my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: "Product Updates"
#3	mode: "wide"
#4	---
#5
#6
#7	<Tabs>
#8	<Tab title="Python">
#9
#10	<Update label="2026-03-03" description="v1.0.5">
#11	- Telemetry Fix
#12	- Fixed an issue where the PostHog client was initialized even after telemetry was disabled. Although events were not captured, the client was unnecessarily initialized.
#13	</Update>
#14
#15	<Update label="2026-02-17" description="v1.0.4">
#16
#17	New Features & Updates:
#18	- Memory Update:
#19	- Added `timestamp` parameter to `update()` — accepts Unix epoch (int/float) or ISO 8601 string
#20
#21	</Update>
#22
#23	<Update label="2026-01-29" description="v1.0.3">
#24
#25	New Features & Updates:
#26	- Project Settings:
#27	- Added inclusion prompt, exclusion prompt, memory depth, and usecase setting
#28
#29	</Update>
#30
#31	<Update label="2026-01-13" description="v1.0.2">
#32
#33	New Features & Updates:
#34	- Vector Stores:
#35	- Added DriverInfo metadata to MongoDB vector store
#36
#37	</Update>
#38
#39	<Update label="2025-11-14" description="v1.0.1">
#40
#41	New Features & Updates:
#42	- Vector Stores:
#43	- Added Apache Cassandra vector store support
#44	- Embeddings:
#45	- Added FastEmbed embedding support for local embeddings
#46	- Graph Store:
#47	- Added configurable embedding similarity threshold for graph store node matching
#48
#49	Bug Fixes:
#50	- Core:
#51	- Fixed condition check for memories_result type in Memory class
#52	- Fixed list_memories endpoint Pydantic validation error
#53	- Fixed memory deletion not removing from vector store
#54
#55	</Update>
#56
#57	<Update label="2025-10-16" description="v1.0.0">
#58
#59	New Features & Updates:
#60	- Vector Stores:
#61	- Added Azure MySQL support
#62	- Added Azure AI Search Vector Store support
#63	- LLMs:
#64	- Added Tool Call support for LangchainLLM
#65	- Enabled custom model and parameters for Hugging Face with huggingface_base_url
#66	- Updated default LLM configuration
#67	- Rerankers:
#68	- Added reranker support: Cohere, ZeroEntropy, Hugging Face, Sentence Transformers, and LLMs
#69	- Core:
#70	- Added metadata filtering for OSS
#71	- Added Assistant memory retrieval
#72	- Enabled async mode as default
#73
#74	Improvements:
#75	- Prompts:
#76	- Improved prompt for better memory retrieval
#77	- Dependencies:
#78	- Updated dependency compatibility with OpenAI 2.x
#79	- Validation:
#80	- Validated embedding_dims for Kuzu integration
#81
#82	Bug Fixes:
#83	- Vector Stores:
#84	- Fixed Databricks Vector Store integration
#85	- Fixed Milvus DB bug and added test coverage
#86	- Fixed Weaviate search method
#87	- LLMs:
#88	- Fixed bug with thinking LLM in vLLM
#89
#90	</Update>
#91
#92	<Update label="2025-09-25" description="v0.1.118">
#93
#94	New Features & Updates:
#95	- Vector Stores:
#96	- Added Valkey vector store support
#97	- Added support for ChromaDB Cloud
#98	- Added Mem0 vector store backend integration for Neptune Analytics
#99	- Graph Store:
#100	- Added Neptune-DB graph store with vector store
#101	- Core:
#102	- Implemented structured exception classes with error codes and suggested actions
#103
#104	Improvements:
#105	- Dependencies:
#106	- Updated OpenAI dependency and improved Ollama compatibility
#107	- Testing:
#108	- Added Weaviate DB test
#109	- Added comprehensive test suite for SQLiteManager
#110	- Documentation:
#111	- Updated category docs
#112	- Updated Search V2 / Get All V2 filters documentation
#113	- Refactored AWS example title
#114	- Fixed Quickstart cURL example
#115
#116	Bug Fixes:
#117	- Vector Stores:
#118	- Databricks bug fixes
#119	- Fixed S3 Vectors memory initialization issue from configuration
#120	- Core:
#121	- Fixed JSON parsing with new memories
#122	- Replaced hardcoded LLM provider with provider from configuration
#123	- LLMs:
#124	- Fixed Bedrock Anthropic models to use system field
#125
#126	</Update>
#127
#128	<Update label="2025-09-03" description="v0.1.117">
#129
#130	New Features & Updates:
