docs: refresh README first fold, reconcile stale benchmark numbers, unify the one-liner
README first fold: - banner 800px -> 520px - badges condensed from two paragraphs into one row (Trendshift kept, inline) - lead with Introduction instead of benchmarks - new How it works section explaining the add/search loop - benchmarks moved below the intro and retitled from the date-stamped New Memory Algorithm (April 2026) - dropped Research Highlights, which restated the benchmark table verbatim Benchmarks: the README was already correct at 92.5 / 94.4, matching mem0.ai/research and docs/core-concepts/memory-evaluation.mdx. The stale copies were in the migration guides, which quote the numbers as a live reason to upgrade. Updated both to 92.5 / 94.4 (+21 / +27). docs/changelog/highlights.mdx keeps 91.6 / 93.4 inside its dated 2026-04-14 entry, which records what was announced at the time. One-liner: standardized on 'the memory layer for AI agents', already the canonical form in cli-spec.json, cli/python/pyproject.toml and the CLI specification. Swept the remaining variants.
This commit is contained in:
kartik-mem0
@@ -11,7 +11,7 @@
|
||||
{
|
||||
"name": "mem0",
|
||||
"source": "./integrations/mem0-plugin",
|
||||
"description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows.",
|
||||
"description": "Mem0, the memory layer for AI agents. Add persistent memory, personalization, and semantic search to Claude workflows.",
|
||||
"version": "0.2.14"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
{
|
||||
"name": "mem0",
|
||||
"source": "./integrations/mem0-plugin",
|
||||
"description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search.",
|
||||
"description": "Mem0, the memory layer for AI agents. Add persistent memory, personalization, and semantic search.",
|
||||
"version": "0.2.14"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Mem0 - The Memory Layer for Personalized AI
|
||||
# Mem0 - The Memory Layer for AI Agents
|
||||
|
||||
## Overview
|
||||
|
||||
|
||||
@@ -1,12 +1,17 @@
|
||||
<p align="center">
|
||||
<a href="https://github.com/mem0ai/mem0">
|
||||
<img src="docs/images/banner-sm.png" width="800px" alt="Mem0 - The Memory Layer for Personalized AI">
|
||||
<img src="docs/images/banner-sm.png" width="520px" alt="Mem0 - The Memory Layer for AI Agents">
|
||||
</a>
|
||||
</p>
|
||||
<p align="center" style="display: flex; justify-content: center; gap: 20px; align-items: center;">
|
||||
<a href="https://trendshift.io/repositories/11194" target="blank">
|
||||
<img src="https://trendshift.io/api/badge/repositories/11194" alt="mem0ai%2Fmem0 | Trendshift" width="250" height="55"/>
|
||||
</a>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://trendshift.io/repositories/11194" target="blank"><img src="https://trendshift.io/api/badge/repositories/11194" alt="mem0ai/mem0 | Trendshift" height="20"></a>
|
||||
<a href="https://pypi.org/project/mem0ai" target="blank"><img src="https://img.shields.io/pypi/v/mem0ai?color=%2334D058&label=pypi" alt="PyPI version"></a>
|
||||
<a href="https://www.npmjs.com/package/mem0ai" target="blank"><img src="https://img.shields.io/npm/v/mem0ai?label=npm" alt="npm version"></a>
|
||||
<a href="https://pepy.tech/project/mem0ai"><img src="https://img.shields.io/pypi/dm/mem0ai?label=downloads" alt="PyPI downloads"></a>
|
||||
<a href="https://mem0.dev/DiG"><img src="https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white" alt="Discord"></a>
|
||||
<a href="https://www.ycombinator.com/companies/mem0"><img src="https://img.shields.io/badge/Y%20Combinator-S24-orange" alt="Y Combinator S24"></a>
|
||||
<a href="https://github.com/mem0ai/mem0/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue" alt="Apache 2.0"></a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
@@ -15,62 +20,29 @@
|
||||
<a href="https://mem0.dev/DiG">Join Discord</a>
|
||||
·
|
||||
<a href="https://mem0.dev/demo">Demo</a>
|
||||
·
|
||||
<a href="https://mem0.ai/research">Research</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://mem0.dev/DiG">
|
||||
<img src="https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white" alt="Mem0 Discord">
|
||||
</a>
|
||||
<a href="https://pepy.tech/project/mem0ai">
|
||||
<img src="https://img.shields.io/pypi/dm/mem0ai" alt="Mem0 PyPI - Downloads">
