates Mem0 and compares it with different memory and retrieval techniques for AI systems:
+
+1. **Established LOCOMO Benchmarks**: We evaluate against five established approaches from the literature: LoCoMo, ReadAgent, MemoryBank, MemGPT, and A-Mem.
+2. **Open-Source Memory Solutions**: We test promising open-source memory architectures including LangMem, which provides flexible memory management capabilities.
+3. **RAG Systems**: We implement Retrieval-Augmented Generation with various configurations, testing different chunk sizes and retrieval counts to optimize performance.
+4. **Full-Context Processing**: We examine the effectiveness of passing the entire conversation history within the context window of the LLM as a baseline approach.
+5. **Proprietary Memory Systems**: We evaluate OpenAI's built-in memory feature available in their ChatGPT interface to compare against commercial solutions.
+6. **Third-Party Memory Providers**: We incorporate Zep, a specialized memory management platform designed for AI agents, to assess the performance of dedicated memory infrastructure.
+
+We test these techniques on the LOCOMO dataset, which contains conversational data with various question types to evaluate memory recall and understanding.
+
+## 🔍 Dataset
+
+The LOCOMO dataset used in our experiments can be downloaded from our Google Drive repository:
+
+[Download LOCOMO Dataset](https://drive.google.com/drive/folders/1L-cTjTm0ohMsitsHg4dijSPJtqNflwX-?usp=drive_link)
+
+The dataset contains conversational data specifically designed to test memory recall and understanding across various question types and complexity levels.
+
+Place the dataset files in the `dataset/` directory:
+- `locomo10.json`: Original dataset
+- `locomo10_rag.json`: Dataset formatted for RAG experiments
+
+## 📁 Project Structure
+
+```
+.
+├── src/                  # Source code for different memory techniques
+│   ├── mem0/             # Implementation of the Mem0 technique
+│   ├── openai/           # Implementation of the OpenAI memory
+│   ├── zep/              # Implementation of the Zep memory
+│   ├── rag.py            # Implementation of the RAG technique
+│   └── langmem.py        # Implementation of the Language-based memory
+├── metrics/              # Code for evaluation metrics
+├── results/              # Results of experiments
+├── dataset/              # Dataset files
+├── evals.py              # Evaluation script
+├── run_experiments.py    # Script to run experiments
+├── generate_scores.py    # Script to generate scores from results
+└── prompts.py            # Prompts used for the models
+```
+
+## 🚀 Getting Started
+
+### Prerequisites
+
+Create a `.env` file with your API keys and configurations. The following keys are required:
+
+```
+# OpenAI API key for GPT models and embeddings
+OPENAI_API_KEY="your-openai-api-key"
+
+# Mem0 API keys (for Mem0 and Mem0+ techniques)
+MEM0_API_KEY="your-mem0-api-key"
+MEM0_PROJECT_ID="your-mem0-project-id"
+MEM0_ORGANIZATION_ID="your-mem0-organization-id"
+
+# Model configuration
+MODEL="gpt-4o-mini"  # or your preferred model
+EMBEDDING_MODEL="text-embedding-3-small"  # or your preferred embedding model
+ZEP_API_KEY="api-key-from-zep"
+```
+
+### Running Experiments
+
+You can run experiments using the provided Makefile commands:
+
+#### Memory Techniques
+
+```bash
+# Run Mem0 experiments
+make run-mem0-add         # Add memories using Mem0
+make run-mem0-search      # Search memories using Mem0
+
+# Run Mem0+ experiments (with graph-based search)
+make run-mem0-plus-add    # Add memories using Mem0+
+make run-mem0-plus-search # Search memories using Mem0+
+
+# Run RAG experiments
+make run-rag              # Run RAG with chunk size 500
+make run-full-context     # Run RAG with full context
+
+# Run LangMem experiments
+make run-langmem          # Run LangMem
+
+# Run Zep experiments
+make run-zep-add          # Add memories using Zep
+make run-zep-search       # Search memories using Zep
+
+# Run OpenAI experiments
+make run-openai           # Run OpenAI experiments
+```
+
+Alternatively, you can run experiments directly with custom parameters:
+
+```bash
+python run_experiments.py --technique_type [mem0|rag|langmem] [additional parameters]
+```
+
+#### Command-line Parameters:
+
+| Parameter | Description | Default |
+|-----------|-------------|---------|
+| `--technique_type` | Memory technique to use (mem0, rag, langmem) | mem0 |
+| `--method` | Method to use (add, search) | add |
+| `--chunk_size` | Chunk size for processing | 1000 |
+| `--top_k` | Number of top memories to retrieve | 30 |
+| `--filter_memories` | Whether to filter memories | False |
+| `--is_graph` | Whether to use graph-based search | False |
+| `--num_chunks` | Number of chunks to process for RAG | 1 |
+
+### 📊 Evaluation
+
+To evaluate results, run:
+
+```bash
+python evals.py --input_file [path_to_results] --output_file [output_path]
+```
+
+This script:
+1. Processes each question-answer pair
+2. Calculates BLEU and F1 scores automatically
+3. Uses an LLM judge to evaluate answer correctness
+4. Saves the combined results to the output file
+
+### 📈 Generating Scores
+
+Generate final scores with:
+
+```bash
+python generate_scores.py
+```
+
+This script:
+1. Loads the evaluation metrics data
+2. Calculates mean scores for each category (BLEU, F1, LLM)
+3. Reports the number of questions per category
+4. Calculates overall mean scores across all categories
+
+Example output:
+```
+Mean Scores Per Category:
+         bleu_score  f1_score  llm_score  count
+category                                       
+1           0.xxxx    0.xxxx     0.xxxx     xx
+2           0.xxxx    0.xxxx     0.xxxx     xx
+3           0.xxxx    0.xxxx     0.xxxx     xx
+
+Overall Mean Scores:
+bleu_score    0.xxxx
+f1_score      0.xxxx
+llm_score     0.xxxx
+```
+
+## 📏 Evaluation Metrics
+
+We use several metrics to evaluate the performance of different memory techniques:
+
+1. **BLEU Score**: Measures the similarity between the model's response and the ground truth
+2. **F1 Score**: Measures the harmonic mean of precision and recall
+3. **LLM Score**: A binary score (0 or 1) determined by an LLM judge evaluating the correctness of responses
+4. **Token Consumption**: Number of tokens required to generate final answer.
+5. **Latency**: Time required during search and to generate response.
+
+## 📚 Citation
+
+If you use this code or dataset in your research, please cite our paper:
+
+```bibtex
+@article{mem0,
+  title={Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory},
+  author={Chhikara, Prateek and Khant, Dev and Aryan, Saket and Singh, Taranjeet and Yadav, Deshraj},
+  journal={arXiv preprint arXiv:2504.19413},
+  year={2025}
+}
+```
+
+## 📄 License
+
+[MIT License](LICENSE)
+
+## 👥 Contributors
+
+- [Prateek Chhikara](https://github.com/prateekchhikara)
+- [Dev Khant](https://github.com/Dev-Khant)
+- [Saket Aryan](https://github.com/whysosaket)
+- [Taranjeet Singh](https://github.com/taranjeet)
+- [Deshraj Yadav](https://github.com/deshraj)
+

evaluation/evals.py

@@ -0,0 +1,81 @@
+import argparse
+import concurrent.futures
+import json
+import threading
+from collections import defaultdict
+
+from metrics.llm_judge import evaluate_llm_judge
+from metrics.utils import calculate_bleu_scores, calculate_metrics
+from tqdm import tqdm
+
+
+def process_item(item_data):
+    k, v = item_data
+    local_results = defaultdict(list)
+
+    for item in v:
+        gt_answer = str(item["answer"])
+        pred_answer = str(item["response"])
+        category = str(item["category"])
+        question = str(item["question"])
+
+        # Skip category 5
+        if category == "5":
+            continue
+
+        metrics = calculate_metrics(pred_answer, gt_answer)
+        bleu_scores = calculate_bleu_scores(pred_answer, gt_answer)
+        llm_score = evaluate_llm_judge(question, gt_answer, pred_answer)
+
+        local_results[k].append(
+            {
+                "question": question,
+                "answer": gt_answer,
+                "response": pred_answer,
+                "category": category,
+                "bleu_score": bleu_scores["bleu1"],
+                "f1_score": metrics["f1"],
+                "llm_score": llm_score,
+            }
+        )
+
+    return local_results
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Evaluate RAG results")
+    parser.add_argument(
+        "--input_file", type=str, default="results/rag_results_500_k1.json", help="Path to the input dataset file"
+    )
+    parser.add_argument(
+        "--output_file", type=str, default="evaluation_metrics.json", help="Path to save the evaluation results"
+    )
+    parser.add_argument("--max_workers", type=int, default=10, help="Maximum number of worker threads")
+
+    args = parser.parse_args()
+
+    with open(args.input_file, "r") as f:
+        data = json.load(f)
+
+    results = defaultdict(list)
+    results_lock = threading.Lock()
+
+    # Use ThreadPoolExecutor with specified workers
+    with concurrent.futures.ThreadPoolExecutor(max_workers=args.max_workers) as executor:
+        futures = [executor.submit(process_item, item_data) for item_data in data.items()]
+
+        for future in tqdm(concurrent.futures.as_completed(futures), total=len(futures)):
+            local_results = future.result()
+            with results_lock:
+                for k, items in local_results.items():
+                    results[k].extend(items)
+
+    # Save results to JSON file
+    with open(args.output_file, "w") as f:
+        json.dump(results, f, indent=4)
+
+    print(f"Results saved to {args.output_file}")
+
+
+if __name__ == "__main__":
+    main()

evaluation/generate_scores.py

@@ -0,0 +1,34 @@
+import json
+
+import pandas as pd
+
+# Load the evaluation metrics data
+with open("evaluation_metrics.json", "r") as f:
+    data = json.load(f)
+
+# Flatten the data into a list of question items
+all_items = []
+for key in data:
+    all_items.extend(data[key])
+
+# Convert to DataFrame
+df = pd.DataFrame(all_items)
+
+# Convert category to numeric type
+df["category"] = pd.to_numeric(df["category"])
+
+# Calculate mean scores by category
+result = df.groupby("category").agg({"bleu_score": "mean", "f1_score": "mean", "llm_score": "mean"}).round(4)
+
+# Add count of questions per category
+result["count"] = df.groupby("category").size()
+
+# Print the results
+print("Mean Scores Per Category:")
+print(result)
+
+# Calculate overall means
+overall_means = df.agg({"bleu_score": "mean", "f1_score": "mean", "llm_score": "mean"}).round(4)
+
+print("\nOverall Mean Scores:")
+print(overall_means)

evaluation/metrics/llm_judge.py

@@ -0,0 +1,130 @@
+import argparse
+import json
+from collections import defaultdict
+
+import numpy as np
+from openai import OpenAI
+
+from mem0.memory.utils import extract_json
+
+client = OpenAI()
+
+ACCURACY_PROMPT = """
+Your task is to label an answer to a question as ’CORRECT’ or ’WRONG’. You will be given the following data:
+    (1) a question (posed by one user to another user), 
+    (2) a ’gold’ (ground truth) answer, 
+    (3) a generated answer
+which you will score as CORRECT/WRONG.
+
+The point of the question is to ask about something one user should know about the other user based on their prior conversations.
+The gold answer will usually be a concise and short answer that includes the referenced topic, for example:
+Question: Do you remember what I got the last time I went to Hawaii?
+Gold answer: A shell necklace
+The generated answer might be much longer, but you should be generous with your grading - as long as it touches on the same topic as the gold answer, it should be counted as CORRECT. 
+
+For time related questions, the gold answer will be a specific date, month, year, etc. The generated answer might be much longer or use relative time references (like "last Tuesday" or "next month"), but you should be generous with your grading - as long as it refers to the same date or time period as the gold answer, it should be counted as CORRECT. Even if the format differs (e.g., "May 7th" vs "7 May"), consider it CORRECT if it's the same date.
+
+Now it's time for the real question:
+Question: {question}
+Gold answer: {gold_answer}
+Generated answer: {generated_answer}
+
+First, provide a short (one sentence) explanation of your reasoning, then finish with CORRECT or WRONG. 
+Do NOT include both CORRECT and WRONG in your response, or it will break the evaluation script.
+
+Just return the label CORRECT or WRONG in a json format with the key as "label".
+"""
+
+
+def evaluate_llm_judge(question, gold_answer, generated_answer):
+    """Evaluate the generated answer against the gold answer using an LLM judge."""
+    response = client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=[
+            {
+                "role": "user",
+                "content": ACCURACY_PROMPT.format(
+                    question=question, gold_answer=gold_answer, generated_answer=generated_answer
+                ),
+            }
+        ],
+        response_format={"type": "json_object"},
+        temperature=0.0,
+    )
+    label = json.loads(extract_json(response.choices[0].message.content))["label"]
+    return 1 if label == "CORRECT" else 0
+
+
+def main():
+    """Main function to evaluate RAG results using LLM judge."""
+    parser = argparse.ArgumentParser(description="Evaluate RAG results using LLM judge")
+    parser.add_argument(
+        "--input_file",
+        type=str,
+        default="results/default_run_v4_k30_new_graph.json",
+        help="Path to the input dataset file",
+    )
+
+    args = parser.parse_args()
+
+    dataset_path = args.input_file
+    output_path = f"results/llm_judge_{dataset_path.split('/')[-1]}"
+
+    with open(dataset_path, "r") as f:
+        data = json.load(f)
+
+    LLM_JUDGE = defaultdict(list)
+    RESULTS = defaultdict(list)
+
+    index = 0
+    for k, v in data.items():
+        for x in v:
+            question = x["question"]
+            gold_answer = x["answer"]
+            generated_answer = x["response"]
+            category = x["category"]
+
+            # Skip category 5
+            if int(category) == 5:
+                continue
+
+            # Evaluate the answer
+            label = evaluate_llm_judge(question, gold_answer, generated_answer)
+            LLM_JUDGE[category].append(label)
+
+            # Store the results
+            RESULTS[index].append(
+                {
+                    "question": question,
+                    "gt_answer": gold_answer,
+                    "response": generated_answer,
+                    "category": category,
+                    "llm_label": label,
+                }
+            )
+
+            # Save intermediate results
+            with open(output_path, "w") as f:
+                json.dump(RESULTS, f, indent=4)
+
+            # Print current accuracy for all categories
+            print("All categories accuracy:")
+            for cat, results in LLM_JUDGE.items():
+                if results:  # Only print if there are results for this category
+                    print(f"  Category {cat}: {np.mean(results):.4f} ({sum(results)}/{len(results)})")
+            print("------------------------------------------")
+        index += 1
+
+    # Save final results
+    with open(output_path, "w") as f:
+        json.dump(RESULTS, f, indent=4)
+
+    # Print final summary
+    print("PATH: ", dataset_path)
+    print("------------------------------------------")
+    for k, v in LLM_JUDGE.items():
+        print(k, np.mean(v))
+
+
+if __name__ == "__main__":
+    main()