#131	- OpenMemory:
#132	- Added memory export / import feature
#133	- Added vector store integrations: Weaviate, FAISS, PGVector, Chroma, Redis, Elasticsearch, Milvus
#134	- Added `export_openmemory.sh` migration script
#135	- Vector Stores:
#136	- Added Amazon S3 Vectors support
#137	- Added Databricks Mosaic AI vector store support
#138	- Added support for OpenAI Store
#139	- Graph Memory: Added support for graph memory using Kuzu
#140	- Azure: Added Azure Identity for Azure OpenAI and Azure AI Search authentication
#141	- Elasticsearch: Added headers configuration support
#142
#143	Improvements:
#144	- Added custom connection client to enable connecting to local containers for Weaviate
#145	- Updated configuration AWS Bedrock
#146	- Fixed dependency issues and tests; updated docstrings
#147	- Documentation:
#148	- Fixed Graph Docs page missing in sidebar
#149	- Updated integration documentation
#150	- Added version param in Search V2 API documentation
#151	- Updated Databricks documentation and refactored docs
#152	- Updated favicon logo
#153	- Fixed typos and Typescript docs
#154
#155	Bug Fixes:
#156	- Baidu: Added missing provider for Baidu vector DB
#157	- MongoDB: Replaced `query_vector` args in search method
#158	- Fixed new memory mistaken for current
#159	- AsyncMemory._add_to_vector_store: handled edge case when no facts found
#160	- Fixed missing commas in Kuzu graph INSERT queries
#161	- Fixed inconsistent created and updated properties for Graph
#162	- Fixed missing `app_id` on client for Neptune Analytics
#163	- Correctly pick AWS region from environment variable
#164	- Fixed Ollama model existence check
#165
#166	Refactoring:
#167	- PGVector: Use internal connection pools and context managers
#168
#169	</Update>
#170
#171	<Update label="2025-08-14" description="v0.1.116">
#172
#173	New Features & Updates:
#174	- Pinecone: Added namespace support and improved type safety
#175	- Milvus: Added db_name field to MilvusDBConfig
#176	- Vector Stores: Added multi-id filters support
#177	- Vercel AI SDK: Migration to AI SDK V5.0
#178	- Python Support: Added Python 3.12 support
#179	- Graph Memory: Added sanitizer methods for nodes and relationships
#180	- LLM Monitoring: Added monitoring callback support
#181
#182	Improvements:
#183	- Performance:
#184	- Improved async handling in AsyncMemory class
#185	- Documentation:
#186	- Added async add announcement
#187	- Added personalized search docs
#188	- Added Neptune examples
#189	- Added V5 migration docs
#190	- Configuration:
#191	- Refactored base class config for LLMs
#192	- Added sslmode for pgvector
#193	- Dependencies:
#194	- Updated psycopg to version 3
#195	- Updated Docker compose
#196
#197	Bug Fixes:
#198	- Tests:
#199	- Fixed failing tests
#200	- Restricted package versions
#201	- Memgraph:
#202	- Fixed async attribute errors
#203	- Fixed n_embeddings usage
#204	- Fixed indexing issues
#205	- Vector Stores:
#206	- Fixed Qdrant cloud indexing
#207	- Fixed Neo4j Cypher syntax
#208	- Fixed LLM parameters
#209	- Graph Store:
#210	- Fixed LM config prioritization
#211	- Dependencies:
#212	- Fixed JSON import for psycopg
#213
#214	Refactoring:
#215	- Google AI: Refactored from Gemini to Google AI
#216	- Base Classes: Refactored LLM base class configuration
#217
#218	</Update>
#219
#220	<Update label="2025-07-24" description="v0.1.115">
#221
#222	New Features & Updates:
#223	- Enhanced project management via `client.project` and `AsyncMemoryClient.project` interfaces
#224	- Full support for project CRUD operations (create, read, update, delete)
#225	- Project member management: add, update, remove, and list members
#226	- Manage project settings including custom instructions, categories, retrieval criteria, and graph enablement
#227	- Both sync and async support for all project management operations
#228
#229	Improvements:
#230	- Documentation:
#231	- Added detailed API reference and usage examples for new project management methods.
