What's Changed

• fix(memory): set updated_at on creation and preserve pre-existing created_at by @utkarsh240799 in #4499
• feat: add reasoning_effort parameter support for reasoning models by @GopalGB in #4461
• fix(vector_stores): handle vector=None in Milvus and Qdrant update methods by @utkarsh240799 in #4568
• fix: preserve original actor_id during memory update by @kartik-mem0 in #4570
• docs: add navigation links for platform features in docs by @kartik-mem0 in #4572
• feat: add official mem0 CLI (Python & TypeScript) by @whysosaket in #4575
• docs: improve CLI dev workflow and prioritize Node.js installation by @whysosaket in #4579
• fix(docs): add Token prefix to Events API code examples by @agumpandey in #3927
• refactor: update default Gemini and Vertex AI embedder model to gemini-embedding-001 by @kartik-mem0 in #4571
• [docs] fix python quickstart code snippet #3770 by @danielsiwiec in #3771
• docs: add content-writing cookbook to operations by @kartik-mem0 in #4566
• fix: rebuild FAISS index on vector deletion by @Br1an67 in #4178
• fix: remove README.md from wheel shared-data by @l1anch1 in #4052
• feat: adding oss version of companion cookbook by @kartik-mem0 in #4564
• docs: add installation and configuration guide for email automation with Mem0 open source by @kartik-mem0 in #4567
• fix(memory): centralize entity cleanup and skip malformed LLM relation dicts by @Himanshu-Sangshetti in #4515
• chore: fix failing CI lint errors by @kartik-mem0 in #4584
• fix(ts): work around Qdrant Cloud "Illegal host" error by @utkarsh240799 in #4565
• chore: bump mem0ai and mem0-ts versions to 1.0.9/2.4.4 and update changelog by @kartik-mem0 in #4585

New Contributors

• @GopalGB made their first contribution in #4461
• @agumpandey made their first contribution in #3927
• @danielsiwiec made their first contribution in #3771
• @l1anch1 made their first contribution in #4052