evaluation/metrics/utils.py

@@ -0,0 +1,211 @@
+"""
+Borrowed from https://github.com/WujiangXu/AgenticMemory/blob/main/utils.py
+
+@article{xu2025mem,
+    title={A-mem: Agentic memory for llm agents},
+    author={Xu, Wujiang and Liang, Zujie and Mei, Kai and Gao, Hang and Tan, Juntao
+           and Zhang, Yongfeng},
+    journal={arXiv preprint arXiv:2502.12110},
+    year={2025}
+}
+"""
+
+import statistics
+from collections import defaultdict
+from typing import Dict, List, Union
+
+import nltk
+from bert_score import score as bert_score
+from nltk.translate.bleu_score import SmoothingFunction, sentence_bleu
+from nltk.translate.meteor_score import meteor_score
+from rouge_score import rouge_scorer
+from sentence_transformers import SentenceTransformer
+
+# from load_dataset import load_locomo_dataset, QA, Turn, Session, Conversation
+from sentence_transformers.util import pytorch_cos_sim
+
+# Download required NLTK data
+try:
+    nltk.download("punkt", quiet=True)
+    nltk.download("wordnet", quiet=True)
+except Exception as e:
+    print(f"Error downloading NLTK data: {e}")
+
+# Initialize SentenceTransformer model (this will be reused)
+try:
+    sentence_model = SentenceTransformer("all-MiniLM-L6-v2")
+except Exception as e:
+    print(f"Warning: Could not load SentenceTransformer model: {e}")
+    sentence_model = None
+
+
+def simple_tokenize(text):
+    """Simple tokenization function."""
+    # Convert to string if not already
+    text = str(text)
+    return text.lower().replace(".", " ").replace(",", " ").replace("!", " ").replace("?", " ").split()
+
+
+def calculate_rouge_scores(prediction: str, reference: str) -> Dict[str, float]:
+    """Calculate ROUGE scores for prediction against reference."""
+    scorer = rouge_scorer.RougeScorer(["rouge1", "rouge2", "rougeL"], use_stemmer=True)
+    scores = scorer.score(reference, prediction)
+    return {
+        "rouge1_f": scores["rouge1"].fmeasure,
+        "rouge2_f": scores["rouge2"].fmeasure,
+        "rougeL_f": scores["rougeL"].fmeasure,
+    }
+
+
+def calculate_bleu_scores(prediction: str, reference: str) -> Dict[str, float]:
+    """Calculate BLEU scores with different n-gram settings."""
+    pred_tokens = nltk.word_tokenize(prediction.lower())
+    ref_tokens = [nltk.word_tokenize(reference.lower())]
+
+    weights_list = [(1, 0, 0, 0), (0.5, 0.5, 0, 0), (0.33, 0.33, 0.33, 0), (0.25, 0.25, 0.25, 0.25)]
+    smooth = SmoothingFunction().method1
+
+    scores = {}
+    for n, weights in enumerate(weights_list, start=1):
+        try:
+            score = sentence_bleu(ref_tokens, pred_tokens, weights=weights, smoothing_function=smooth)
+        except Exception as e:
+            print(f"Error calculating BLEU score: {e}")
+            score = 0.0
+        scores[f"bleu{n}"] = score
+
+    return scores
+
+
+def calculate_bert_scores(prediction: str, reference: str) -> Dict[str, float]:
+    """Calculate BERTScore for semantic similarity."""
+    try:
+        P, R, F1 = bert_score([prediction], [reference], lang="en", verbose=False)
+        return {"bert_precision": P.item(), "bert_recall": R.item(), "bert_f1": F1.item()}
+    except Exception as e:
+        print(f"Error calculating BERTScore: {e}")
+        return {"bert_precision": 0.0, "bert_recall": 0.0, "bert_f1": 0.0}
+
+
+def calculate_meteor_score(prediction: str, reference: str) -> float:
+    """Calculate METEOR score for the prediction."""
+    try:
+        return meteor_score([reference.split()], prediction.split())
+    except Exception as e:
+        print(f"Error calculating METEOR score: {e}")
+        return 0.0
+
+
+def calculate_sentence_similarity(prediction: str, reference: str) -> float:
+    """Calculate sentence embedding similarity using SentenceBERT."""
+    if sentence_model is None:
+        return 0.0
+    try:
+        # Encode sentences
+        embedding1 = sentence_model.encode([prediction], convert_to_tensor=True)
+        embedding2 = sentence_model.encode([reference], convert_to_tensor=True)
+
+        # Calculate cosine similarity
+        similarity = pytorch_cos_sim(embedding1, embedding2).item()
+        return float(similarity)
+    except Exception as e:
+        print(f"Error calculating sentence similarity: {e}")
+        return 0.0
+
+
+def calculate_metrics(prediction: str, reference: str) -> Dict[str, float]:
+    """Calculate comprehensive evaluation metrics for a prediction."""
+    # Handle empty or None values
+    if not prediction or not reference:
+        return {
+            "exact_match": 0,
+            "f1": 0.0,
+            "rouge1_f": 0.0,
+            "rouge2_f": 0.0,
+            "rougeL_f": 0.0,
+            "bleu1": 0.0,
+            "bleu2": 0.0,
+            "bleu3": 0.0,
+            "bleu4": 0.0,
+            "bert_f1": 0.0,
+            "meteor": 0.0,
+            "sbert_similarity": 0.0,
+        }
+
+    # Convert to strings if they're not already
+    prediction = str(prediction).strip()
+    reference = str(reference).strip()
+
+    # Calculate exact match
+    exact_match = int(prediction.lower() == reference.lower())
+
+    # Calculate token-based F1 score
+    pred_tokens = set(simple_tokenize(prediction))
+    ref_tokens = set(simple_tokenize(reference))
+    common_tokens = pred_tokens & ref_tokens
+
+    if not pred_tokens or not ref_tokens:
+        f1 = 0.0
+    else:
+        precision = len(common_tokens) / len(pred_tokens)
+        recall = len(common_tokens) / len(ref_tokens)
+        f1 = 2 * precision * recall / (precision + recall) if (precision + recall) > 0 else 0.0
+
+    # Calculate all scores
+    bleu_scores = calculate_bleu_scores(prediction, reference)
+
+    # Combine all metrics
+    metrics = {
+        "exact_match": exact_match,
+        "f1": f1,
+        **bleu_scores,
+    }
+
+    return metrics
+
+
+def aggregate_metrics(
+    all_metrics: List[Dict[str, float]], all_categories: List[int]
+) -> Dict[str, Dict[str, Union[float, Dict[str, float]]]]:
+    """Calculate aggregate statistics for all metrics, split by category."""
+    if not all_metrics:
+        return {}
+
+    # Initialize aggregates for overall and per-category metrics
+    aggregates = defaultdict(list)
+    category_aggregates = defaultdict(lambda: defaultdict(list))
+
+    # Collect all values for each metric, both overall and per category
+    for metrics, category in zip(all_metrics, all_categories):
+        for metric_name, value in metrics.items():
+            aggregates[metric_name].append(value)
+            category_aggregates[category][metric_name].append(value)
+
+    # Calculate statistics for overall metrics
+    results = {"overall": {}}
+
+    for metric_name, values in aggregates.items():
+        results["overall"][metric_name] = {
+            "mean": statistics.mean(values),
+            "std": statistics.stdev(values) if len(values) > 1 else 0.0,
+            "median": statistics.median(values),
+            "min": min(values),
+            "max": max(values),
+            "count": len(values),
+        }
+
+    # Calculate statistics for each category
+    for category in sorted(category_aggregates.keys()):
+        results[f"category_{category}"] = {}
+        for metric_name, values in category_aggregates[category].items():
+            if values:  # Only calculate if we have values for this category
+                results[f"category_{category}"][metric_name] = {
+                    "mean": statistics.mean(values),
+                    "std": statistics.stdev(values) if len(values) > 1 else 0.0,
+                    "median": statistics.median(values),
+                    "min": min(values),
+                    "max": max(values),
+                    "count": len(values),
+                }
+
+    return results