#232	- Updated all docs to use `client.project.get()` and `client.project.update()` instead of deprecated methods.
#233
#234	- Deprecation:
#235	- Marked `get_project()` and `update_project()` as deprecated (these methods were already present); added warnings to guide users to the new API.
#236
#237	Bug Fixes:
#238	- Tests:
#239	- Fixed Gemini embedder and LLM test mocks for correct error handling and argument structure.
#240	- vLLM:
#241	- Fixed duplicate import in vLLM module.
#242
#243	</Update>
#244
#245	<Update label="2025-07-05" description="v0.1.114">
#246
#247	New Features:
#248	- OpenAI Agents: Added OpenAI agents SDK support
#249	- Amazon Neptune: Added Amazon Neptune Analytics graph_store configuration and integration
#250	- vLLM: Added vLLM support
#251
#252	Improvements:
#253	- Documentation:
#254	- Added SOC2 and HIPAA compliance documentation
#255	- Enhanced group chat feature documentation for platform
#256	- Added Google AI ADK Integration documentation
#257	- Fixed documentation images and links
#258	- Setup: Fixed Mem0 setup, logging, and documentation issues
#259
#260	Bug Fixes:
#261	- MongoDB: Fixed MongoDB Vector Store misaligned strings and classes
#262	- vLLM: Fixed missing OpenAI import in vLLM module and call errors
#263	- Dependencies: Fixed CI issues related to missing dependencies
#264	- Installation: Reverted pip install changes
#265
#266	</Update>
#267
#268	<Update label="2025-06-30" description="v0.1.113">
#269
#270	Bug Fixes:
#271	- Gemini: Fixed Gemini embedder configuration
#272
#273	</Update>
#274
#275	<Update label="2025-06-27" description="v0.1.112">
#276
#277	New Features:
#278	- Memory: Added immutable parameter to add method
#279	- OpenMemory: Added async_mode parameter support
#280
#281	Improvements:
#282	- Documentation:
#283	- Enhanced platform feature documentation
#284	- Fixed documentation links
#285	- Added async_mode documentation
#286	- MongoDB: Fixed MongoDB configuration name
#287
#288	Bug Fixes:
#289	- Bedrock: Fixed Bedrock LLM, embeddings, tools, and temporary credentials
#290	- Memory: Fixed memory categorization by updating dependencies and correcting API usage
#291	- Gemini: Fixed Gemini Embeddings and LLM issues
#292
#293	</Update>
#294
#295	<Update label="2025-06-23" description="v0.1.111">
#296
#297	New Features:
#298	- OpenMemory:
#299	- Added OpenMemory augment support
#300	- Added OpenMemory Local Support using new library
#301	- vLLM: Added vLLM support integration
#302
#303	Improvements:
#304	- Documentation:
#305	- Added MCP Client Integration Guide and updated installation commands
#306	- Improved Agent Id documentation for Mem0 OSS Graph Memory
#307	- Core: Added JSON parsing to solve hallucination errors
#308
#309	Bug Fixes:
#310	- Gemini: Fixed Gemini Embeddings migration
#311
#312	</Update>
#313
#314	<Update label="2025-06-20" description="v0.1.110">
#315
#316	New Features:
#317	- Baidu: Added Baidu vector database integration
#318
#319	Improvements:
#320	- Documentation:
#321	- Updated changelog
#322	- Fixed example in quickstart page
#323	- Updated client.update() method documentation in OpenAPI specification
#324	- OpenSearch: Updated logger warning
#325
#326	Bug Fixes:
#327	- CI: Fixed failing CI pipeline
#328
#329	</Update>
#330
#331	<Update label="2025-06-19" description="v0.1.109">
#332
#333	New Features:
#334	- AgentOps: Added AgentOps integration
#335	- LM Studio: Added response_format parameter for LM Studio configuration
#336	- Examples: Added Memory agent powered by voice (Cartesia + Agno)
#337
#338	Improvements:
#339	- AI SDK: Added output_format parameter
#340	- Client: Enhanced update method to support metadata
#341	- Google: Added Google Genai library support
#342
#343	Bug Fixes:
