JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,119 Commits 152 Branches 420 Tags
573ca546370a0d2bfff94cdc552f7c404c76a866
Commit Graph

2119 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Soumil Rathi 573ca54637 fix: restore _is_sensitive_field and sensitive field redaction in _safe_deepcopy_config 
The function and associated constants (_SENSITIVE_FIELDS_EXACT,
_SENSITIVE_SUFFIXES) were accidentally dropped during the merge.
Restores telemetry-safe config cloning that redacts API keys,
passwords, and other secrets while preserving runtime auth objects.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 10:53:56 -07:00
Soumil Rathi 59880a6f8f feat: TS SDK v3 port, graph store removal, client v3 API migration 
TypeScript SDK v3 pipeline (full parity with Python):
- Single-pass additive extraction with ADDITIVE_EXTRACTION_PROMPT
- Hybrid search (semantic + BM25 + entity boost) with additive scoring
- 8-phase batch pipeline (batch embed, persist, entity linking)
- New utils: scoring.ts, lemmatization.ts (natural), entity_extraction.ts (compromise)
- keywordSearch() on 8 vector stores (3 full: PGVector, Memory, Azure AI Search)
- Message persistence in SQLiteManager (rolling window of 10)
- Entity store as second vector collection
- MAX_BATCH=100 chunking guard on OpenAI/Azure embedBatch
- Updated default LLM model to gpt-4.1-nano-2025-04-14
- compromise + natural added as peer dependencies

Graph store removal (Python + TypeScript):
- Removed Neo4j, Memgraph, Kuzu, Neptune, Apache AGE integrations
- Deleted 18 graph-related files across both SDKs
- Removed GraphStoreFactory, GraphStoreConfig, graph_store config field
- Removed "relations" key from all API responses
- Removed graph optional dependency group from pyproject.toml
- Removed neo4j-driver from TS peerDependencies
- Simplified add/search/delete/reset (no more parallel graph operations)

Client SDK v3 API migration:
- add() endpoint: /v1/memories/ -> /v3/memories/ (async response)
- search() endpoint: /v2/memories/search/ -> /v3/memories/search/
- Removed output_format injection and v1.1 unwrapping logic
- Applied to both Python (sync + async) and TypeScript clients

Review feedback fixes:
- Removed deprecated custom_update_memory_prompt from MemoryConfig
- Added MAX_BATCH=100 chunking to Python + TS embed_batch
- Moved all inline imports to top level in main.py
- Cleaned up GraphStoreError dead code from exceptions.py

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 10:45:40 -07:00
Soumil Rathi 3402c67805 fix: address PR review feedback 
- Remove deprecated custom_update_memory_prompt from MemoryConfig entirely
- Add MAX_BATCH=100 chunking guard to embed_batch in openai.py and azure_openai.py
- Move all inline imports (mem0.utils.*) to top-level in main.py
- Remove custom_update_memory_prompt from test fixture

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 09:01:07 -07:00
Soumil Rathi c0343aec1b Merge remote-tracking branch 'origin/feat/v3-pipeline' into feat/v3-pipeline 
# Conflicts:
#	mem0-ts/src/oss/src/utils/factory.ts
#	mem0/vector_stores/milvus.py
#	mem0/vector_stores/qdrant.py
 2026-04-12 16:30:05 -07:00
Soumil Rathi b9e26acf4d merge: integrate main into feat/v3-pipeline + port AsyncMemory to v3 
Merge 190 commits from main including:
- limit→top_k rename across all vector store APIs
- custom_fact_extraction_prompt→custom_instructions rename
- enable_graph flag removal (use self.graph truthiness)
- US/Pacific→timezone.utc normalization
- 18 Category A bug fixes (partial updates, graph cleanup on delete,
  telemetry gating, metadata mutation prevention, filter operator
  merging, delete timestamps, actor_id preservation, etc.)

Conflict resolutions:
- openai.py: merged _pass_dimensions_to_api with embed_batch
- milvus.py: merged partial-update logic with BM25 text field
- qdrant.py: took main's enhanced _create_filter, merged BM25
  sparse vectors with partial-update endpoints
- test_main.py: adopted main's test structure, removed obsolete
  test_custom_prompts, kept hybrid search over-fetch assertion

AsyncMemory v3 port (full parity):
- Rewrote AsyncMemory._add_to_vector_store with the same 8-phase
  batch pipeline as sync Memory (single LLM call, batch embed,
  hash dedup, batch persist, batch entity linking, message saving)
- All blocking calls wrapped in await asyncio.to_thread()
- Moved _build_session_scope to module level for shared access