evaluation/prompts.py

@@ -0,0 +1,147 @@
+ANSWER_PROMPT_GRAPH = """
+    You are an intelligent memory assistant tasked with retrieving accurate information from 
+    conversation memories.
+
+    # CONTEXT:
+    You have access to memories from two speakers in a conversation. These memories contain 
+    timestamped information that may be relevant to answering the question. You also have 
+    access to knowledge graph relations for each user, showing connections between entities, 
+    concepts, and events relevant to that user.
+
+    # INSTRUCTIONS:
+    1. Carefully analyze all provided memories from both speakers
+    2. Pay special attention to the timestamps to determine the answer
+    3. If the question asks about a specific event or fact, look for direct evidence in the 
+       memories
+    4. If the memories contain contradictory information, prioritize the most recent memory
+    5. If there is a question about time references (like "last year", "two months ago", 
+       etc.), calculate the actual date based on the memory timestamp. For example, if a 
+       memory from 4 May 2022 mentions "went to India last year," then the trip occurred 
+       in 2021.
+    6. Always convert relative time references to specific dates, months, or years. For 
+       example, convert "last year" to "2022" or "two months ago" to "March 2023" based 
+       on the memory timestamp. Ignore the reference while answering the question.
+    7. Focus only on the content of the memories from both speakers. Do not confuse 
+       character names mentioned in memories with the actual users who created those 
+       memories.
+    8. The answer should be less than 5-6 words.
+    9. Use the knowledge graph relations to understand the user's knowledge network and 
+       identify important relationships between entities in the user's world.
+
+    # APPROACH (Think step by step):
+    1. First, examine all memories that contain information related to the question
+    2. Examine the timestamps and content of these memories carefully
+    3. Look for explicit mentions of dates, times, locations, or events that answer the 
+       question
+    4. If the answer requires calculation (e.g., converting relative time references), 
+       show your work
+    5. Analyze the knowledge graph relations to understand the user's knowledge context
+    6. Formulate a precise, concise answer based solely on the evidence in the memories
+    7. Double-check that your answer directly addresses the question asked
+    8. Ensure your final answer is specific and avoids vague time references
+
+    Memories for user {{speaker_1_user_id}}:
+
+    {{speaker_1_memories}}
+
+    Relations for user {{speaker_1_user_id}}:
+
+    {{speaker_1_graph_memories}}
+
+    Memories for user {{speaker_2_user_id}}:
+
+    {{speaker_2_memories}}
+
+    Relations for user {{speaker_2_user_id}}:
+
+    {{speaker_2_graph_memories}}
+
+    Question: {{question}}
+
+    Answer:
+    """
+
+
+ANSWER_PROMPT = """
+    You are an intelligent memory assistant tasked with retrieving accurate information from conversation memories.
+
+    # CONTEXT:
+    You have access to memories from two speakers in a conversation. These memories contain 
+    timestamped information that may be relevant to answering the question.
+
+    # INSTRUCTIONS:
+    1. Carefully analyze all provided memories from both speakers
+    2. Pay special attention to the timestamps to determine the answer
+    3. If the question asks about a specific event or fact, look for direct evidence in the memories
+    4. If the memories contain contradictory information, prioritize the most recent memory
+    5. If there is a question about time references (like "last year", "two months ago", etc.), 
+       calculate the actual date based on the memory timestamp. For example, if a memory from 
+       4 May 2022 mentions "went to India last year," then the trip occurred in 2021.
+    6. Always convert relative time references to specific dates, months, or years. For example, 
+       convert "last year" to "2022" or "two months ago" to "March 2023" based on the memory 
+       timestamp. Ignore the reference while answering the question.
+    7. Focus only on the content of the memories from both speakers. Do not confuse character 
+       names mentioned in memories with the actual users who created those memories.
+    8. The answer should be less than 5-6 words.
+
+    # APPROACH (Think step by step):
+    1. First, examine all memories that contain information related to the question
+    2. Examine the timestamps and content of these memories carefully
+    3. Look for explicit mentions of dates, times, locations, or events that answer the question
+    4. If the answer requires calculation (e.g., converting relative time references), show your work
+    5. Formulate a precise, concise answer based solely on the evidence in the memories
+    6. Double-check that your answer directly addresses the question asked
+    7. Ensure your final answer is specific and avoids vague time references
+
+    Memories for user {{speaker_1_user_id}}:
+
+    {{speaker_1_memories}}
+
+    Memories for user {{speaker_2_user_id}}:
+
+    {{speaker_2_memories}}
+
+    Question: {{question}}
+
+    Answer:
+    """
+
+
+ANSWER_PROMPT_ZEP = """
+    You are an intelligent memory assistant tasked with retrieving accurate information from conversation memories.
+
+    # CONTEXT:
+    You have access to memories from a conversation. These memories contain
+    timestamped information that may be relevant to answering the question.
+
+    # INSTRUCTIONS:
+    1. Carefully analyze all provided memories
+    2. Pay special attention to the timestamps to determine the answer
+    3. If the question asks about a specific event or fact, look for direct evidence in the memories
+    4. If the memories contain contradictory information, prioritize the most recent memory
+    5. If there is a question about time references (like "last year", "two months ago", etc.), 
+       calculate the actual date based on the memory timestamp. For example, if a memory from 
+       4 May 2022 mentions "went to India last year," then the trip occurred in 2021.
+    6. Always convert relative time references to specific dates, months, or years. For example, 
+       convert "last year" to "2022" or "two months ago" to "March 2023" based on the memory 
+       timestamp. Ignore the reference while answering the question.
+    7. Focus only on the content of the memories. Do not confuse character 
+       names mentioned in memories with the actual users who created those memories.
+    8. The answer should be less than 5-6 words.
+
+    # APPROACH (Think step by step):
+    1. First, examine all memories that contain information related to the question
+    2. Examine the timestamps and content of these memories carefully
+    3. Look for explicit mentions of dates, times, locations, or events that answer the question
+    4. If the answer requires calculation (e.g., converting relative time references), show your work
+    5. Formulate a precise, concise answer based solely on the evidence in the memories
+    6. Double-check that your answer directly addresses the question asked
+    7. Ensure your final answer is specific and avoids vague time references
+
+    Memories:
+
+    {{memories}}
+
+    Question: {{question}}
+    Answer:
+    """

evaluation/run_experiments.py

@@ -0,0 +1,75 @@
+import argparse
+import os
+
+from src.langmem import LangMemManager
+from src.memzero.add import MemoryADD
+from src.memzero.search import MemorySearch
+from src.openai.predict import OpenAIPredict
+from src.rag import RAGManager
+from src.utils import METHODS, TECHNIQUES
+from src.zep.add import ZepAdd
+from src.zep.search import ZepSearch
+
+
+class Experiment:
+    def __init__(self, technique_type, chunk_size):
+        self.technique_type = technique_type
+        self.chunk_size = chunk_size
+
+    def run(self):
+        print(f"Running experiment with technique: {self.technique_type}, chunk size: {self.chunk_size}")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Run memory experiments")
+    parser.add_argument("--technique_type", choices=TECHNIQUES, default="mem0", help="Memory technique to use")
+    parser.add_argument("--method", choices=METHODS, default="add", help="Method to use")
+    parser.add_argument("--chunk_size", type=int, default=1000, help="Chunk size for processing")
+    parser.add_argument("--output_folder", type=str, default="results/", help="Output path for results")
+    parser.add_argument("--top_k", type=int, default=30, help="Number of top memories to retrieve")
+    parser.add_argument("--filter_memories", action="store_true", default=False, help="Whether to filter memories")
+    parser.add_argument("--is_graph", action="store_true", default=False, help="Whether to use graph-based search")
+    parser.add_argument("--num_chunks", type=int, default=1, help="Number of chunks to process")
+
+    args = parser.parse_args()
+
+    # Add your experiment logic here
+    print(f"Running experiments with technique: {args.technique_type}, chunk size: {args.chunk_size}")
+
+    if args.technique_type == "mem0":
+        if args.method == "add":
+            memory_manager = MemoryADD(data_path="dataset/locomo10.json", is_graph=args.is_graph)
+            memory_manager.process_all_conversations()
+        elif args.method == "search":
+            output_file_path = os.path.join(
+                args.output_folder,
+                f"mem0_results_top_{args.top_k}_filter_{args.filter_memories}_graph_{args.is_graph}.json",
+            )
+            memory_searcher = MemorySearch(output_file_path, args.top_k, args.filter_memories, args.is_graph)
+            memory_searcher.process_data_file("dataset/locomo10.json")
+    elif args.technique_type == "rag":
+        output_file_path = os.path.join(args.output_folder, f"rag_results_{args.chunk_size}_k{args.num_chunks}.json")
+        rag_manager = RAGManager(data_path="dataset/locomo10_rag.json", chunk_size=args.chunk_size, k=args.num_chunks)
+        rag_manager.process_all_conversations(output_file_path)
+    elif args.technique_type == "langmem":
+        output_file_path = os.path.join(args.output_folder, "langmem_results.json")
+        langmem_manager = LangMemManager(dataset_path="dataset/locomo10_rag.json")
+        langmem_manager.process_all_conversations(output_file_path)
+    elif args.technique_type == "zep":
+        if args.method == "add":
+            zep_manager = ZepAdd(data_path="dataset/locomo10.json")
+            zep_manager.process_all_conversations("1")
+        elif args.method == "search":
+            output_file_path = os.path.join(args.output_folder, "zep_search_results.json")
+            zep_manager = ZepSearch()
+            zep_manager.process_data_file("dataset/locomo10.json", "1", output_file_path)
+    elif args.technique_type == "openai":
+        output_file_path = os.path.join(args.output_folder, "openai_results.json")
+        openai_manager = OpenAIPredict()
+        openai_manager.process_data_file("dataset/locomo10.json", output_file_path)
+    else:
+        raise ValueError(f"Invalid technique type: {args.technique_type}")
+
+
+if __name__ == "__main__":
+    main()

evaluation/src/langmem.py

@@ -0,0 +1,185 @@
+import json
+import multiprocessing as mp
+import os
+import time
+from collections import defaultdict
+
+from dotenv import load_dotenv
+from jinja2 import Template
+from langgraph.checkpoint.memory import MemorySaver
+from langgraph.prebuilt import create_react_agent
+from langgraph.store.memory import InMemoryStore
+from langgraph.utils.config import get_store
+from langmem import create_manage_memory_tool, create_search_memory_tool
+from openai import OpenAI
+from prompts import ANSWER_PROMPT
+from tqdm import tqdm
+
+load_dotenv()
+
+client = OpenAI()
+
+ANSWER_PROMPT_TEMPLATE = Template(ANSWER_PROMPT)
+
+
+def get_answer(question, speaker_1_user_id, speaker_1_memories, speaker_2_user_id, speaker_2_memories):
+    prompt = ANSWER_PROMPT_TEMPLATE.render(
+        question=question,
+        speaker_1_user_id=speaker_1_user_id,
+        speaker_1_memories=speaker_1_memories,
+        speaker_2_user_id=speaker_2_user_id,
+        speaker_2_memories=speaker_2_memories,
+    )
+
+    t1 = time.time()
+    response = client.chat.completions.create(
+        model=os.getenv("MODEL"), messages=[{"role": "system", "content": prompt}], temperature=0.0
+    )
+    t2 = time.time()
+    return response.choices[0].message.content, t2 - t1
+
+
+def prompt(state):
+    """Prepare the messages for the LLM."""
+    store = get_store()
+    memories = store.search(
+        ("memories",),
+        query=state["messages"][-1].content,
+    )
+    system_msg = f"""You are a helpful assistant.
+
+## Memories
+<memories>
+{memories}
+</memories>
+"""
+    return [{"role": "system", "content": system_msg}, *state["messages"]]
+
+
+class LangMem:
+    def __init__(
+        self,
+    ):
+        self.store = InMemoryStore(
+            index={
+                "dims": 1536,
+                "embed": f"openai:{os.getenv('EMBEDDING_MODEL')}",
+            }
+        )
+        self.checkpointer = MemorySaver()  # Checkpoint graph state
+
+        self.agent = create_react_agent(
+            f"openai:{os.getenv('MODEL')}",
+            prompt=prompt,
+            tools=[
+                create_manage_memory_tool(namespace=("memories",)),
+                create_search_memory_tool(namespace=("memories",)),
+            ],
+            store=self.store,
+            checkpointer=self.checkpointer,
+        )
+
+    def add_memory(self, message, config):
+        return self.agent.invoke({"messages": [{"role": "user", "content": message}]}, config=config)
+
+    def search_memory(self, query, config):
+        try:
+            t1 = time.time()
+            response = self.agent.invoke({"messages": [{"role": "user", "content": query}]}, config=config)
+            t2 = time.time()
+            return response["messages"][-1].content, t2 - t1
+        except Exception as e:
+            print(f"Error in search_memory: {e}")
+            return "", t2 - t1
+
+
+class LangMemManager:
+    def __init__(self, dataset_path):
+        self.dataset_path = dataset_path
+        with open(self.dataset_path, "r") as f:
+            self.data = json.load(f)
+
+    def process_all_conversations(self, output_file_path):
+        OUTPUT = defaultdict(list)
+
+        # Process conversations in parallel with multiple workers
+        def process_conversation(key_value_pair):
+            key, value = key_value_pair
+            result = defaultdict(list)
+
+            chat_history = value["conversation"]
+            questions = value["question"]
+
+            agent1 = LangMem()
+            agent2 = LangMem()
+            config = {"configurable": {"thread_id": f"thread-{key}"}}
+            speakers = set()
+
+            # Identify speakers
+            for conv in chat_history:
+                speakers.add(conv["speaker"])
+
+            if len(speakers) != 2:
+                raise ValueError(f"Expected 2 speakers, got {len(speakers)}")
+
+            speaker1 = list(speakers)[0]
+            speaker2 = list(speakers)[1]
+
+            # Add memories for each message
+            for conv in tqdm(chat_history, desc=f"Processing messages {key}", leave=False):
+                message = f"{conv['timestamp']} | {conv['speaker']}: {conv['text']}"
+                if conv["speaker"] == speaker1:
+                    agent1.add_memory(message, config)
+                elif conv["speaker"] == speaker2:
+                    agent2.add_memory(message, config)
+                else:
+                    raise ValueError(f"Expected speaker1 or speaker2, got {conv['speaker']}")
+
+            # Process questions
+            for q in tqdm(questions, desc=f"Processing questions {key}", leave=False):
+                category = q["category"]
+
+                if int(category) == 5:
+                    continue
+
+                answer = q["answer"]
+                question = q["question"]
+                response1, speaker1_memory_time = agent1.search_memory(question, config)
+                response2, speaker2_memory_time = agent2.search_memory(question, config)
+
+                generated_answer, response_time = get_answer(question, speaker1, response1, speaker2, response2)
+
+                result[key].append(
+                    {
+                        "question": question,
+                        "answer": answer,
+                        "response1": response1,
+                        "response2": response2,
+                        "category": category,
+                        "speaker1_memory_time": speaker1_memory_time,
+                        "speaker2_memory_time": speaker2_memory_time,
+                        "response_time": response_time,
+                        "response": generated_answer,
+                    }
+                )
+
+            return result
+
+        # Use multiprocessing to process conversations in parallel
+        with mp.Pool(processes=10) as pool:
+            results = list(
+                tqdm(
+                    pool.imap(process_conversation, list(self.data.items())),
+                    total=len(self.data),
+                    desc="Processing conversations",
+                )
+            )
+
+        # Combine results from all workers
+        for result in results:
+            for key, items in result.items():
+                OUTPUT[key].extend(items)
+
+        # Save final results
+        with open(output_file_path, "w") as f:
+            json.dump(OUTPUT, f, indent=4)