Full Changelog: v1.0.8...v1.0.9

What's Changed

• docs: add Claude Code setup instructions for OpenMemory by @utkarsh240799 in #4430
• fix: handle None content and empty candidates in GeminiLLM parsing by @kartik-mem0 in #4462
• feat: add NemoClaw + Mem0 plugin setup scripts and quickstart by @utkarsh240799 in #4464
• fix(graph): soft-delete graph relationships instead of hard DELETE by @sxu75374 in #4188
• feat: integrate turbopuffer as vector database provider by @utkarsh240799 in #4428
• Add missing SEO metadata to turbopuffer page by @mintlify[bot] in #4468
• fix(qdrant): implement enhanced metadata filtering operators by @longway-code in #4127
• fix: use root LLM config as fallback for graph store instead of hardcoded OpenAI default by @utkarsh240799 in #4466
• fix: Bug: Zod Schema Incompatible with OpenAI Structured Outputs API by @Paulie-Aditya in #3462
• refactor: add vector validation to OpenSearchDB to ensure non‑null, non‑empty, and correct‑dimension vectors by @kartik-mem0 in #4472
• fix(mcp): operator precedence in search_memory filter (#4470) by @Himanshu-Sangshetti in #4474
• Fix 4 broken placeholder links in template files by @mintlify[bot] in #4478
• fix: upgrade MongoDB vector store from deprecated knnVector to GA vectorSearch by @veeceey in #3995
• fix: accept default /tmp/chroma path in ChromaDbConfig validator by @Br1an67 in #4179
• fix: add missing limit, threshold, infer, memory_type, and prompt params to REST API by @utkarsh240799 in #4496
• fix(qdrant): do not remove local path on init (#4473) by @Himanshu-Sangshetti in #4475
• docs: add issue templates for bug, feature, benchmark, documentation, and update contact links by @kartik-mem0 in #4500
• chore: update issue templates and workflows for improved labeling and formatting by @kartik-mem0 in #4501
• fix(ts-oss): register pgvector in VectorStoreFactory (#3367) by @Himanshu-Sangshetti in #4502
• fix: align Databricks docs with config and fix query mode selection by @utkarsh240799 in #4477
• fix: clean up graph store data on Memory.delete() by @utkarsh240799 in #4505
• docs: add Vibecoding guide with Mem0 integration by @kartik-mem0 in #4511
• chore: remove benchmark submission issue template and label matcher by @kartik-mem0 in #4514
• fix: avoid sending both temperature and top_p to Anthropic API by @utkarsh240799 in #4471
• fix: preserve custom metadata when updating memory by @kartik-mem0 in #4495
• docs: remove OpenMemory references from docs, README, and issue templates by @whysosaket in #4520
• chore: replace local MCP and Smithery with cloud MCP server by @whysosaket in #4532
• fix(bedrock): omit topP for Anthropic Converse; use AWSBedrockConfig in LlmFactory by @Himanshu-Sangshetti in #4469
• fix: prevent in-place mutation of metadata in _create_memory by @utkarsh240799 in #4529
• feat: expose infer param in MCP add_memories tool by @utkarsh240799 in #4517
• MCP: add Streamable HTTP transport endpoint by @lan17 in #4122
• Fix: prevent double embedding in mem0.add (fixes #3723) by @veeceey in #3996
• fix: sanitize hyphens in Neo4j Cypher relationship names by @lamost423 in #4154
• Fix/OpenAI embedding dimensions 4153 by @Himanshu-Sangshetti in #4481
• feat: add Mem0 plugin for Claude Code and Cursor by @gabrielstein-mem0 in #4518
• fix(openclaw): prevent extraction of standalone timestamps as memories by @chaithanyak42 in #4550
• fix: handle chatty LLM responses in JSON parsing by @utkarsh240799 in #4525
• fix(openclaw): improve credential detection in extraction instructions by @chaithanyak42 in #4552
• fix: add timestamps for DELETE operations in history by @VictorECDSA in #4492
• docs: fix LLM reranker config examples and field names by @utkarsh240799 in #4539
• fix: update parameter added to the update function which is exposed t… by @zaiddkhan in #3799
• docs: fix OSS REST API endpoint discrepancies by @utkarsh240799 in #4555
• fix(oss): make pgvector pg import compatible with ESM by @fmercurio in #4544
• fix: prevent SQL injection in Databricks vector store by @utkarsh240799 in #4558
• fix: merge multiple filter operators for same key by @utkarsh240799 in #4559
• Fix short SEO description in integration guide template by @mintlify[bot] in #4551
• fix(plugin): make Cursor plugin fully functional by @gabrielstein-mem0 in #4547
• chore: updating the sdk version and changelog by @kartik-mem0 in #4561

New Contributors

• @longway-code made their first contribution in #4127
• @Paulie-Aditya made their first contribution in #3462
• @Br1an67 made their first contribution in #4179
• @lan17 made their first contribution in #4122
• @lamost423 made their first contribution in #4154
• @gabrielstein-mem0 made their first contribution in #4518
• @VictorECDSA made their first contribution in #4492
• @zaiddkhan made their first contribution in #3799
• @fmercurio made their first contribution in #4544