|
||||
</a>
|
||||
<a href="https://github.com/mem0ai/mem0">
|
||||
<img src="https://img.shields.io/github/commit-activity/m/mem0ai/mem0?style=flat-square" alt="GitHub commit activity">
|
||||
</a>
|
||||
<a href="https://pypi.org/project/mem0ai" target="blank">
|
||||
<img src="https://img.shields.io/pypi/v/mem0ai?color=%2334D058&label=pypi%20package" alt="Package version">
|
||||
</a>
|
||||
<a href="https://www.npmjs.com/package/mem0ai" target="blank">
|
||||
<img src="https://img.shields.io/npm/v/mem0ai" alt="Npm package">
|
||||
</a>
|
||||
<a href="https://www.ycombinator.com/companies/mem0">
|
||||
<img src="https://img.shields.io/badge/Y%20Combinator-S24-orange?style=flat-square" alt="Y Combinator S24">
|
||||
</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://mem0.ai/research"><strong>📄 Benchmarking Mem0's token-efficient memory algorithm →</strong></a>
|
||||
</p>
|
||||
|
||||
## New Memory Algorithm (April 2026)
|
||||
|
||||
| Benchmark | Old | New | Tokens | Latency p50 |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| **LoCoMo** | 71.4 | **92.5** | 7.0K | 0.88s |
|
||||
| **LongMemEval** | 67.8 | **94.4** | 6.8K | 1.09s |
|
||||
| **BEAM (1M)** | — | **64.1** | 6.7K | 1.00s |
|
||||
| **BEAM (10M)** | — | **48.6** | 6.9K | 1.05s |
|
||||
|
||||
All benchmarks run on the same production-representative model stack. Single-pass retrieval (one call, no agentic loops) at a top_200 retrieval budget. Scores reflect Mem0's managed platform, which includes proprietary optimizations not available in the open-source SDK; open-source users should expect directionally similar gains but not identical numbers.
|
||||
|
||||
**What changed:**
|
||||
- **Single-pass ADD-only extraction** -- one LLM call, no UPDATE/DELETE. Memories accumulate; nothing is overwritten.
|
||||
- **Agent-generated facts are first-class** -- when an agent confirms an action, that information is now stored with equal weight.
|
||||
- **Entity linking** -- entities are extracted, embedded, and linked across memories for retrieval boosting.
|
||||
- **Multi-signal retrieval** -- semantic, BM25 keyword, and entity matching scored in parallel and fused.
|
||||
- **Temporal Reasoning** -- time-aware retrieval that ranks the right dated instance for queries about current state, past events, and upcoming plans.
|
||||
|
||||
See the [migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for upgrade instructions. The [evaluation framework](https://github.com/mem0ai/memory-benchmarks) is open-sourced so anyone can reproduce the numbers.
|
||||
|
||||
## Research Highlights
|
||||
- **92.5 on LoCoMo** -- +21 points over the previous algorithm
|
||||
- **94.4 on LongMemEval** -- +27 points, with 98.2 on assistant memory recall
|
||||
- **64.1 on BEAM (1M)** -- production-scale memory evaluation at 1M tokens
|
||||
- [Read the full paper](https://mem0.ai/research)
|
||||
|
||||
# Introduction
|
||||
|
||||
[Mem0](https://mem0.ai) ("mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. It remembers user preferences, adapts to individual needs, and continuously learns over time—ideal for customer support chatbots, AI assistants, and autonomous systems.
|
||||
[Mem0](https://mem0.ai) ("mem-zero") is the memory layer for AI agents. It remembers user preferences, decisions, and history across sessions, so your agents stop asking the same questions and stay useful over weeks instead of a single conversation.
|
||||
|
||||
## How it works
|
||||
|
||||
Mem0 sits between your app and your LLM. Two calls do the work.
|
||||
|
||||
**On `add()`, Mem0 writes memory:**
|
||||
1. Your conversation messages go to an LLM in a single extraction pass, which pulls out durable facts ("prefers dark mode", "ships to Berlin") and discards small talk.
|
||||
2. Entities in those facts are extracted, embedded, and linked to entities already stored, so related memories connect to each other.
|
||||
3. Facts are stored additively. Nothing is overwritten or deleted, so history stays auditable and a wrong extraction cannot silently erase a correct one.
|
||||
|
||||
**On `search()`, Mem0 reads memory:**
|
||||
1. Your query runs against three signals in parallel: semantic vector similarity, BM25 keyword matching, and entity overlap.