evaluation/src/memzero/add.py

@@ -0,0 +1,141 @@
+import json
+import os
+import threading
+import time
+from concurrent.futures import ThreadPoolExecutor
+
+from dotenv import load_dotenv
+from tqdm import tqdm
+
+from mem0 import MemoryClient
+
+load_dotenv()
+
+
+# Update custom instructions
+custom_instructions = """
+Generate personal memories that follow these guidelines:
+
+1. Each memory should be self-contained with complete context, including:
+   - The person's name, do not use "user" while creating memories
+   - Personal details (career aspirations, hobbies, life circumstances)
+   - Emotional states and reactions
+   - Ongoing journeys or future plans
+   - Specific dates when events occurred
+
+2. Include meaningful personal narratives focusing on:
+   - Identity and self-acceptance journeys
+   - Family planning and parenting
+   - Creative outlets and hobbies
+   - Mental health and self-care activities
+   - Career aspirations and education goals
+   - Important life events and milestones
+
+3. Make each memory rich with specific details rather than general statements
+   - Include timeframes (exact dates when possible)
+   - Name specific activities (e.g., "charity race for mental health" rather than just "exercise")
+   - Include emotional context and personal growth elements
+
+4. Extract memories only from user messages, not incorporating assistant responses
+
+5. Format each memory as a paragraph with a clear narrative structure that captures the person's experience, challenges, and aspirations
+"""
+
+
+class MemoryADD:
+    def __init__(self, data_path=None, batch_size=2, is_graph=False):
+        self.mem0_client = MemoryClient(
+            api_key=os.getenv("MEM0_API_KEY"),
+            org_id=os.getenv("MEM0_ORGANIZATION_ID"),
+            project_id=os.getenv("MEM0_PROJECT_ID"),
+        )
+
+        self.mem0_client.update_project(custom_instructions=custom_instructions)
+        self.batch_size = batch_size
+        self.data_path = data_path
+        self.data = None
+        self.is_graph = is_graph
+        if data_path:
+            self.load_data()
+
+    def load_data(self):
+        with open(self.data_path, "r") as f:
+            self.data = json.load(f)
+        return self.data
+
+    def add_memory(self, user_id, message, metadata, retries=3):
+        for attempt in range(retries):
+            try:
+                _ = self.mem0_client.add(
+                    message, user_id=user_id, version="v2", metadata=metadata, enable_graph=self.is_graph
+                )
+                return
+            except Exception as e:
+                if attempt < retries - 1:
+                    time.sleep(1)  # Wait before retrying
+                    continue
+                else:
+                    raise e
+
+    def add_memories_for_speaker(self, speaker, messages, timestamp, desc):
+        for i in tqdm(range(0, len(messages), self.batch_size), desc=desc):
+            batch_messages = messages[i : i + self.batch_size]
+            self.add_memory(speaker, batch_messages, metadata={"timestamp": timestamp})
+
+    def process_conversation(self, item, idx):
+        conversation = item["conversation"]
+        speaker_a = conversation["speaker_a"]
+        speaker_b = conversation["speaker_b"]
+
+        speaker_a_user_id = f"{speaker_a}_{idx}"
+        speaker_b_user_id = f"{speaker_b}_{idx}"
+
+        # delete all memories for the two users
+        self.mem0_client.delete_all(user_id=speaker_a_user_id)
+        self.mem0_client.delete_all(user_id=speaker_b_user_id)
+
+        for key in conversation.keys():
+            if key in ["speaker_a", "speaker_b"] or "date" in key or "timestamp" in key:
+                continue
+
+            date_time_key = key + "_date_time"
+            timestamp = conversation[date_time_key]
+            chats = conversation[key]
+
+            messages = []
+            messages_reverse = []
+            for chat in chats:
+                if chat["speaker"] == speaker_a:
+                    messages.append({"role": "user", "content": f"{speaker_a}: {chat['text']}"})
+                    messages_reverse.append({"role": "assistant", "content": f"{speaker_a}: {chat['text']}"})
+                elif chat["speaker"] == speaker_b:
+                    messages.append({"role": "assistant", "content": f"{speaker_b}: {chat['text']}"})
+                    messages_reverse.append({"role": "user", "content": f"{speaker_b}: {chat['text']}"})
+                else:
+                    raise ValueError(f"Unknown speaker: {chat['speaker']}")
+
+            # add memories for the two users on different threads
+            thread_a = threading.Thread(
+                target=self.add_memories_for_speaker,
+                args=(speaker_a_user_id, messages, timestamp, "Adding Memories for Speaker A"),
+            )
+            thread_b = threading.Thread(
+                target=self.add_memories_for_speaker,
+                args=(speaker_b_user_id, messages_reverse, timestamp, "Adding Memories for Speaker B"),
+            )
+
+            thread_a.start()
+            thread_b.start()
+            thread_a.join()
+            thread_b.join()
+
+        print("Messages added successfully")
+
+    def process_all_conversations(self, max_workers=10):
+        if not self.data:
+            raise ValueError("No data loaded. Please set data_path and call load_data() first.")
+        with ThreadPoolExecutor(max_workers=max_workers) as executor:
+            futures = [executor.submit(self.process_conversation, item, idx) for idx, item in enumerate(self.data)]
+
+            for future in futures:
+                future.result()

evaluation/src/memzero/search.py

@@ -0,0 +1,215 @@
+import json
+import os
+import time
+from collections import defaultdict
+from concurrent.futures import ThreadPoolExecutor
+
+from dotenv import load_dotenv
+from jinja2 import Template
+from openai import OpenAI
+from prompts import ANSWER_PROMPT, ANSWER_PROMPT_GRAPH
+from tqdm import tqdm
+
+from mem0 import MemoryClient
+
+load_dotenv()
+
+
+class MemorySearch:
+    def __init__(self, output_path="results.json", top_k=10, filter_memories=False, is_graph=False):
+        self.mem0_client = MemoryClient(
+            api_key=os.getenv("MEM0_API_KEY"),
+            org_id=os.getenv("MEM0_ORGANIZATION_ID"),
+            project_id=os.getenv("MEM0_PROJECT_ID"),
+        )
+        self.top_k = top_k
+        self.openai_client = OpenAI()
+        self.results = defaultdict(list)
+        self.output_path = output_path
+        self.filter_memories = filter_memories
+        self.is_graph = is_graph
+
+        if self.is_graph:
+            self.ANSWER_PROMPT = ANSWER_PROMPT_GRAPH
+        else:
+            self.ANSWER_PROMPT = ANSWER_PROMPT
+
+    def search_memory(self, user_id, query, max_retries=3, retry_delay=1):
+        start_time = time.time()
+        retries = 0
+        while retries < max_retries:
+            try:
+                if self.is_graph:
+                    print("Searching with graph")
+                    memories = self.mem0_client.search(
+                        query,
+                        user_id=user_id,
+                        top_k=self.top_k,
+                        filter_memories=self.filter_memories,
+                        enable_graph=True,
+                        output_format="v1.1",
+                    )
+                else:
+                    memories = self.mem0_client.search(
+                        query, user_id=user_id, top_k=self.top_k, filter_memories=self.filter_memories
+                    )
+                break
+            except Exception as e:
+                print("Retrying...")
+                retries += 1
+                if retries >= max_retries:
+                    raise e
+                time.sleep(retry_delay)
+
+        end_time = time.time()
+        if not self.is_graph:
+            semantic_memories = [
+                {
+                    "memory": memory["memory"],
+                    "timestamp": memory["metadata"]["timestamp"],
+                    "score": round(memory["score"], 2),
+                }
+                for memory in memories
+            ]
+            graph_memories = None
+        else:
+            semantic_memories = [
+                {
+                    "memory": memory["memory"],
+                    "timestamp": memory["metadata"]["timestamp"],
+                    "score": round(memory["score"], 2),
+                }
+                for memory in memories["results"]
+            ]
+            graph_memories = [
+                {"source": relation["source"], "relationship": relation["relationship"], "target": relation["target"]}
+                for relation in memories["relations"]
+            ]
+        return semantic_memories, graph_memories, end_time - start_time
+
+    def answer_question(self, speaker_1_user_id, speaker_2_user_id, question, answer, category):
+        speaker_1_memories, speaker_1_graph_memories, speaker_1_memory_time = self.search_memory(
+            speaker_1_user_id, question
+        )
+        speaker_2_memories, speaker_2_graph_memories, speaker_2_memory_time = self.search_memory(
+            speaker_2_user_id, question
+        )
+
+        search_1_memory = [f"{item['timestamp']}: {item['memory']}" for item in speaker_1_memories]
+        search_2_memory = [f"{item['timestamp']}: {item['memory']}" for item in speaker_2_memories]
+
+        template = Template(self.ANSWER_PROMPT)
+        answer_prompt = template.render(
+            speaker_1_user_id=speaker_1_user_id.split("_")[0],
+            speaker_2_user_id=speaker_2_user_id.split("_")[0],
+            speaker_1_memories=json.dumps(search_1_memory, indent=4),
+            speaker_2_memories=json.dumps(search_2_memory, indent=4),
+            speaker_1_graph_memories=json.dumps(speaker_1_graph_memories, indent=4),
+            speaker_2_graph_memories=json.dumps(speaker_2_graph_memories, indent=4),
+            question=question,
+        )
+
+        t1 = time.time()
+        response = self.openai_client.chat.completions.create(
+            model=os.getenv("MODEL"), messages=[{"role": "system", "content": answer_prompt}], temperature=0.0
+        )
+        t2 = time.time()
+        response_time = t2 - t1
+        return (
+            response.choices[0].message.content,
+            speaker_1_memories,
+            speaker_2_memories,
+            speaker_1_memory_time,
+            speaker_2_memory_time,
+            speaker_1_graph_memories,
+            speaker_2_graph_memories,
+            response_time,
+        )
+
+    def process_question(self, val, speaker_a_user_id, speaker_b_user_id):
+        question = val.get("question", "")
+        answer = val.get("answer", "")
+        category = val.get("category", -1)
+        evidence = val.get("evidence", [])
+        adversarial_answer = val.get("adversarial_answer", "")
+
+        (
+            response,
+            speaker_1_memories,
+            speaker_2_memories,
+            speaker_1_memory_time,
+            speaker_2_memory_time,
+            speaker_1_graph_memories,
+            speaker_2_graph_memories,
+            response_time,
+        ) = self.answer_question(speaker_a_user_id, speaker_b_user_id, question, answer, category)
+
+        result = {
+            "question": question,
+            "answer": answer,
+            "category": category,
+            "evidence": evidence,
+            "response": response,
+            "adversarial_answer": adversarial_answer,
+            "speaker_1_memories": speaker_1_memories,
+            "speaker_2_memories": speaker_2_memories,
+            "num_speaker_1_memories": len(speaker_1_memories),
+            "num_speaker_2_memories": len(speaker_2_memories),
+            "speaker_1_memory_time": speaker_1_memory_time,
+            "speaker_2_memory_time": speaker_2_memory_time,
+            "speaker_1_graph_memories": speaker_1_graph_memories,
+            "speaker_2_graph_memories": speaker_2_graph_memories,
+            "response_time": response_time,
+        }
+
+        # Save results after each question is processed
+        with open(self.output_path, "w") as f:
+            json.dump(self.results, f, indent=4)
+
+        return result
+
+    def process_data_file(self, file_path):
+        with open(file_path, "r") as f:
+            data = json.load(f)
+
+        for idx, item in tqdm(enumerate(data), total=len(data), desc="Processing conversations"):
+            qa = item["qa"]
+            conversation = item["conversation"]
+            speaker_a = conversation["speaker_a"]
+            speaker_b = conversation["speaker_b"]
+
+            speaker_a_user_id = f"{speaker_a}_{idx}"
+            speaker_b_user_id = f"{speaker_b}_{idx}"
+
+            for question_item in tqdm(
+                qa, total=len(qa), desc=f"Processing questions for conversation {idx}", leave=False
+            ):
+                result = self.process_question(question_item, speaker_a_user_id, speaker_b_user_id)
+                self.results[idx].append(result)
+
+                # Save results after each question is processed
+                with open(self.output_path, "w") as f:
+                    json.dump(self.results, f, indent=4)
+
+        # Final save at the end
+        with open(self.output_path, "w") as f:
+            json.dump(self.results, f, indent=4)
+
+    def process_questions_parallel(self, qa_list, speaker_a_user_id, speaker_b_user_id, max_workers=1):
+        def process_single_question(val):
+            result = self.process_question(val, speaker_a_user_id, speaker_b_user_id)
+            # Save results after each question is processed
+            with open(self.output_path, "w") as f:
+                json.dump(self.results, f, indent=4)
+            return result
+
+        with ThreadPoolExecutor(max_workers=max_workers) as executor:
+            results = list(
+                tqdm(executor.map(process_single_question, qa_list), total=len(qa_list), desc="Answering Questions")
+            )
+
+        # Final save at the end
+        with open(self.output_path, "w") as f:
+            json.dump(self.results, f, indent=4)
+
+        return results