Full Changelog: v1.0.7...v1.0.8

What's Changed

• docs: add MiroFish integration and swarm memory cookbook documentation by @kartik-mem0 in #4373
• chore: remove the integration/mirofish path from docs by @kartik-mem0 in #4399
• fix(ollama): pass tools to client.chat and parse tool_calls from response by @sxu75374 in #4176
• fix(oss): normalize malformed LLM fact output before embedding by @amahuli03 in #4224
• refactor: improve Ollama embedder, normalize model names, add error handling, update tests by @kartik-mem0 in #4403
• fix: pass encoding_format='float' in OpenAI embeddings for proxy compatibility by @AtharvaJaiswal005 in #4058
• fix: forward tools parameter to Gemini API in GoogleLLM (#4380) by @DhilipBinny in #4386
• fix(ts-sdk): externalize all peerDependencies in tsup config by @kartik-mem0 in #4408
• feat(openclaw): improve extraction quality with noise filtering, deduplication, and better instructions by @utkarsh240799 in #4302
• fix(docs): add redirect rules for legacy and moved documentation pages by @whysosaket in #4413
• fix(reranker): support nested llm config in LLMReranker for non-OpenAI providers by @kartik-mem0 in #4405
• fix: add LLM provider detection and defaults to memory config by @kartik-mem0 in #4400
• fix: preserve http_auth in _safe_deepcopy_config for OpenSearch (#3580) by @utkarsh240799 in #4418
• replace hardcoded US/Pacific timezone references with timezone.utc by @amahuli03 in #4404
• fix: handle control characters in LLM JSON responses by @utkarsh240799 in #4420
• feat(test): integration test for ts-sdk by @kartik-mem0 in #4395
• chore: delete obsolete e2e tests by @kartik-mem0 in #4419
• fix: handle truncated code blocks in removeCodeBlocks function by @kartik-mem0 in #4421
• refactor: fix webhook create/update serialization, add payload types, and MEMORY_CATEGORIZED event by @kartik-mem0 in #4429
• fix: wrap vector and payload in lists for Langchain.update by @kartik-mem0 in #4446
• fix: prevent embedding corruption in Valkey and Redis when vector is None (#4336) by @DhilipBinny in #4362
• Improve SEO metadata across documentation pages by @mintlify[bot] in #4447
• feat: add optional API key authentication to REST API server by @utkarsh240799 in #4442
• fix: raise ValueError when deleting nonexistent memory by @kartik-mem0 in #4455
• feat: add MiniMax LLM provider (#4132) by @Himanshu-Sangshetti in #4431
• fix: add missing _parse_response to AzureOpenAIStructuredLLM by @mvanhorn in #4434
• feat: add Apache AGE graph store support by @utkarsh240799 in #4448
• fix: use toCamelCase in redis get method for the payload by @Failfail2603 in #3172
• Fix: add pgvector support to NodeJS OSS VectorStoreFactory (fixes #3491) by @veeceey in #3997

New Contributors

• @sxu75374 made their first contribution in #4176
• @AtharvaJaiswal005 made their first contribution in #4058
• @mintlify[bot] made their first contribution in #4447
• @Himanshu-Sangshetti made their first contribution in #4431
• @mvanhorn made their first contribution in #4434
• @Failfail2603 made their first contribution in #3172
• @veeceey made their first contribution in #3997