#344	- Build: Fixed Build CI failure
#345	- Pinecone: Fixed pinecone for async memory
#346
#347	</Update>
#348
#349	<Update label="2025-06-14" description="v0.1.108">
#350
#351	New Features:
#352	- MongoDB: Added MongoDB Vector Store support
#353	- Client: Added client support for summary functionality
#354
#355	Improvements:
#356	- Pinecone: Fixed pinecone version issues
#357	- OpenSearch: Added logger support
#358	- Testing: Added python version test environments
#359
#360	</Update>
#361
#362	<Update label="2025-06-11" description="v0.1.107">
#363
#364	Improvements:
#365	- Documentation:
#366	- Updated Livekit documentation migration
#367	- Updated OpenMemory hosted version documentation
#368	- Core: Updated categorization flow
#369	- Storage: Fixed migration issues
#370
#371	</Update>
#372
#373	<Update label="2025-06-09" description="v0.1.106">
#374
#375	New Features:
#376	- Cloudflare: Added Cloudflare vector store support
#377	- Search: Added threshold parameter to search functionality
#378	- API: Added wildcard character support for v2 Memory APIs
#379
#380	Improvements:
#381	- Documentation: Updated README docs for OpenMemory environment setup
#382	- Core: Added support for unique user IDs
#383
#384	Bug Fixes:
#385	- Core: Fixed error handling exceptions
#386
#387	</Update>
#388
#389	<Update label="2025-06-03" description="v0.1.104">
#390
#391	Bug Fixes:
#392	- Vector Stores: Fixed GET_ALL functionality for FAISS and OpenSearch
#393
#394	</Update>
#395
#396	<Update label="2025-06-02" description="v0.1.103">
#397
#398	New Features:
#399	- LLM: Added support for OpenAI compatible LLM providers with baseUrl configuration
#400
#401	Improvements:
#402	- Documentation:
#403	- Fixed broken links
#404	- Improved Graph Memory features documentation clarity
#405	- Updated enable_graph documentation
#406	- TypeScript SDK: Updated Google SDK peer dependency version
#407	- Client: Added async mode parameter
#408
#409	</Update>
#410
#411	<Update label="2025-05-26" description="v0.1.102">
#412
#413	New Features:
#414	- Examples: Added Neo4j example
#415	- AI SDK: Added Google provider support
#416	- OpenMemory: Added LLM and Embedding Providers support
#417
#418	Improvements:
#419	- Documentation:
#420	- Updated memory export documentation
#421	- Enhanced role-based memory attribution rules documentation
#422	- Updated API reference and messages documentation
#423	- Added Mastra and Raycast documentation
#424	- Added NOT filter documentation for Search and GetAll V2
#425	- Announced Claude 4 support
#426	- Core:
#427	- Removed support for passing string as input in client.add()
#428	- Added support for sarvam-m model
#429	- TypeScript SDK: Fixed types from message interface
#430
#431	Bug Fixes:
#432	- Memory: Prevented saving prompt artifacts as memory when no new facts are present
#433	- OpenMemory: Fixed typos in MCP tool description
#434
#435	</Update>
#436
#437	<Update label="2025-05-15" description="v0.1.101">
#438
#439	New Features:
#440	- Neo4j: Added base label configuration support
#441
#442	Improvements:
#443	- Documentation:
#444	- Updated Healthcare example index
#445	- Enhanced collaborative task agent documentation clarity
#446	- Added criteria-based filtering documentation
#447	- OpenMemory: Added cURL command for easy installation
#448	- Build: Migrated to Hatch build system
#449
#450	</Update>
#451
#452	<Update label="2025-05-10" description="v0.1.100">
#453
#454	New Features:
#455	- Memory: Added Group Chat Memory Feature support
#456	- Examples: Added Healthcare assistant using Mem0 and Google ADK
#457
#458	Bug Fixes:
#459	- SSE: Fixed SSE connection issues
#460	- MCP: Fixed memories not appearing in MCP clients added from Dashboard
#461
#462	</Update>
#463