evaluation/src/openai/predict.py

@@ -0,0 +1,131 @@
+import argparse
+import json
+import os
+import time
+from collections import defaultdict
+
+from dotenv import load_dotenv
+from jinja2 import Template
+from openai import OpenAI
+from tqdm import tqdm
+
+load_dotenv()
+
+
+ANSWER_PROMPT = """
+    You are an intelligent memory assistant tasked with retrieving accurate information from conversation memories.
+
+    # CONTEXT:
+    You have access to memories from a conversation. These memories contain
+    timestamped information that may be relevant to answering the question.
+
+    # INSTRUCTIONS:
+    1. Carefully analyze all provided memories
+    2. Pay special attention to the timestamps to determine the answer
+    3. If the question asks about a specific event or fact, look for direct evidence in the memories
+    4. If the memories contain contradictory information, prioritize the most recent memory
+    5. If there is a question about time references (like "last year", "two months ago", etc.), 
+       calculate the actual date based on the memory timestamp. For example, if a memory from 
+       4 May 2022 mentions "went to India last year," then the trip occurred in 2021.
+    6. Always convert relative time references to specific dates, months, or years. For example, 
+       convert "last year" to "2022" or "two months ago" to "March 2023" based on the memory 
+       timestamp. Ignore the reference while answering the question.
+    7. Focus only on the content of the memories. Do not confuse character 
+       names mentioned in memories with the actual users who created those memories.
+    8. The answer should be less than 5-6 words.
+
+    # APPROACH (Think step by step):
+    1. First, examine all memories that contain information related to the question
+    2. Examine the timestamps and content of these memories carefully
+    3. Look for explicit mentions of dates, times, locations, or events that answer the question
+    4. If the answer requires calculation (e.g., converting relative time references), show your work
+    5. Formulate a precise, concise answer based solely on the evidence in the memories
+    6. Double-check that your answer directly addresses the question asked
+    7. Ensure your final answer is specific and avoids vague time references
+
+    Memories:
+
+    {{memories}}
+
+    Question: {{question}}
+    Answer:
+    """
+
+
+class OpenAIPredict:
+    def __init__(self, model="gpt-4o-mini"):
+        self.model = model
+        self.openai_client = OpenAI()
+        self.results = defaultdict(list)
+
+    def search_memory(self, idx):
+        with open(f"memories/{idx}.txt", "r") as file:
+            memories = file.read()
+
+        return memories, 0
+
+    def process_question(self, val, idx):
+        question = val.get("question", "")
+        answer = val.get("answer", "")
+        category = val.get("category", -1)
+        evidence = val.get("evidence", [])
+        adversarial_answer = val.get("adversarial_answer", "")
+
+        response, search_memory_time, response_time, context = self.answer_question(idx, question)
+
+        result = {
+            "question": question,
+            "answer": answer,
+            "category": category,
+            "evidence": evidence,
+            "response": response,
+            "adversarial_answer": adversarial_answer,
+            "search_memory_time": search_memory_time,
+            "response_time": response_time,
+            "context": context,
+        }
+
+        return result
+
+    def answer_question(self, idx, question):
+        memories, search_memory_time = self.search_memory(idx)
+
+        template = Template(ANSWER_PROMPT)
+        answer_prompt = template.render(memories=memories, question=question)
+
+        t1 = time.time()
+        response = self.openai_client.chat.completions.create(
+            model=os.getenv("MODEL"), messages=[{"role": "system", "content": answer_prompt}], temperature=0.0
+        )
+        t2 = time.time()
+        response_time = t2 - t1
+        return response.choices[0].message.content, search_memory_time, response_time, memories
+
+    def process_data_file(self, file_path, output_file_path):
+        with open(file_path, "r") as f:
+            data = json.load(f)
+
+        for idx, item in tqdm(enumerate(data), total=len(data), desc="Processing conversations"):
+            qa = item["qa"]
+
+            for question_item in tqdm(
+                qa, total=len(qa), desc=f"Processing questions for conversation {idx}", leave=False
+            ):
+                result = self.process_question(question_item, idx)
+                self.results[idx].append(result)
+
+                # Save results after each question is processed
+                with open(output_file_path, "w") as f:
+                    json.dump(self.results, f, indent=4)
+
+        # Final save at the end
+        with open(output_file_path, "w") as f:
+            json.dump(self.results, f, indent=4)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--output_file_path", type=str, required=True)
+    args = parser.parse_args()
+    openai_predict = OpenAIPredict()
+    openai_predict.process_data_file("../../dataset/locomo10.json", args.output_file_path)

evaluation/src/rag.py

@@ -0,0 +1,183 @@
+import json
+import os
+import time
+from collections import defaultdict
+
+import numpy as np
+import tiktoken
+from dotenv import load_dotenv
+from jinja2 import Template
+from openai import OpenAI
+from tqdm import tqdm
+
+load_dotenv()
+
+PROMPT = """
+# Question: 
+{{QUESTION}}
+
+# Context: 
+{{CONTEXT}}
+
+# Short answer:
+"""
+
+
+class RAGManager:
+    def __init__(self, data_path="dataset/locomo10_rag.json", chunk_size=500, k=1):
+        self.model = os.getenv("MODEL")
+        self.client = OpenAI()
+        self.data_path = data_path
+        self.chunk_size = chunk_size
+        self.k = k
+
+    def generate_response(self, question, context):
+        template = Template(PROMPT)
+        prompt = template.render(CONTEXT=context, QUESTION=question)
+
+        max_retries = 3
+        retries = 0
+
+        while retries <= max_retries:
+            try:
+                t1 = time.time()
+                response = self.client.chat.completions.create(
+                    model=self.model,
+                    messages=[
+                        {
+                            "role": "system",
+                            "content": "You are a helpful assistant that can answer "
+                            "questions based on the provided context."
+                            "If the question involves timing, use the conversation date for reference."
+                            "Provide the shortest possible answer."
+                            "Use words directly from the conversation when possible."
+                            "Avoid using subjects in your answer.",
+                        },
+                        {"role": "user", "content": prompt},
+                    ],
+                    temperature=0,
+                )
+                t2 = time.time()
+                return response.choices[0].message.content.strip(), t2 - t1
+            except Exception as e:
+                retries += 1
+                if retries > max_retries:
+                    raise e
+                time.sleep(1)  # Wait before retrying
+
+    def clean_chat_history(self, chat_history):
+        cleaned_chat_history = ""
+        for c in chat_history:
+            cleaned_chat_history += f"{c['timestamp']} | {c['speaker']}: {c['text']}\n"
+
+        return cleaned_chat_history
+
+    def calculate_embedding(self, document):
+        response = self.client.embeddings.create(model=os.getenv("EMBEDDING_MODEL"), input=document)
+        return response.data[0].embedding
+
+    def calculate_similarity(self, embedding1, embedding2):
+        return np.dot(embedding1, embedding2) / (np.linalg.norm(embedding1) * np.linalg.norm(embedding2))
+
+    def search(self, query, chunks, embeddings, k=1):
+        """
+        Search for the top-k most similar chunks to the query.
+
+        Args:
+            query: The query string
+            chunks: List of text chunks
+            embeddings: List of embeddings for each chunk
+            k: Number of top chunks to return (default: 1)
+
+        Returns:
+            combined_chunks: The combined text of the top-k chunks
+            search_time: Time taken for the search
+        """
+        t1 = time.time()
+        query_embedding = self.calculate_embedding(query)
+        similarities = [self.calculate_similarity(query_embedding, embedding) for embedding in embeddings]
+
+        # Get indices of top-k most similar chunks
+        if k == 1:
+            # Original behavior - just get the most similar chunk
+            top_indices = [np.argmax(similarities)]
+        else:
+            # Get indices of top-k chunks
+            top_indices = np.argsort(similarities)[-k:][::-1]
+
+        # Combine the top-k chunks
+        combined_chunks = "\n<->\n".join([chunks[i] for i in top_indices])
+
+        t2 = time.time()
+        return combined_chunks, t2 - t1
+
+    def create_chunks(self, chat_history, chunk_size=500):
+        """
+        Create chunks using tiktoken for more accurate token counting
+        """
+        # Get the encoding for the model
+        encoding = tiktoken.encoding_for_model(os.getenv("EMBEDDING_MODEL"))
+
+        documents = self.clean_chat_history(chat_history)
+
+        if chunk_size == -1:
+            return [documents], []
+
+        chunks = []
+
+        # Encode the document
+        tokens = encoding.encode(documents)
+
+        # Split into chunks based on token count
+        for i in range(0, len(tokens), chunk_size):
+            chunk_tokens = tokens[i : i + chunk_size]
+            chunk = encoding.decode(chunk_tokens)
+            chunks.append(chunk)
+
+        embeddings = []
+        for chunk in chunks:
+            embedding = self.calculate_embedding(chunk)
+            embeddings.append(embedding)
+
+        return chunks, embeddings
+
+    def process_all_conversations(self, output_file_path):
+        with open(self.data_path, "r") as f:
+            data = json.load(f)
+
+        FINAL_RESULTS = defaultdict(list)
+        for key, value in tqdm(data.items(), desc="Processing conversations"):
+            chat_history = value["conversation"]
+            questions = value["question"]
+
+            chunks, embeddings = self.create_chunks(chat_history, self.chunk_size)
+
+            for item in tqdm(questions, desc="Answering questions", leave=False):
+                question = item["question"]
+                answer = item.get("answer", "")
+                category = item["category"]
+
+                if self.chunk_size == -1:
+                    context = chunks[0]
+                    search_time = 0
+                else:
+                    context, search_time = self.search(question, chunks, embeddings, k=self.k)
+                response, response_time = self.generate_response(question, context)
+
+                FINAL_RESULTS[key].append(
+                    {
+                        "question": question,
+                        "answer": answer,
+                        "category": category,
+                        "context": context,
+                        "response": response,
+                        "search_time": search_time,
+                        "response_time": response_time,
+                    }
+                )
+                with open(output_file_path, "w+") as f:
+                    json.dump(FINAL_RESULTS, f, indent=4)
+
+        # Save results
+        with open(output_file_path, "w+") as f:
+            json.dump(FINAL_RESULTS, f, indent=4)

evaluation/src/utils.py

@@ -0,0 +1,3 @@
+TECHNIQUES = ["mem0", "rag", "langmem", "zep", "openai"]
+
+METHODS = ["add", "search"]

evaluation/src/zep/add.py

@@ -0,0 +1,76 @@
+import argparse
+import json
+import os
+
+from dotenv import load_dotenv
+from tqdm import tqdm
+from zep_cloud import Message
+from zep_cloud.client import Zep
+
+load_dotenv()
+
+
+class ZepAdd:
+    def __init__(self, data_path=None):
+        self.zep_client = Zep(api_key=os.getenv("ZEP_API_KEY"))
+        self.data_path = data_path
+        self.data = None
+        if data_path:
+            self.load_data()
+
+    def load_data(self):
+        with open(self.data_path, "r") as f:
+            self.data = json.load(f)
+        return self.data
+
+    def process_conversation(self, run_id, item, idx):
+        conversation = item["conversation"]
+
+        user_id = f"run_id_{run_id}_experiment_user_{idx}"
+        session_id = f"run_id_{run_id}_experiment_session_{idx}"
+
+        # # delete all memories for the two users
+        # self.zep_client.user.delete(user_id=user_id)
+        # self.zep_client.memory.delete(session_id=session_id)
+
+        self.zep_client.user.add(user_id=user_id)
+        self.zep_client.memory.add_session(
+            user_id=user_id,
+            session_id=session_id,
+        )
+
+        print("Starting to add memories... for user", user_id)
+        for key in tqdm(conversation.keys(), desc=f"Processing user {user_id}"):
+            if key in ["speaker_a", "speaker_b"] or "date" in key:
+                continue
+
+            date_time_key = key + "_date_time"
+            timestamp = conversation[date_time_key]
+            chats = conversation[key]
+
+            for chat in tqdm(chats, desc=f"Adding chats for {key}", leave=False):
+                self.zep_client.memory.add(
+                    session_id=session_id,
+                    messages=[
+                        Message(
+                            role=chat["speaker"],
+                            role_type="user",
+                            content=f"{timestamp}: {chat['text']}",
+                        )
+                    ],
+                )
+
+    def process_all_conversations(self, run_id):
+        if not self.data:
+            raise ValueError("No data loaded. Please set data_path and call load_data() first.")
+        for idx, item in tqdm(enumerate(self.data)):
+            if idx == 0:
+                self.process_conversation(run_id, item, idx)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--run_id", type=str, required=True)
+    args = parser.parse_args()
+    zep_add = ZepAdd(data_path="../../dataset/locomo10.json")
+    zep_add.process_all_conversations(args.run_id)