Full Changelog: v1.0.6...v1.0.7

What's Changed

• Fix handle malformed entity dicts and None LLM response in memgraph_memory by @liviaellen in #4238
• feat(openclaw): add per-agent memory isolation for multi-agent setups by @utkarsh240799 in #4245
• docs(openclaw): clarify userId is user-defined by @utkarsh240799 in #4277
• fix(openclaw): migrate platform search to mem0 v2 API by @utkarsh240799 in #4276
• fix(ts-sdk): replace sqlite3 with better-sqlite3 to fix native binding resolution by @utkarsh240799 in #4270
• chore(openclaw): bump version to 0.3.0 by @utkarsh240799 in #4283
• fix(docs): correct Deploy with Docker Compose card link by @kartik-mem0 in #4296
• fix(docs): use filters param for search in LiveKit integration by @kartik-mem0 in #4300
• fix(ts-sdk): resolve SQLite db paths correctly in OSS mode by @utkarsh240799 in #4307
• fix(oss): auto-detect embedding dimension to fix Qdrant mismatch with non-OpenAI embedders by @utkarsh240799 in #4297
• feat(skills): add Mem0 Platform Claude Code skill by @kartik-mem0 in #4309
• fix(openclaw): use absolute URL for architecture image in README by @utkarsh240799 in #4311
• fix: add missing 'json' keyword to graph memory prompts (fixes #4248) by @giulio-leone in #4249
• fix OpenAI embedder baseurl by @amahuli03 in #4275
• fix: incorrect database param by @ajmalmohad in #3913
• chore: bump protobuf dependency to 5.29.6 and extend upper bound to 7.0.0 by @kartik-mem0 in #4326
• fix(ts): extract content from code blocks instead of deleting it by @voidborne-d in #4317
• chore(ts-sdk): bump mem0ai version to 2.4.0 by @utkarsh240799 in #4332
• chore(ts-sdk): fix lints by @whysosaket in #4334
• chore(openclaw): add tsup build pipeline with ESM output and type declarations by @whysosaket in #4335
• fix(openclaw): point plugin extension entry to built output for npm compatibility by @whysosaket in #4340
• fix: key error when llm omits entities key tool call by @amahuli03 in #4313
• fix: skip telemetry vector store init when MEM0_TELEMETRY is disabled by @kartik-mem0 in #4351
• fix: remove destructive vector_store.reset() from delete_all() by @kartik-mem0 in #4349
• fix(openclaw): add SQLite resilience for OSS mode initialization by @utkarsh240799 in #4337
• fix(oss): OllamaLLM now respects configured url instead of always falling back to localhost by @kartik-mem0 in #4320
• chore: update langchain dependencies to v1.0.0 by @kartik-mem0 in #4353
• fix: Ensure JSON instruction in prompts for json_object response format (#3559) by @DhilipBinny in #4271
• chore(docs): adding skills.sh installation command in the readme. by @kartik-mem0 in #4350
• chore: bump mem0-ts to 2.4.1, pyproject to 1.0.6, update changelog with bug fixes by @kartik-mem0 in #4361
• docs: fix mintlify build failing by @whysosaket in #4363
• feat: add openclaw checks CI workflow by @whysosaket in #4368
• fix: cast vector_distance to float in Redis search by @utkarsh240799 in #4377
• fix(qdrant): handle 401/403 in ensureCollection for scoped JWTs by @huveewomg in #4356
• feat(mem0-ts): add LM Studio embedder and LLM support by @utkarsh240799 in #4354
• chore: end to end test coverage for ts sdk by @kartik-mem0 in #4357

New Contributors

• @liviaellen made their first contribution in #4238
• @utkarsh240799 made their first contribution in #4245
• @kartik-mem0 made their first contribution in #4296
• @giulio-leone made their first contribution in #4249
• @amahuli03 made their first contribution in #4275
• @ajmalmohad made their first contribution in #3913
• @voidborne-d made their first contribution in #4317
• @DhilipBinny made their first contribution in #4271
• @huveewomg made their first contribution in #4356

Full Changelog: v1.0.5...v1.0.6

What's Changed

• docs: add memory_categorize webhook event type by @MgeeeeK in #4077
• Add source openclaw by @deshraj in #4082
• Update OpenClaw integration architecture diagram by @prathameshagrawal in #4079
• fix: Bug: Openclaw Extension OSS Mode lacks threshold restrictions (#4106) by @mem0-bot[bot] in #4115
• fix(oss): validate LLM fact output via FactRetrievalSchema before embedding by @mgoulart in #4083
• docs: update delete_all to reflect filter validation breaking change by @whysosaket in #4103
• chore(ts-sdk): bump axios to 1.13.6 by @whysosaket in #4177
• fix: disable ph telemetry still calls posthog by @whysosaket in #4203

New Contributors

• @prathameshagrawal made their first contribution in #4079
• @mem0-bot[bot] made their first contribution in #4115
• @mgoulart made their first contribution in #4083

Full Changelog: v1.0.4...v1.0.5

What's Changed

• chore: remove legacy v0.x docs and version dropdown by @whysosaket in #4060
• OpenClaw plugin: fix auto-recall injection and auto-capture message drop by @Zlo7 in #4065
• chore: update user facing timestamp for a memory by @MgeeeeK in #4066

New Contributors

• @Zlo7 made their first contribution in #4065
• @MgeeeeK made their first contribution in #4066