#464	<Update label="2025-05-07" description="v0.1.99">
#465
#466	New Features:
#467	- OpenMemory: Added OpenMemory support
#468	- Neo4j: Added weights to Neo4j model
#469	- AWS: Added support for Opsearch Serverless
#470	- Examples: Added ElizaOS Example
#471
#472	Improvements:
#473	- Documentation: Updated Azure AI documentation
#474	- AI SDK: Added missing parameters and updated demo application
#475	- OSS: Fixed AOSS and AWS BedRock LLM
#476
#477	</Update>
#478
#479	<Update label="2025-04-30" description="v0.1.98">
#480
#481	New Features:
#482	- Neo4j: Added support for Neo4j database
#483	- AWS: Added support for AWS Bedrock Embeddings
#484
#485	Improvements:
#486	- Client: Updated delete_users() to use V2 API endpoints
#487	- Documentation: Updated timestamp and dual-identity memory management docs
#488	- Neo4j: Improved Neo4j queries and removed warnings
#489	- AI SDK: Added support for graceful failure when services are down
#490
#491	Bug Fixes:
#492	- Fixed AI SDK filters
#493	- Fixed new memories wrong type
#494	- Fixed duplicated metadata issue while adding/updating memories
#495
#496	</Update>
#497
#498	<Update label="2025-04-23" description="v0.1.97">
#499
#500	New Features:
#501	- HuggingFace: Added support for HF Inference
#502
#503	Bug Fixes:
#504	- Fixed proxy for Mem0
#505
#506	</Update>
#507
#508	<Update label="2025-04-16" description="v0.1.96">
#509
#510	New Features:
#511	- Vercel AI SDK: Added Graph Memory support
#512
#513	Improvements:
#514	- Documentation: Fixed timestamp and README links
#515	- Client: Updated TS client to use proper types for deleteUsers
#516	- Dependencies: Removed unnecessary dependencies from base package
#517
#518	</Update>
#519
#520	<Update label="2025-04-09" description="v0.1.95">
#521
#522	Improvements:
#523	- Client: Fixed Ping Method for using default org_id and project_id
#524	- Documentation: Updated documentation
#525
#526	Bug Fixes:
#527	- Fixed mem0-migrations issue
#528
#529	</Update>
#530
#531	<Update label="2025-04-26" description="v0.1.94">
#532
#533	New Features:
#534	- Integrations: Added Memgraph integration
#535	- Memory: Added timestamp support
#536	- Vector Stores: Added reset function for VectorDBs
#537
#538	Improvements:
#539	- Documentation:
#540	- Updated timestamp and expiration_date documentation
#541	- Fixed v2 search documentation
#542	- Added "memory" in EC "Custom config" section
#543	- Fixed typos in the json config sample
#544
#545	</Update>
#546
#547	<Update label="2025-04-21" description="v0.1.93">
#548
#549	Improvements:
#550	- Vector Stores: Initialized embedding_model_dims in all vectordbs
#551
#552	Bug Fixes:
#553	- Documentation: Fixed agno link
#554
#555	</Update>
#556
#557	<Update label="2025-04-18" description="v0.1.92">
#558
#559	New Features:
#560	- Memory: Added Memory Reset functionality
#561	- Client: Added support for Custom Instructions
#562	- Examples: Added Fitness Checker powered by memory
#563
#564	Improvements:
#565	- Core: Updated capture_event
#566	- Documentation: Fixed curl for v2 get_all
#567
#568	Bug Fixes:
#569	- Vector Store: Fixed user_id functionality
#570	- Client: Various client improvements
#571
#572	</Update>
#573
#574	<Update label="2025-04-16" description="v0.1.91">
#575
#576	New Features:
#577	- LLM Integrations: Added Azure OpenAI Embedding Model
#578	- Examples:
#579	- Added movie recommendation using grok3
#580	- Added Voice Assistant using Elevenlabs
#581
#582	Improvements:
#583	- Documentation:
#584	- Added keywords AI
#585	- Reformatted navbar page URLs
#586	- Updated changelog
#587	- Updated openai.mdx
#588	- FAISS: Silenced FAISS info logs
#589
#590	</Update>
#591
#592	<Update label="2025-04-11" description="v0.1.90">
#593
#594	New Features:
#595	- LLM Integrations: Added Mistral AI as LLM provider