|
||||
2. The three scores are fused, and time-aware ranking picks the right dated instance when facts changed over time ("where do I live" vs "where did I live before").
|
||||
3. You get back a short, ranked list to drop into your prompt, typically under 7K tokens instead of replaying a 25K+ token conversation history.
|
||||
|
||||
That is the whole loop: `add()` after a turn, `search()` before the next one. Everything else (vector store, embedder, LLM, reranker) is swappable.
|
||||
|
||||
### Key Features & Use Cases
|
||||
|
||||
@@ -84,6 +56,19 @@ See the [migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for upgra
|
||||
- **Healthcare**: Track patient preferences and history for personalized care
|
||||
- **Productivity & Gaming**: Adaptive workflows and environments based on user behavior
|
||||
|
||||
## Benchmarks
|
||||
|
||||
| Benchmark | Previous | Current | Tokens | Latency p50 |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| **LoCoMo** | 71.4 | **92.5** | 7.0K | 0.88s |
|
||||
| **LongMemEval** | 67.8 | **94.4** | 6.8K | 1.09s |
|
||||
| **BEAM (1M)** | -- | **64.1** | 6.7K | 1.00s |
|
||||
| **BEAM (10M)** | -- | **48.6** | 6.9K | 1.05s |
|
||||
|
||||
All benchmarks run on the same production-representative model stack. Single-pass retrieval (one call, no agentic loops) at a top_200 retrieval budget. Scores reflect Mem0's managed platform, which includes proprietary optimizations not available in the open-source SDK; open-source users should expect directionally similar gains but not identical numbers.
|
||||
|
||||
The [evaluation framework](https://github.com/mem0ai/memory-benchmarks) is open-sourced so anyone can reproduce the numbers, and the [full paper](https://mem0.ai/research) covers the methodology. Upgrading from v2? See the [migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3).
|
||||
|
||||
## 🚀 Quickstart Guide <a name="quickstart"></a>
|
||||
|
||||
### Sign up as an agent
|
||||
|
||||
+1
-1
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"$schema": "https://mintlify.com/docs.json",
|
||||
"name": "Mem0",
|
||||
"description": "Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users.",
|
||||
"description": "Mem0 is the memory layer for AI agents, giving them persistent, personalized context across sessions.",
|
||||
"theme": "aspen",
|
||||
"colors": {
|
||||
"primary": "#8F74E0",
|
||||
|
||||
@@ -3,7 +3,7 @@ title: "Raycast Extension"
|
||||
description: "Mem0 Raycast extension for intelligent memory management"
|
||||
---
|
||||
|
||||
Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users. This extension lets you store and retrieve text snippets using Mem0's intelligent memory system. Find Mem0 in [Raycast Store](https://www.raycast.com/dev_khant/mem0) for using it.
|
||||
Mem0 is the memory layer for AI agents, giving them persistent, personalized context across sessions. This extension lets you store and retrieve text snippets using Mem0's intelligent memory system. Find Mem0 in [Raycast Store](https://www.raycast.com/dev_khant/mem0) for using it.
|
||||
|
||||
## Getting Started
|
||||
|
||||
|
||||
@@ -7,7 +7,7 @@ Build AI applications with persistent memory and comprehensive LLM observability
|
||||
|
||||
## Overview
|
||||
|
||||
Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users. Respan (formerly Keywords AI) provides complete LLM observability.
|
||||
Mem0 is the memory layer for AI agents, giving them persistent, personalized context across sessions. Respan (formerly Keywords AI) provides complete LLM observability.
|
||||
|
||||
Combining Mem0 with Respan allows you to:
|
||||
1. Add persistent memory to your AI applications
|
||||
|
||||
@@ -20,7 +20,7 @@ The new Mem0 release redesigns both extraction and retrieval, and cleans up the
|
||||
- **SDK cleanup**: Deprecated parameters removed, naming conventions standardized
|
||||
- **API surface aligned with Platform**: Entity IDs now follow the same convention across OSS and Platform: top-level kwargs for `add()` / `delete_all()`, inside `filters` for `search()` / `get_all()`
|
||||
|
||||
These changes produce a **+20 point improvement on LoCoMo** (71.4 → 91.6) and **+26 point improvement on LongMemEval** (67.8 → 93.4), while cutting extraction latency roughly in half.
|
||||
These changes produce a **+21 point improvement on LoCoMo** (71.4 → 92.5) and **+27 point improvement on LongMemEval** (67.8 → 94.4), while cutting extraction latency roughly in half.