Full Changelog: v1.0.3...v1.0.4

What's Changed

• feat: add OpenClaw plugin and documentation by @deshraj in #3964
• fix: add OpenClaw to docs navigation by @deshraj in #3965
• chore: add update project options by @whysosaket in #3947

Full Changelog: v1.0.2...v1.0.3

What's Changed

• [feat add]FastEmbed embedding for local embeddings by @lucifertrj in #3552
• Fix condition check for memories_result type in Memory class by @aesher9o1 in #3596
• Add Apache Cassandra vector store support by @faizan842 in #3578
• feat: Add configurable embedding similarity threshold for graph store node matching by @ron-42 in #3593
• Fix list_memories endpoint Pydantic validation error by @frederikb96 in #3608
• Fix memory deletion not removing from vector store by @frederikb96 in #3610
• Fix embedder config schema to support embeddingDims and url parameters by @Mrinank-Bhowmick in #3633
• Fix condition check for memories_result type in AsyncMemory class by @rahulsharmavishwakarma in #3621
• Add redirect to new apis doc page by @prateekchhikara in #3639
• fix: Prevent Mock object issues in graph memory tests by @ron-42 in #3627
• Fix: Add missing filter methods to AsyncMemory by @frederikb96 in #3624
• Fix REST API infer parameter ignored by @frederikb96 in #3607
• Add delete_memories MCP tool for targeted deletion by @frederikb96 in #3616
• feat(api): add vector store configuration endpoints by @vedant381 in #3583
• [fix] list' object has no attribute 'id' - Id fault with chroma pinecone and other providers by @parthshr370 in #3693
• Add Strands agent (with AWS ElastiCache and Neptune) example mention in Joint blog post by Mem0 and AWS by @swarnaprakash in #3824
• chore: remove unnecessary dependencies from Vercel AI SDK to reduce package size by @whysosaket in #3856
• (ts-sdk-update): Update for TypeScript SDK v2.2. by @whysosaket in #3865
• feat(ts-sdk): add support for keyword arguments in add and search methods by @whysosaket in #3895
• INTPYTHON-722 - Add DriverInfo metadata to MongoDB vector store by @NoahStapp in #3648
• chore: do a disk cleanup in gh actions by @whysosaket in #3899
• (fix): mongodb distribution name, azure ai search, and workflow trigger by @whysosaket in #3900
• (version-bump): update the project version to v1.0.2 by @whysosaket in #3902

New Contributors

• @aesher9o1 made their first contribution in #3596
• @faizan842 made their first contribution in #3578
• @ron-42 made their first contribution in #3593
• @rahulsharmavishwakarma made their first contribution in #3621
• @parthshr370 made their first contribution in #3603
• @NoahStapp made their first contribution in #3648

Full Changelog: v1.0.0...v1.0.2

🚀 What’s New in Mem0 v1.0.0

This release marks a major milestone for Mem0 — introducing v1.0.0 with key architectural improvements, expanded vector store integrations, and broader LLM provider compatibility. Expect better performance, more stability, and enhanced developer experience across SDKs.

🌟 New Features

• Added Azure MySQL support for improved cloud database flexibility by @parshvadaftari
• Introduced Azure AI Search Vector Store support for the TypeScript SDK by @G26karthik
• Added Tool Call support for LangchainLLM by @soapun
• Enabled custom model and parameters for Hugging Face with huggingface_base_url by @vedant381
• Added default LLM configuration updates for streamlined setup by @parshvadaftari
• Enabled async mode as default for optimized performance by @kk2211
• Reranker support - cohere, zeroentropy, huggingface, sentence transformers and LLMs by @parshvadaftari
• Added metadata filtering for the OSS @parshvadaftari
• Added Assisstant memory retrieval by @parshvadaftari
• Improved prompt for better memory retrieval by @parshvadaftari