evaluation/src/zep/search.py

@@ -0,0 +1,140 @@
+import argparse
+import json
+import os
+import time
+from collections import defaultdict
+
+from dotenv import load_dotenv
+from jinja2 import Template
+from openai import OpenAI
+from prompts import ANSWER_PROMPT_ZEP
+from tqdm import tqdm
+from zep_cloud import EntityEdge, EntityNode
+from zep_cloud.client import Zep
+
+load_dotenv()
+
+TEMPLATE = """
+FACTS and ENTITIES represent relevant context to the current conversation.
+
+# These are the most relevant facts and their valid date ranges
+# format: FACT (Date range: from - to)
+
+{facts}
+
+
+# These are the most relevant entities
+# ENTITY_NAME: entity summary
+
+{entities}
+
+"""
+
+
+class ZepSearch:
+    def __init__(self):
+        self.zep_client = Zep(api_key=os.getenv("ZEP_API_KEY"))
+        self.results = defaultdict(list)
+        self.openai_client = OpenAI()
+
+    def format_edge_date_range(self, edge: EntityEdge) -> str:
+        # return f"{datetime(edge.valid_at).strftime('%Y-%m-%d %H:%M:%S') if edge.valid_at else 'date unknown'} - {(edge.invalid_at.strftime('%Y-%m-%d %H:%M:%S') if edge.invalid_at else 'present')}"
+        return f"{edge.valid_at if edge.valid_at else 'date unknown'} - {(edge.invalid_at if edge.invalid_at else 'present')}"
+
+    def compose_search_context(self, edges: list[EntityEdge], nodes: list[EntityNode]) -> str:
+        facts = [f"  - {edge.fact} ({self.format_edge_date_range(edge)})" for edge in edges]
+        entities = [f"  - {node.name}: {node.summary}" for node in nodes]
+        return TEMPLATE.format(facts="\n".join(facts), entities="\n".join(entities))
+
+    def search_memory(self, run_id, idx, query, max_retries=3, retry_delay=1):
+        start_time = time.time()
+        retries = 0
+        while retries < max_retries:
+            try:
+                user_id = f"run_id_{run_id}_experiment_user_{idx}"
+                edges_results = (
+                    self.zep_client.graph.search(
+                        user_id=user_id, reranker="cross_encoder", query=query, scope="edges", limit=20
+                    )
+                ).edges
+                node_results = (
+                    self.zep_client.graph.search(user_id=user_id, reranker="rrf", query=query, scope="nodes", limit=20)
+                ).nodes
+                context = self.compose_search_context(edges_results, node_results)
+                break
+            except Exception as e:
+                print("Retrying...")
+                retries += 1
+                if retries >= max_retries:
+                    raise e
+                time.sleep(retry_delay)
+
+        end_time = time.time()
+
+        return context, end_time - start_time
+
+    def process_question(self, run_id, val, idx):
+        question = val.get("question", "")
+        answer = val.get("answer", "")
+        category = val.get("category", -1)
+        evidence = val.get("evidence", [])
+        adversarial_answer = val.get("adversarial_answer", "")
+
+        response, search_memory_time, response_time, context = self.answer_question(run_id, idx, question)
+
+        result = {
+            "question": question,
+            "answer": answer,
+            "category": category,
+            "evidence": evidence,
+            "response": response,
+            "adversarial_answer": adversarial_answer,
+            "search_memory_time": search_memory_time,
+            "response_time": response_time,
+            "context": context,
+        }
+
+        return result
+
+    def answer_question(self, run_id, idx, question):
+        context, search_memory_time = self.search_memory(run_id, idx, question)
+
+        template = Template(ANSWER_PROMPT_ZEP)
+        answer_prompt = template.render(memories=context, question=question)
+
+        t1 = time.time()
+        response = self.openai_client.chat.completions.create(
+            model=os.getenv("MODEL"), messages=[{"role": "system", "content": answer_prompt}], temperature=0.0
+        )
+        t2 = time.time()
+        response_time = t2 - t1
+        return response.choices[0].message.content, search_memory_time, response_time, context
+
+    def process_data_file(self, file_path, run_id, output_file_path):
+        with open(file_path, "r") as f:
+            data = json.load(f)
+
+        for idx, item in tqdm(enumerate(data), total=len(data), desc="Processing conversations"):
+            qa = item["qa"]
+
+            for question_item in tqdm(
+                qa, total=len(qa), desc=f"Processing questions for conversation {idx}", leave=False
+            ):
+                result = self.process_question(run_id, question_item, idx)
+                self.results[idx].append(result)
+
+                # Save results after each question is processed
+                with open(output_file_path, "w") as f:
+                    json.dump(self.results, f, indent=4)
+
+        # Final save at the end
+        with open(output_file_path, "w") as f:
+            json.dump(self.results, f, indent=4)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--run_id", type=str, required=True)
+    args = parser.parse_args()
+    zep_search = ZepSearch()
+    zep_search.process_data_file("../../dataset/locomo10.json", args.run_id, "results/zep_search_results.json")

mem0-ts/src/client/config.ts

@@ -3,9 +3,7 @@
  *
  * Used to stitch PostHog identities: SDKs and CLIs persist anonymous
  * distinct_id values here, and the TS MemoryClient reads those on init to
- * fire $identify and merge them into the email identity. The OSS user_id is
- * only a stitch candidate when telemetry.oss_used_at proves OSS Memory
- * actually ran here (the platform client never mints ids itself).
+ * fire $identify and merge them into the email identity.
  *
  * Node-only. Browsers (no `process.versions.node`) no-op.
  */
@@ -13,7 +11,6 @@
 export interface Mem0AnonIds {
   oss?: string;
   cli?: string;
-  ossUsedAt?: string;
   aliasedPairs: string[];
 }
 
@@ -113,10 +110,6 @@ export async function readMem0AnonIds(): Promise<Mem0AnonIds | null> {
       typeof telemetry.anonymous_id === "string"
         ? telemetry.anonymous_id
         : undefined,
-    ossUsedAt:
-      typeof telemetry.oss_used_at === "string" && telemetry.oss_used_at
-        ? telemetry.oss_used_at
-        : undefined,
     aliasedPairs: Array.isArray(telemetry.aliased_pairs)
       ? telemetry.aliased_pairs.filter(
           (item: unknown) => typeof item === "string",
@@ -144,26 +137,6 @@ export async function isMem0Aliased(
   return aliasedPairs.includes(aliasPairMarker(node, anonId, email));
 }
 
-export async function markMem0OssUsed(): Promise<void> {
-  const node = await getNodeFs();
-  if (!node) return;
-  try {
-    const config = loadConfig(node) ?? {};
-    const telemetry =
-      config.telemetry && typeof config.telemetry === "object"
-        ? config.telemetry
-        : {};
-    if (typeof telemetry.oss_used_at === "string" && telemetry.oss_used_at) {
-      return;
-    }
-    telemetry.oss_used_at = new Date().toISOString();
-    config.telemetry = telemetry;
-    writeConfig(node, config);
-  } catch {
-    // Best-effort: read-only filesystems and unwritable paths just skip.
-  }
-}
-
 export async function markMem0Aliased(
   anonId: string,
   email: string,

mem0-ts/src/client/mem0.ts

@@ -27,7 +27,12 @@ import {
   isTelemetryEnabled,
   telemetry,
 } from "./telemetry";
-import { isMem0Aliased, markMem0Aliased, readMem0AnonIds } from "./config";
+import {
+  getOrCreateMem0UserId,
+  isMem0Aliased,
+  markMem0Aliased,
+  readMem0AnonIds,
+} from "./config";
 import { camelToSnake, camelToSnakeKeys, snakeToCamelKeys } from "./utils";
 import { createExceptionFromResponse, MemoryError } from "../common/exceptions";
 
@@ -146,16 +151,12 @@ export default class MemoryClient {
     try {
       const email = this.telemetryId;
       if (!email || !email.includes("@")) return;
+      const sharedAnonId = await getOrCreateMem0UserId();
       const anonIds = await readMem0AnonIds();
-      if (!anonIds) return;
-      // The OSS user_id is only a stitch candidate when telemetry.oss_used_at
-      // proves OSS Memory actually ran here; never mint an id from the
-      // platform client path. The CLI anon id is presence-based (only the
-      // CLIs write it).
-      const candidates = [
-        anonIds.ossUsedAt ? anonIds.oss : undefined,
-        anonIds.cli,
-      ].filter((id): id is string => !!id && id !== email);
+      if (!anonIds && !sharedAnonId) return;
+      const candidates = [anonIds?.oss || sharedAnonId, anonIds?.cli].filter(
+        (id): id is string => !!id && id !== email,
+      );
       const seen = new Set<string>();
       for (const anonId of candidates) {
         if (seen.has(anonId) || (await isMem0Aliased(anonId, email))) continue;

mem0-ts/src/client/telemetry.ts

@@ -85,7 +85,6 @@ class UnifiedTelemetry implements TelemetryClient {
       properties: {
         $anon_distinct_id: anonId,
         client_source: "typescript",
-        client_version: version,
         $lib: "posthog-node",
       },
     };

mem0-ts/src/client/tests/telemetry-aliasing.test.ts

@@ -13,7 +13,6 @@ import {
   getOrCreateMem0UserId,
   isMem0Aliased,
   markMem0Aliased,
-  markMem0OssUsed,
   readMem0AnonIds,
 } from "../config";
 import { TEST_API_KEY } from "./helpers";
@@ -146,55 +145,6 @@ describe("config.ts — readMem0AnonIds / markMem0Aliased", () => {
       markMem0Aliased("oss-uuid", "user@example.com"),
     ).resolves.toBeUndefined();
   });
-
-  test("markMem0OssUsed writes marker preserving other fields", async () => {
-    fs.writeFileSync(
-      path.join(tmpHome, "config.json"),
-      JSON.stringify({
-        user_id: "oss-uuid",
-        telemetry: { anonymous_id: "cli-anon", aliased_pairs: ["pair-marker"] },
-      }),
-    );
-    await markMem0OssUsed();
-    const written = JSON.parse(
-      fs.readFileSync(path.join(tmpHome, "config.json"), "utf8"),
-    );
-    expect(written.user_id).toBe("oss-uuid");
-    expect(written.telemetry.anonymous_id).toBe("cli-anon");
-    expect(written.telemetry.aliased_pairs).toEqual(["pair-marker"]);
-    expect(written.telemetry.oss_used_at).toBeTruthy();
-  });
-
-  test("markMem0OssUsed is idempotent", async () => {
-    await markMem0OssUsed();
-    const first = JSON.parse(
-      fs.readFileSync(path.join(tmpHome, "config.json"), "utf8"),
-    ).telemetry.oss_used_at;
-    await markMem0OssUsed();
-    const second = JSON.parse(
-      fs.readFileSync(path.join(tmpHome, "config.json"), "utf8"),
-    ).telemetry.oss_used_at;
-    expect(second).toBe(first);
-  });
-
-  test("readMem0AnonIds surfaces ossUsedAt", async () => {
-    fs.writeFileSync(
-      path.join(tmpHome, "config.json"),
-      JSON.stringify({
-        user_id: "oss-uuid",
-        telemetry: { oss_used_at: "2026-01-01T00:00:00.000Z" },
-      }),
-    );
-    const ids = await readMem0AnonIds();
-    expect(ids?.oss).toBe("oss-uuid");
-    expect(ids?.ossUsedAt).toBe("2026-01-01T00:00:00.000Z");
-  });
-
-  test("markMem0OssUsed does not throw when target dir is unwritable", async () => {
-    fs.writeFileSync(path.join(tmpHome, "blocker"), "x");
-    process.env.MEM0_DIR = path.join(tmpHome, "blocker"); // file used as dir
-    await expect(markMem0OssUsed()).resolves.toBeUndefined();
-  });
 });
 
 // ─── telemetry.captureIdentify ───────────────────────────────
@@ -216,7 +166,6 @@ describe("telemetry.captureIdentify", () => {
     expect(payload.event).toBe("$identify");
     expect(payload.distinct_id).toBe("user@example.com");
     expect(payload.properties.$anon_distinct_id).toBe("anon-uuid");
-    expect(payload.properties.client_version).toBeTruthy();
     expect(payload.properties.$process_person_profile).toBeUndefined();
   });
 
@@ -271,10 +220,7 @@ describe("MemoryClient — _maybeAliasAnonToEmail", () => {
   test("fires $identify on first init and persists pair marker", async () => {
     fs.writeFileSync(
       path.join(tmpHome, "config.json"),
-      JSON.stringify({
-        user_id: "oss-uuid",
-        telemetry: { oss_used_at: "2026-01-01T00:00:00.000Z" },
-      }),
+      JSON.stringify({ user_id: "oss-uuid" }),
     );
     const fetchMock = setupMockFetchWithPostHog();
 
@@ -298,38 +244,17 @@ describe("MemoryClient — _maybeAliasAnonToEmail", () => {
     expect(written.telemetry.aliased_pairs).toHaveLength(1);
   });
 
-  test("platform-only init mints nothing and fires no $identify", async () => {
-    // Regression: the client used to create the shared anon id itself and
-    // immediately stitch it, merging an event-less anon person into every
-    // platform user. The platform path must now be read-only.
+  test("platform-first init creates shared anon ID and identifies it", async () => {
     const fetchMock = setupMockFetchWithPostHog();
 
     const client = makeStubClient("test@example.com");
     await (client as any)._maybeAliasAnonToEmail();
 