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-12 16:26:10 -07:00
Kartik 9d6b79a14e fix(sdk): removing the enable graph flag and switching from snake case to camel case for client ts sdk (#4776) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-12 02:40:54 +05:30
Kartik e44b46ef2e fix(sdk): removing deprecating param from our sdk and docs changes with it (#4740) 2026-04-12 00:34:58 +05:30
Saket Aryan 3882af7450 fix(cli): persistent anonymous telemetry ID + pass source=CLI in all API calls (#4789) cli-node-v0.2.3 cli-v0.2.3 2026-04-11 21:00:05 +05:30
Saket Aryan d39ebad09f fix(openclaw): persistent anonymous telemetry ID, flush fix, and email resolution (#4790) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
openclaw-v1.0.6 		2026-04-11 20:57:14 +05:30
Gabriel Stein 9d82e2329d refactor(telemetry): sample OSS hot-path events at 10% to reduce PostHog volume (#4771) 2026-04-11 16:25:38 +05:30
Saket Aryan 398445c691 fix: filters did not support AND, OR and NOT in Qdant and other vector stores (#4780) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-10 23:43:12 +05:30
szinvas 789cc9d607 docs - replace session_id with run_id (#4742) 2026-04-10 20:06:59 +05:30
Jared Diaz e59e3d5f0c Add deepseek.ts to src/llms with corresponding unit tests. Updates fa… (#4613) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-04-10 20:06:22 +05:30
Kartik d926f3697c fix(docs): eliminate ~222 SEO redirect chains on docs.mem0.ai (#4768) 2026-04-10 19:33:45 +05:30
Kartik c996b0e7fa docs: removing the changelog.mdx file adn replacing it with new changelog system (#4750) 2026-04-10 19:07:43 +05:30
Kartik 78ca85a260 refactor: update OpenClaw plugin config, hook logic, and documentation (#4764) openclaw-v1.0.5 2026-04-09 17:36:05 +05:30
Kartik 88f696a60a refactor: drop orgId, projectId, enableGraph config options, update CLI prompts, and clean up related code (#4734) 2026-04-09 14:57:33 +05:30
Ignazio De Santis 081eca6d8f fix: guard temp_uuid_mapping lookups against LLM-hallucinated IDs (fixes #3931) (#4674) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-04-08 21:55:52 +05:30
Kartik 2434b9d550 docs: add ChatDev integration guide and update integrations list (#4751) 2026-04-08 20:16:04 +05:30
Rakhee Singh 3ffea554bc fix(azure_openai): forward response_format to Azure OpenAI API (#4689) 2026-04-08 19:22:02 +05:30
Rakhee Singh 1ad8a59b0c fix(deepseek): forward response_format to OpenAI-compatible API (#4688) 2026-04-08 19:21:11 +05:30
Saket Aryan a670333d67 feat: add AGENTS.md for AI coding agent instructions (#4726) 2026-04-06 21:32:43 +05:30
Saket Aryan 4c2db3e68b feat(skills): introduce Mem0 skill graph with dedicated CLI and Vercel AI SDK skills (#4725) 2026-04-06 20:41:29 +05:30
Saket Aryan 07f0d4f1e0 fix: use npx npm@latest for OIDC trusted publishing (#4724) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
cli-v0.2.2 cli-node-v0.2.2 cli-node-v1.0.4 openclaw-v1.0.4 ts-v2.4.6 		2026-04-06 17:22:00 +05:30
Saket Aryan 3565404eef fix: remove npm self-upgrade from CD workflows (#4723) 2026-04-06 17:11:28 +05:30
Kartik 144627c4ce fix(docs): change the position of the openclaw to agnet plugin and fix the integrations overview and sidebar list view (#4722) v1.0.11 2026-04-06 16:57:24 +05:30
Kartik 6984958138 chore: sat release (#4702) 2026-04-06 16:55:08 +05:30
Kartik b13748c446 feat: add import and event commands, refactor CLI, remove baseUrl config, update docs (#4704) 2026-04-06 16:54:27 +05:30
Soumil Rathi 90f9e6a550 Fix: use caller-provided timestamp for memory created_at instead of always using datetime.now() 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-04 12:52:43 -07:00
Saket Aryan 4642a1d6e3 feat(cli): validate API key upfront via ping and unify telemetry identity resolution (#4701) 2026-04-04 23:03:27 +05:30
Kartik 686d5e987d fix: openclaw plugin and fix the login section there (#4696) 
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com>
 2026-04-04 22:21:46 +05:30
DEVAN CHAUHAN c55447c1e4 [fix] groq model (#4700) 2026-04-04 21:36:17 +05:30
Saket Aryan ee67602c58 feat(cli): add PostHog telemetry and source tracking to Python & Node CLIs (#4699) 2026-04-04 20:47:38 +05:30
Saket Aryan 0daa5d7d03 fix(ci): handle npm prerelease publish across Node.js CD workflows (#4690) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
openclaw-v1.0.4-beta.0 		2026-04-03 21:17:11 +05:30
Kartik cfb3f58e4a fix: adding login and fixing the plugin to follow the openclaw plugin standards (#4686) 2026-04-03 20:59:23 +05:30
Kartik 66230b3f1f docs: update integration docs with new SVG icons and links (#4684) 2026-04-03 20:54:46 +05:30
Soumil Rathi a6130c5436 perf: skip ThreadPoolExecutor when graph store is disabled 
Avoids spawning 2 threads per add() call when graph is not configured.
Fixes thread leakage under high concurrency (was accumulating 3500+ threads
per worker). Calls _add_to_vector_store directly in the current thread.