🧠 Improvements & Fixes

• Refactored v2 search and update examples by @parshvadaftari
• Fixed Databricks Vector Store integration by @hayescode
• Fixed Milvus DB bug and added test coverage by @parshvadaftari
• Fixed Weaviate search method by @matanco1
• Fixed non-serializable objects in config deepcopy by @lsvishaal
• Fixed bug with thinking LLM in vLLM by @dog-last
• Fixed license and README metadata by @lsvishaal
• Fixed hardcoded embedding dimensions and TypeScript build issues by @Mrinank-Bhowmick
• Fixed missing ‘data’ key handling during search operations by @lsvishaal
• Improved Get Memories playground and documentation examples by @parshvadaftari
• Added detailed explanation for output_format v1.1 parameter by @lsvishaal
• Updated dependency compatibility with OpenAI 2.x by @yashikabadaya
• Updated main script and removed stale code by @deshraj
• Added version=v2 as default param in AI SDK add calls by @whysosaket
• Validated embedding_dims for Kuzu integration by @soapun

🧩 Documentation Updates

• Updated and refactored core docs by @deshraj & @parshvadaftari
• Added V2 Filter documentation by @whysosaket

👥 New Contributors

• @lsvishaal made their first contribution in [#3522](#3522)
• @frederikb96 made their first contribution in [#3523](#3523)
• @matanco1 made their first contribution in [#3521](#3521)
• @dog-last made their first contribution in [#3510](#3510)
• @yashikabadaya made their first contribution in [#3533](#3533)
• @soapun made their first contribution in [#3542](#3542)
• @vedant381 made their first contribution in [#3574](#3574)
• @G26karthik made their first contribution in [#3549](#3549)
• @kk2211 made their first contribution in [#3585](#3585)

Full Changelog: [v0.1.118 → v1.0.0](v0.1.118...v1.0.0)

What's Changed

• feat: Add metadata param to TS-SDK in client.update by @whysosaket in #3415
• fix: Use ConfigDict instead of class-based Config by @gabe-l-hart in #3409
• databricks bug fixes by @hayescode in #3416
• fix: 🐛 replace hardcoded llm provider with provider from config by @ranjithkumar8352 in #3423
• Added support for chromadb cloud by @parshvadaftari in #3436
• updates to the category docs by @prateekchhikara in #3437
• feat(vector-store): Add Valkey vector store support by @swarnaprakash in #3272
• Fix bedrock anthropic models to use system field by @acarbonetto in #3438
• docs: Update Search V2/Get All V2 Filters by @whysosaket in #3450
• Fixes ollama and updates openai dependency by @parshvadaftari in #3452
• fix: correct typo in knowledge graph extraction guidelines by @codexvn in #3449
• Fix json parsing with new memories by @parshvadaftari in #3456
• Feat: Mem0 vector store backend integration for Neptune Analytics by @andy-k-improving in #3453
• Aspen theme for 1.x by @parshvadaftari in #3473
• feat: implement structured exception classes with error codes and sug… by @bkidd1 in #3279
• Add Neptune-DB graph store with vector store by @acarbonetto in #3443
• Added weaviate db test by @parshvadaftari in #3483
• Fixed s3 vectors memory initialization issue from configuration by @abdullahirfann in #3481
• [DOCS] Changing 1.0 to 1.0.0 by @parshvadaftari in #3486
• Refactored example title for aws by @parshvadaftari in #3492
• feat(ai-sdk): added file support for multimodal capabilities with memory context by @whysosaket in #3500
• docs-fix: Quickstart cURL example fixed by @whysosaket in #3503
• [test] Add comprehensive test suite for SQLiteManager by @KarthikeyaKollu in #3494
• Update version to 0.1.118 by @parshvadaftari in #3505

New Contributors

• @gabe-l-hart made their first contribution in #3409
• @ranjithkumar8352 made their first contribution in #3423
• @swarnaprakash made their first contribution in #3272
• @codexvn made their first contribution in #3449
• @bkidd1 made their first contribution in #3279
• @abdullahirfann made their first contribution in #3481
• @KarthikeyaKollu made their first contribution in #3494

Full Changelog: v0.1.117...v0.1.118