|
||||
|
||||
## Breaking Changes
|
||||
|
||||
|
||||
@@ -11,7 +11,7 @@ iconType: "solid"
|
||||
|
||||
## Overview
|
||||
|
||||
The new Mem0 memory algorithm is a ground-up redesign of how memories are extracted, stored, and retrieved. It scores **91.6 on LoCoMo** and **93.4 on LongMemEval**: a +20 and +26 point improvement over the previous algorithm: while cutting extraction latency roughly in half.
|
||||
The new Mem0 memory algorithm is a ground-up redesign of how memories are extracted, stored, and retrieved. It scores **92.5 on LoCoMo** and **94.4 on LongMemEval**, a +21 and +27 point improvement over the previous algorithm, while cutting extraction latency roughly in half.
|
||||
|
||||
| What Changed | Before | After |
|
||||
|---|---|---|
|
||||
|
||||
@@ -4,7 +4,7 @@ description: "Managed memory layer for AI agents, production-ready in minutes"
|
||||
icon: "cloud"
|
||||
---
|
||||
|
||||
Mem0 Platform is the fully managed memory layer for your AI apps and agents. Your users stop repeating themselves and your agents keep context across sessions, with no vector store, reranker, or infrastructure to run.
|
||||
Mem0 Platform is the fully managed memory layer for AI agents. Your users stop repeating themselves and your agents keep context across sessions, with no vector store, reranker, or infrastructure to run.
|
||||
|
||||
## Why teams pick the Platform
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "mem0",
|
||||
"version": "0.2.13",
|
||||
"description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search using the Mem0 Platform MCP server.",
|
||||
"description": "Mem0, the memory layer for AI agents. Add persistent memory, personalization, and semantic search using the Mem0 Platform MCP server.",
|
||||
"author": {
|
||||
"name": "Mem0",
|
||||
"email": "support@mem0.ai"
|
||||
|
||||
@@ -16,7 +16,7 @@ compatibility: Requires Python 3.10+ or Node.js 18+, pip install mem0ai or npm i
|
||||
> - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript)
|
||||
> - **[mem0-vercel-ai-sdk](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)** -- Vercel AI SDK provider
|
||||
|
||||
Mem0 is a managed memory layer for AI applications. It stores, retrieves, and manages user memories via API — no infrastructure to deploy. For self-hosted usage, see the OSS section in the client references below.
|
||||
Mem0 is the managed memory layer for AI agents. It stores, retrieves, and manages user memories via API, no infrastructure to deploy. For self-hosted usage, see the OSS section in the client references below.
|
||||
|
||||
## Step 1: Install and authenticate
|
||||
|
||||
|
||||
+2
-2
@@ -1,6 +1,6 @@
|
||||
# Mem0 - The Memory Layer for Your AI Apps
|
||||
# Mem0 - The Memory Layer for AI Agents
|
||||
|
||||
Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users. We offer both cloud and open-source solutions to cater to different needs.
|
||||
Mem0 is the memory layer for AI agents, giving them persistent, personalized context across sessions. We offer both cloud and open-source solutions to cater to different needs.
|
||||
|
||||
See the complete [OSS Docs](https://docs.mem0.ai/open-source/node-quickstart).
|
||||
See the complete [Platform API Reference](https://docs.mem0.ai/api-reference).
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "mem0ai",
|
||||
"version": "3.1.6",
|
||||
"description": "The Memory Layer For Your AI Apps",
|
||||
"description": "The memory layer for AI agents",
|
||||
"main": "./dist/index.js",
|
||||
"module": "./dist/index.mjs",
|
||||
"types": "./dist/index.d.ts",
|
||||
|
||||
@@ -28,7 +28,7 @@ compatibility: Requires Python 3.10+ or Node.js 18+, pip install mem0ai or npm i
|
||||
> - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface
|
||||
> - **[mem0-vercel-ai-sdk](../mem0-vercel-ai-sdk/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)) -- Vercel AI SDK provider
|
||||
|
||||
Mem0 is a managed memory layer for AI applications. It stores, retrieves, and manages user memories via API — no infrastructure to deploy. For self-hosted usage, see the OSS section in the client references below.
|
||||
Mem0 is the managed memory layer for AI agents. It stores, retrieves, and manages user memories via API, no infrastructure to deploy. For self-hosted usage, see the OSS section in the client references below.
|
||||
|
||||
## Step 1: Install and authenticate
|
||||
|
||||
|
||||
Reference in New Issue
Block a user