Applied to both sync Memory and async AsyncMemory classes.
 2026-04-03 07:42:32 -07:00
BillionToken 1941cae031 fix(server): add missing psycopg-pool dependency (#4374) 
Co-authored-by: BillionClaw <267901332+BillionClaw@users.noreply.github.com>
 2026-04-03 20:04:05 +05:30
Utkarsh fcbb70ab3b fix: prevent thread and memory leaks from PostHog telemetry (#4535) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-04-03 20:01:04 +05:30
Soumil Rathi cb64d978fc perf: batch entity linking — embed, search, insert in bulk instead of per-entity 
- Replace sequential _upsert_entity() loop with batched pipeline:
  1. Global dedup: collect unique entities across all memories
  2. Single embed_batch() call for all entity texts
  3. Batch search via search_batch() (Qdrant query_batch_points)
  4. Batch insert for new entities, individual updates for existing
- Add search_batch() to VectorStoreBase (sequential fallback)
- Add native search_batch() to Qdrant using query_batch_points
- ~6-10x reduction in entity linking network round trips
 2026-04-02 19:32:29 -07:00
Soumil Rathi 41532d8850 refactor(oss): trim and update ADDITIVE_EXTRACTION_PROMPT 
Streamline prompt guidelines and update examples for clarity.
Remove redundant sections and verbose explanations.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-02 12:11:52 -07:00
Chaithanya Kumar 33d2bc495d fix(openclaw): clear security scanner exfiltration warning (#4678) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com>
openclaw-v1.0.3 		2026-04-03 00:34:49 +05:30
Gabriel Stein c0cae68646 feat(plugin): add Codex plugin support and integration docs (#4665) 
Co-authored-by: Gabriel Stein <gabrielstein416@gmail.com>
 2026-04-03 00:18:02 +05:30
Soumil Rathi 9c9b3d54e2 feat(oss): make spaCy an optional dependency 
Move spacy from core dependencies to optional [nlp] extra.
The system gracefully degrades without spaCy:
- Lemmatization falls back to raw text
- Entity extraction returns empty (no entity boost)
- BM25 keyword search still works on raw text
- Semantic search and additive scoring unaffected

Install with NLP support: pip install mem0ai[nlp]

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-02 11:04:38 -07:00
Soumil Rathi 70c62ea54f fix: add text_lemmatized to create/update memory + fix keyword search across vector stores 
- Add text_lemmatized to _create_memory() and _update_memory() (sync + async)
  so BM25/keyword search works for all code paths, not just the batch pipeline
- pgvector: add GIN index on text_lemmatized for fast full-text search
- pgvector: add error logging to keyword_search
- milvus: add sparse BM25 field + function to create_col() so keyword_search works
- mongodb: auto-create Atlas Search text index in create_col()
- azure_mysql: add generated column + FULLTEXT index for keyword_search
 2026-04-02 10:34:03 -07:00
Soumil Rathi 4534acdfbe feat(qdrant): implement client-side BM25 sparse vectors via fastembed 
- Add sparse_vectors_config with 'bm25' named vector to create_col()
- Compute BM25 sparse vectors from text_lemmatized during insert/update
- Use client-side fastembed Qdrant/bm25 encoder instead of server-side inference
- Graceful fallback if fastembed not installed
- Fixes keyword_search() returning None on self-hosted Qdrant
 2026-04-02 10:23:17 -07:00
Saket Aryan 3b2f01796e feat(cli): comprehensive docs, version bump, and purple branding (#4680) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
cli-node-v0.2.1 cli-v0.2.1 		2026-04-02 22:52:00 +05:30
Chaithanya Kumar 9cd3d2cca8 fix(openclaw): remove process.env access to clear security scanner warning (#4676) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
openclaw-v1.0.2 		2026-04-02 21:19:12 +05:30
Saket Aryan c53f1f126d docs(openclaw): add v1.0.1 changelog and release notes (#4675) openclaw-v1.0.1 2026-04-02 20:25:49 +05:30
Patel Tirth 0b7615fa87 docs: add api_key parameter to Google AI LLM provider config examples (#4626) 2026-04-02 19:37:23 +05:30