-    expect(fs.existsSync(path.join(tmpHome, "config.json"))).toBe(false);
-
-    const identifyCalls = (fetchMock.mock.calls as any[]).filter(
-      ([, init]: [string, RequestInit]) => {
-        if (!init?.body) return false;
-        return JSON.parse(init.body as string).event === "$identify";
-      },
+    const written = JSON.parse(
+      fs.readFileSync(path.join(tmpHome, "config.json"), "utf8"),
     );
-    expect(identifyCalls.length).toBe(0);
-  });
-
-  test("oss id without oss_used_at marker is not stitched; cli id still is", async () => {
-    fs.writeFileSync(
-      path.join(tmpHome, "config.json"),
-      JSON.stringify({
-        user_id: "oss-uuid",
-        telemetry: { anonymous_id: "cli-anon" },
-      }),
-    );
-    const fetchMock = setupMockFetchWithPostHog();
-
-    const client = makeStubClient("test@example.com");
-    await (client as any)._maybeAliasAnonToEmail();
+    expect(written.user_id).toBeTruthy();
+    expect(written.telemetry.aliased_pairs).toHaveLength(1);
 
     const identifyCalls = (fetchMock.mock.calls as any[]).filter(
       ([, init]: [string, RequestInit]) => {
@@ -339,32 +264,8 @@ describe("MemoryClient — _maybeAliasAnonToEmail", () => {
     );
     expect(identifyCalls.length).toBe(1);
     const body = JSON.parse(identifyCalls[0][1].body);
-    expect(body.properties.$anon_distinct_id).toBe("cli-anon");
-  });
-
-  test("stitches config written by the Python SDK (cross-SDK key compat)", async () => {
-    // Python writes datetime.now(timezone.utc).isoformat(): +00:00 offset.
-    fs.writeFileSync(
-      path.join(tmpHome, "config.json"),
-      JSON.stringify({
-        user_id: "oss-uuid",
-        telemetry: { oss_used_at: "2026-01-01T00:00:00+00:00" },
-      }),
-    );
-    const fetchMock = setupMockFetchWithPostHog();
-
-    const client = makeStubClient("test@example.com");
-    await (client as any)._maybeAliasAnonToEmail();
-
-    const identifyCalls = (fetchMock.mock.calls as any[]).filter(
-      ([, init]: [string, RequestInit]) => {
-        if (!init?.body) return false;
-        return JSON.parse(init.body as string).event === "$identify";
-      },
-    );
-    expect(identifyCalls.length).toBe(1);
-    const body = JSON.parse(identifyCalls[0][1].body);
-    expect(body.properties.$anon_distinct_id).toBe("oss-uuid");
+    expect(body.distinct_id).toBe("test@example.com");
+    expect(body.properties.$anon_distinct_id).toBe(written.user_id);
   });
 
   test("second init does not refire $identify", async () => {
@@ -372,7 +273,7 @@ describe("MemoryClient — _maybeAliasAnonToEmail", () => {
       path.join(tmpHome, "config.json"),
       JSON.stringify({
         user_id: "oss-uuid",
-        telemetry: { oss_used_at: "2026-01-01T00:00:00.000Z" },
+        telemetry: {},
       }),
     );
     await markMem0Aliased("oss-uuid", "test@example.com");
@@ -395,10 +296,7 @@ describe("MemoryClient — _maybeAliasAnonToEmail", () => {
       path.join(tmpHome, "config.json"),
       JSON.stringify({
         user_id: "oss-uuid",
-        telemetry: {
-          anonymous_id: "cli-anon",
-          oss_used_at: "2026-01-01T00:00:00.000Z",
-        },
+        telemetry: { anonymous_id: "cli-anon" },
       }),
     );
     const fetchMock = setupMockFetchWithPostHog();
@@ -509,18 +407,4 @@ describe("config.ts in browser-like environment", () => {
       jest.resetModules();
     }
   });
-
-  test("markMem0OssUsed is a no-op when not Node", async () => {
-    const originalProcess = global.process;
-    // @ts-expect-error force-undefining global to simulate a browser
-    delete global.process;
-    try {
-      jest.resetModules();
-      const { markMem0OssUsed: browserMark } = await import("../config");
-      await expect(browserMark()).resolves.toBeUndefined();
-    } finally {
-      global.process = originalProcess;
-      jest.resetModules();
-    }
-  });
 });

mem0-ts/src/oss/src/memory/index.ts

@@ -40,7 +40,7 @@ import {
 } from "./memory.types";
 import { parse_vision_messages } from "../utils/memory";
 import { HistoryManager } from "../storage/base";
-import { captureClientEvent, isTelemetryEnabled } from "../utils/telemetry";
+import { captureClientEvent } from "../utils/telemetry";
 import {
   detectScaleThresholdFromAddResult,
   detectScaleThresholdFromTopK,
@@ -72,7 +72,7 @@ import {
   ScoredResult,
 } from "../utils/scoring";
 import { getDefaultVectorStoreDbPath } from "../utils/sqlite";
-import { getOrCreateMem0UserId, markMem0OssUsed } from "../../../client/config";
+import { getOrCreateMem0UserId } from "../../../client/config";
 
 // Entity params that must be passed via filters - check both snake_case and camelCase
 const ENTITY_PARAMS = [
@@ -470,12 +470,6 @@ export class Memory {
     try {
       await this._getTelemetryId();
 
-      // Record genuine OSS usage so the platform client may stitch this
-      // machine's anon id to a platform email later.
-      if (isTelemetryEnabled()) {
-        await markMem0OssUsed();
-      }
-
       // Capture initialization event
       await captureClientEvent("init", this, {
         api_version: this.apiVersion,

mem0/client/main.py

@@ -19,13 +19,16 @@ from mem0.client.types import (
 from mem0.client.utils import api_error_handler
 
 # Exception classes are referenced in docstrings only
-from mem0.memory.setup import get_user_id, is_aliased, is_oss_used, mark_aliased, read_anon_ids
+from mem0.memory.setup import get_user_id, is_aliased, mark_aliased, read_anon_ids, setup_config
 from mem0.memory.telemetry import capture_client_event, client_telemetry
 
 logger = logging.getLogger(__name__)
 
 warnings.filterwarnings("default", category=DeprecationWarning)
 
+# Setup user config
+setup_config()
+
 # Entity parameters that must be passed via filters, not top-level
 ENTITY_PARAMS = frozenset({"user_id", "agent_id", "app_id", "run_id"})
 
@@ -42,10 +45,6 @@ def _validate_and_trim_search_query(query: str) -> str:
 def _maybe_alias_anon_to_email(user_email):
     """Fire $identify per prior anon ID so PostHog merges them into email.
 
-    The OSS user_id is only a stitch candidate when telemetry.oss_used_at
-    proves OSS Memory actually ran here; bare user_id values were historically
-    minted at import time by platform-only clients and must not be stitched.
-    The CLI anon id keeps presence-based stitching (only the CLIs write it).
     Idempotent via telemetry.aliased_pairs: only writes markers when
     telemetry is actually enabled, so disabling/re-enabling MEM0_TELEMETRY still works.
     Best-effort: never raises.
@@ -56,9 +55,8 @@ def _maybe_alias_anon_to_email(user_email):
         return
     try:
         anon_ids = read_anon_ids()
-        oss_id = anon_ids.get("oss") if is_oss_used() else None
         seen = set()
-        for anon_id in (oss_id, anon_ids.get("cli")):
+        for anon_id in (anon_ids.get("oss"), anon_ids.get("cli")):
             if not anon_id or anon_id == user_email or anon_id in seen:
                 continue
             seen.add(anon_id)

mem0/memory/main.py

@@ -24,7 +24,7 @@ from mem0.configs.prompts import (
 )
 from mem0.exceptions import ValidationError as Mem0ValidationError
 from mem0.memory.base import MemoryBase
-from mem0.memory.setup import mark_oss_used, mem0_dir, setup_config
+from mem0.memory.setup import mem0_dir, setup_config
 from mem0.memory.storage import SQLiteManager
 from mem0.memory.telemetry import MEM0_TELEMETRY, capture_event
 from mem0.memory.notices import (
@@ -370,6 +370,7 @@ def _entity_collection_name(provider: str, collection_name: str) -> str:
     return f"{collection_name}{separator}entities"
 
 
+setup_config()
 logger = logging.getLogger(__name__)
 
 _PROJECT_UPDATE_UNSUPPORTED_ERROR = "Project updates are not supported by the OSS Memory SDK."
@@ -468,13 +469,6 @@ class Memory(MemoryBase):
                 self.config.vector_store.provider,
             )
 
-        # Mint the OSS anon id (and record genuine OSS usage) only on real OSS
-        # init, never at import time: platform-only clients must not create
-        # stitch candidates. Must run before the first capture_event so the
-        # telemetry singleton picks up the minted user_id.
-        if MEM0_TELEMETRY:
-            setup_config()
-            mark_oss_used()
         capture_event("mem0.init", self, {"sync_type": "sync"})
 
     @property
@@ -2015,9 +2009,6 @@ class AsyncMemory(MemoryBase):
                 self.config.vector_store.provider,
             )
 
-        if MEM0_TELEMETRY:
-            setup_config()
-            mark_oss_used()
         capture_event("mem0.init", self, {"sync_type": "async"})
 
     @property

mem0/memory/setup.py

@@ -3,7 +3,6 @@ import logging
 import os
 import tempfile
 import uuid
-from datetime import datetime, timezone
 from hashlib import sha256
 
 # Set up the directory path
@@ -57,12 +56,10 @@ def _write_config(config):
 def setup_config():
     """Ensure ~/.mem0/config.json exists with a top-level user_id.
 
-    Called lazily from OSS Memory/AsyncMemory init (never at import time, so
-    platform-only MemoryClient usage mints no anon id). Idempotent: backfills
-    user_id for users whose config was written by the CLI (which writes
-    telemetry.anonymous_id but no top-level user_id). Without this, OSS Python
-    telemetry is silently dropped because get_user_id() returns None when
-    user_id is missing.
+    Idempotent: backfills user_id for users whose config was written by the
+    CLI (which writes telemetry.anonymous_id but no top-level user_id).
+    Without this, OSS Python telemetry is silently dropped because
+    get_user_id() returns None when user_id is missing.
     """
     config = _load_config()
     if config.get("user_id"):
@@ -134,31 +131,6 @@ def mark_aliased(anon_id, email):
     _write_config(config)
 
 
-def is_oss_used():
-    """Return whether OSS Memory has genuinely initialized on this machine.
-
-    Gates identity stitching: the top-level user_id is only a stitch candidate
-    when telemetry.oss_used_at is present, because bare user_id values were
-    historically minted at import time by platform-only clients.
-    """
-    config = _load_config()
-    telemetry = config.get("telemetry") if isinstance(config.get("telemetry"), dict) else {}
-    return bool(telemetry.get("oss_used_at"))
-
-
-def mark_oss_used():
-    """Persist telemetry.oss_used_at on first genuine OSS Memory init. Never raises."""
-    config = _load_config()
-    telemetry = config.get("telemetry")
-    if not isinstance(telemetry, dict):
-        telemetry = {}
-    if telemetry.get("oss_used_at"):
-        return
-    telemetry["oss_used_at"] = datetime.now(timezone.utc).isoformat()
-    config["telemetry"] = telemetry
-    _write_config(config)
-
-
 def get_or_create_user_id(vector_store=None):
     """Store user_id in vector store and return it.
 

mem0/memory/telemetry.py

@@ -129,11 +129,7 @@ class AnonymousTelemetry:
             self.posthog.capture(
                 distinct_id=email,
                 event="$identify",
-                properties={
-                    "$anon_distinct_id": anon_id,
-                    "client_source": "python",
-                    "client_version": mem0.__version__,
-                },
+                properties={"$anon_distinct_id": anon_id, "client_source": "python"},
             )
             return True
         except Exception as e:

tests/test_telemetry_aliasing.py

@@ -164,68 +164,11 @@ class TestMarkAliased:
         assert not setup_module.is_aliased("oss-uuid", "other@example.com")
 
 
-# ─── oss_used marker ─────────────────────────────────────────────────────────
-
-
-class TestOssUsedMarker:
-    def test_mark_writes_marker_preserving_fields(self, tmp_mem0_dir):
-        import mem0.memory.setup as setup_module
-
-        _write_config(
-            tmp_mem0_dir,
-            {
-                "user_id": "oss-uuid",
-                "telemetry": {"anonymous_id": "cli-anon", "aliased_pairs": ["pair-marker"]},
-            },
-        )
-        setup_module.mark_oss_used()
-        config = json.loads((tmp_mem0_dir / "config.json").read_text())
-        assert config["user_id"] == "oss-uuid"
-        assert config["telemetry"]["anonymous_id"] == "cli-anon"
-        assert config["telemetry"]["aliased_pairs"] == ["pair-marker"]
-        assert config["telemetry"]["oss_used_at"]
-        assert setup_module.is_oss_used()
-
-    def test_mark_is_idempotent(self, tmp_mem0_dir):
-        import mem0.memory.setup as setup_module
-
-        setup_module.mark_oss_used()
-        first = json.loads((tmp_mem0_dir / "config.json").read_text())["telemetry"]["oss_used_at"]
-        setup_module.mark_oss_used()
-        second = json.loads((tmp_mem0_dir / "config.json").read_text())["telemetry"]["oss_used_at"]
-        assert first == second
-
-    def test_is_oss_used_false_when_no_config(self, tmp_mem0_dir):
-        import mem0.memory.setup as setup_module
-
-        assert not setup_module.is_oss_used()
-
-    def test_is_oss_used_false_without_marker(self, tmp_mem0_dir):
-        import mem0.memory.setup as setup_module
-
-        _write_config(tmp_mem0_dir, {"user_id": "oss-uuid", "telemetry": {"anonymous_id": "cli-anon"}})
-        assert not setup_module.is_oss_used()
-
-    def test_is_oss_used_false_on_malformed_json(self, tmp_mem0_dir):
-        import mem0.memory.setup as setup_module
-
-        (tmp_mem0_dir / "config.json").write_text("{not json")
-        assert not setup_module.is_oss_used()
-
-    def test_mark_does_not_raise_when_config_path_unwritable(self, tmp_mem0_dir):
-        import mem0.memory.setup as setup_module
-
-        (tmp_mem0_dir / "config.json").mkdir()  # open() on a directory fails
-        setup_module.mark_oss_used()  # must not raise
-        assert not setup_module.is_oss_used()
-
-
 # ─── capture_identify ────────────────────────────────────────────────────────
 
 
 class TestCaptureIdentify:
     def test_fires_identify_with_anon_distinct_id(self):
-        import mem0
         import mem0.memory.telemetry as telemetry_module
 
         with patch.object(telemetry_module, "MEM0_TELEMETRY", True):
@@ -238,7 +181,6 @@ class TestCaptureIdentify:
                 assert kwargs["distinct_id"] == "user@example.com"
                 assert kwargs["event"] == "$identify"
                 assert kwargs["properties"]["$anon_distinct_id"] == "anon-123"
-                assert kwargs["properties"]["client_version"] == mem0.__version__
 
     def test_skips_when_anon_equals_email(self):
         import mem0.memory.telemetry as telemetry_module
@@ -288,7 +230,8 @@ class TestCaptureIdentify:
 
 class TestMaybeAliasAnonToEmail:
     """Test the alias helper in isolation by mocking out the config readers
-    and the telemetry client, so no real ~/.mem0/config.json is touched."""
+    and the telemetry client, since module-level setup_config() side effects
+    make end-to-end fixturing awkward."""
 
     def test_fires_identify_for_oss_uuid(self):
         from mem0.client import main as client_main
@@ -299,7 +242,6 @@ class TestMaybeAliasAnonToEmail:
                 "read_anon_ids",
                 return_value={"oss": "oss-uuid", "cli": None, "aliased_pairs": []},
             ),
-            patch.object(client_main, "is_oss_used", return_value=True),
             patch.object(client_main, "is_aliased", return_value=False),
             patch.object(client_main, "mark_aliased") as mark,
             patch.object(client_main, "client_telemetry") as telemetry,
@@ -310,7 +252,6 @@ class TestMaybeAliasAnonToEmail:
             mark.assert_called_once_with("oss-uuid", "user@example.com")
 
     def test_fires_identify_for_cli_anon(self):
-        """The CLI anon id is presence-based: it stitches even without the oss_used marker."""
         from mem0.client import main as client_main
 
         with (
@@ -319,7 +260,6 @@ class TestMaybeAliasAnonToEmail:
                 "read_anon_ids",
                 return_value={"oss": None, "cli": "cli-anon-xyz", "aliased_pairs": []},
             ),
-            patch.object(client_main, "is_oss_used", return_value=False),
             patch.object(client_main, "is_aliased", return_value=False),
             patch.object(client_main, "mark_aliased"),
             patch.object(client_main, "client_telemetry") as telemetry,
@@ -337,7 +277,6 @@ class TestMaybeAliasAnonToEmail:
                 "read_anon_ids",
                 return_value={"oss": "oss-uuid", "cli": "cli-anon", "aliased_pairs": []},
             ),
-            patch.object(client_main, "is_oss_used", return_value=True),
             patch.object(client_main, "is_aliased", return_value=False),
             patch.object(client_main, "mark_aliased"),
             patch.object(client_main, "client_telemetry") as telemetry,
@@ -349,26 +288,6 @@ class TestMaybeAliasAnonToEmail:
             assert ("oss-uuid", "user@example.com") in calls
             assert ("cli-anon", "user@example.com") in calls
 
-    def test_oss_id_requires_oss_used_marker(self):
-        """Without proof of real OSS usage, the oss user_id must never be
-        stitched (it may have been minted by an old platform-only client)."""
-        from mem0.client import main as client_main
-
-        with (
-            patch.object(
-                client_main,
-                "read_anon_ids",
-                return_value={"oss": "oss-uuid", "cli": "cli-anon", "aliased_pairs": []},
-            ),
-            patch.object(client_main, "is_oss_used", return_value=False),
-            patch.object(client_main, "is_aliased", return_value=False),
-            patch.object(client_main, "mark_aliased"),
-            patch.object(client_main, "client_telemetry") as telemetry,
-        ):
-            telemetry.capture_identify.return_value = True
-            client_main._maybe_alias_anon_to_email("user@example.com")
-            telemetry.capture_identify.assert_called_once_with("cli-anon", "user@example.com")
-
     def test_skips_when_pair_already_aliased(self):
         from mem0.client import main as client_main
 
@@ -378,7 +297,6 @@ class TestMaybeAliasAnonToEmail:
                 "read_anon_ids",
                 return_value={"oss": "oss-uuid", "cli": None, "aliased_pairs": ["pair-marker"]},
             ),
-            patch.object(client_main, "is_oss_used", return_value=True),
             patch.object(client_main, "is_aliased", return_value=True),
             patch.object(client_main, "mark_aliased") as mark,
             patch.object(client_main, "client_telemetry") as telemetry,
@@ -424,7 +342,6 @@ class TestMaybeAliasAnonToEmail:
                 "read_anon_ids",
                 return_value={"oss": "oss-uuid", "cli": None, "aliased_pairs": []},
             ),
-            patch.object(client_main, "is_oss_used", return_value=True),
             patch.object(client_main, "is_aliased", return_value=False),
             patch.object(client_main, "mark_aliased") as mark,
             patch.object(client_main, "client_telemetry", mock_telemetry),
@@ -442,7 +359,6 @@ class TestMaybeAliasAnonToEmail:
                 "read_anon_ids",
                 return_value={"oss": "user@example.com", "cli": None, "aliased_pairs": []},
             ),
-            patch.object(client_main, "is_oss_used", return_value=True),
             patch.object(client_main, "is_aliased", return_value=False),
             patch.object(client_main, "mark_aliased"),
             patch.object(client_main, "client_telemetry") as telemetry,
@@ -470,12 +386,8 @@ class TestEndToEndIdempotency:
     calls fire $identify exactly once thanks to the persisted pair marker."""
 
     def test_second_call_is_noop_after_pair_marker_persisted(self, tmp_mem0_dir):
-        # Pre-populate config with an OSS user_id plus the oss_used_at marker
-        # (without the marker the oss id is no longer a stitch candidate).
-        _write_config(
-            tmp_mem0_dir,
-            {"user_id": "oss-uuid", "telemetry": {"oss_used_at": "2026-01-01T00:00:00+00:00"}},
-        )
+        # Pre-populate config with an OSS user_id only.
+        _write_config(tmp_mem0_dir, {"user_id": "oss-uuid"})
         # Reload setup so it uses the tempdir, then reload client.main so it
         # picks up the freshly-loaded read_anon_ids/mark_aliased bindings.
         import mem0.memory.setup as setup_module
@@ -497,112 +409,3 @@ class TestEndToEndIdempotency:
 
         config = json.loads((tmp_mem0_dir / "config.json").read_text())
         assert len(config["telemetry"]["aliased_pairs"]) == 1
-
-    def test_oss_then_platform_stitches_exactly_once(self, tmp_mem0_dir):
-        """Genuine OSS usage (setup_config + mark_oss_used, as Memory.__init__
-        does) followed by platform inits stitches the minted id exactly once."""
-        import mem0.memory.setup as setup_module
-
-        setup_module.setup_config()
-        setup_module.mark_oss_used()
-        oss_id = json.loads((tmp_mem0_dir / "config.json").read_text())["user_id"]
-
-        from mem0.client import main as client_main
-
-        importlib.reload(client_main)
-
-        with patch.object(client_main, "client_telemetry") as telemetry:
-            telemetry.capture_identify.return_value = True
-            client_main._maybe_alias_anon_to_email("user@example.com")
-            telemetry.capture_identify.assert_called_once_with(oss_id, "user@example.com")
-            client_main._maybe_alias_anon_to_email("user@example.com")
-            assert telemetry.capture_identify.call_count == 1
-
-        config = json.loads((tmp_mem0_dir / "config.json").read_text())
-        assert len(config["telemetry"]["aliased_pairs"]) == 1
-        assert config["telemetry"]["oss_used_at"]
-
-
-# ─── Platform-only init must not mint or stitch ──────────────────────────────
-
-
-class TestPlatformOnlyDoesNotMint:
-    """Regression for the bug where importing the client minted an anon id at
-    import time and then stitched it on MemoryClient init, merging an
-    event-less anon person into every platform user."""
-
-    def test_no_config_created_and_no_identify(self, tmp_mem0_dir):
-        from mem0.client import main as client_main
-
-        # Re-execute the client module: it must not create config.json.
-        importlib.reload(client_main)
-        assert not (tmp_mem0_dir / "config.json").exists()
-
-        with patch.object(client_main, "client_telemetry") as telemetry:
-            telemetry.capture_identify.return_value = True
-            client_main._maybe_alias_anon_to_email("user@example.com")
-            telemetry.capture_identify.assert_not_called()
-
-        assert not (tmp_mem0_dir / "config.json").exists()
-
-
-# ─── Lazy minting from OSS Memory init ───────────────────────────────────────
-
-
-class TestLazyOssMinting:
-    """OSS Memory/AsyncMemory init mints the anon id and records genuine OSS
-    usage; nothing happens at import time or with telemetry disabled."""
-
-    def test_memory_init_mints_and_marks(self, tmp_path):
-        import mem0.memory.main as memory_main
-
-        with (
-            patch.object(memory_main, "EmbedderFactory"),
-            patch.object(memory_main, "VectorStoreFactory"),
-            patch.object(memory_main, "LlmFactory"),
-            patch.object(memory_main, "SQLiteManager"),
-            patch.object(memory_main, "capture_event"),
-            patch.object(memory_main, "mem0_dir", str(tmp_path)),
-            patch.object(memory_main, "setup_config") as setup,
-            patch.object(memory_main, "mark_oss_used") as mark,
-            patch.object(memory_main, "MEM0_TELEMETRY", True),
-        ):
-            memory_main.Memory()
-            setup.assert_called_once()
-            mark.assert_called_once()
-
-    def test_memory_init_skips_minting_when_telemetry_disabled(self, tmp_path):
-        import mem0.memory.main as memory_main
-
-        with (
-            patch.object(memory_main, "EmbedderFactory"),
-            patch.object(memory_main, "VectorStoreFactory"),
-            patch.object(memory_main, "LlmFactory"),
-            patch.object(memory_main, "SQLiteManager"),
-            patch.object(memory_main, "capture_event"),
-            patch.object(memory_main, "mem0_dir", str(tmp_path)),
-            patch.object(memory_main, "setup_config") as setup,
-            patch.object(memory_main, "mark_oss_used") as mark,
-            patch.object(memory_main, "MEM0_TELEMETRY", False),
-        ):
-            memory_main.Memory()
-            setup.assert_not_called()
-            mark.assert_not_called()
-
-    def test_async_memory_init_mints_and_marks(self, tmp_path):
-        import mem0.memory.main as memory_main
-
-        with (
-            patch.object(memory_main, "EmbedderFactory"),
-            patch.object(memory_main, "VectorStoreFactory"),
-            patch.object(memory_main, "LlmFactory"),
-            patch.object(memory_main, "SQLiteManager"),
-            patch.object(memory_main, "capture_event"),
-            patch.object(memory_main, "mem0_dir", str(tmp_path)),
-            patch.object(memory_main, "setup_config") as setup,
-            patch.object(memory_main, "mark_oss_used") as mark,
-            patch.object(memory_main, "MEM0_TELEMETRY", True),
-        ):
-            memory_main.AsyncMemory()
-            setup.assert_called_once()
-            mark.assert_called_once()