#596
#597	Improvements:
#598	- Documentation:
#599	- Updated changelog
#600	- Fixed memory exclusion example
#601	- Updated xAI documentation
#602	- Updated YouTube Chrome extension example documentation
#603
#604	Bug Fixes:
#605	- Core: Fixed EmbedderFactory.create() in GraphMemory
#606	- Azure OpenAI: Added patch to fix Azure OpenAI
#607	- Telemetry: Fixed telemetry issue
#608
#609	</Update>
#610
#611	<Update label="2025-04-11" description="v0.1.89">
#612
#613	New Features:
#614	- Langchain Integration: Added support for Langchain VectorStores
#615	- Examples:
#616	- Added personal assistant example
#617	- Added personal study buddy example
#618	- Added YouTube assistant Chrome extension example
#619	- Added agno example
#620	- Updated OpenAI Responses API examples
#621	- Vector Store: Added capability to store user_id in vector database
#622	- Async Memory: Added async support for OSS
#623
#624	Improvements:
#625	- Documentation: Updated formatting and examples
#626
#627	</Update>
#628
#629	<Update label="2025-04-09" description="v0.1.87">
#630
#631	New Features:
#632	- Upstash Vector: Added support for Upstash Vector store
#633
#634	Improvements:
#635	- Code Quality: Removed redundant code lines
#636	- Build: Updated MAKEFILE
#637	- Documentation: Updated memory export documentation
#638
#639	</Update>
#640
#641	<Update label="2025-04-07" description="v0.1.86">
#642
#643	Improvements:
#644	- FAISS: Added embedding_dims parameter to FAISS vector store
#645
#646	</Update>
#647
#648	<Update label="2025-04-07" description="v0.1.84">
#649
#650	New Features:
#651	- Langchain Embedder: Added Langchain embedder integration
#652
#653	Improvements:
#654	- Langchain LLM: Updated Langchain LLM integration to directly pass the Langchain object LLM
#655	</Update>
#656
#657	<Update label="2025-04-07" description="v0.1.83">
#658
#659	Bug Fixes:
#660	- Langchain LLM: Fixed issues with Langchain LLM integration
#661	</Update>
#662
#663	<Update label="2025-04-07" description="v0.1.82">
#664
#665	New Features:
#666	- LLM Integrations: Added support for Langchain LLMs, Google as new LLM and embedder
#667	- Development: Added development docker compose
#668
#669	Improvements:
#670	- Output Format: Set output_format='v1.1' and updated documentation
#671
#672	Documentation:
#673	- Integrations: Added LMStudio and Together.ai documentation
#674	- API Reference: Updated output_format documentation
#675	- Integrations: Added PipeCat integration documentation
#676	- Integrations: Added Flowise integration documentation for Mem0 memory setup
#677
#678	Bug Fixes:
#679	- Tests: Fixed failing unit tests
#680	</Update>
#681
#682	<Update label="2025-04-02" description="v0.1.79">
#683
#684	New Features:
#685	- FAISS Support: Added FAISS vector store support
#686
#687	</Update>
#688
#689	<Update label="2025-04-02" description="v0.1.78">
#690
#691	New Features:
#692	- Livekit Integration: Added Mem0 livekit example
#693	- Evaluation: Added evaluation framework and tools
#694
#695	Documentation:
#696	- Multimodal: Updated multimodal documentation
#697	- Examples: Added examples for email processing
#698	- API Reference: Updated API reference section
#699	- Elevenlabs: Added Elevenlabs integration example
#700
#701	Bug Fixes:
#702	- OpenAI Environment Variables: Fixed issues with OpenAI environment variables
#703	- Deployment Errors: Added `package.json` file to fix deployment errors
#704	- Tools: Fixed tools issues and improved formatting
#705	- Docs: Updated API reference section for `expiration date`
#706	</Update>
#707
#708	<Update label="2025-03-26" description="v0.1.77">
#709
#710	Bug Fixes:
#711	- OpenAI Environment Variables: Fixed issues with OpenAI environment variables
#712	- Deployment Errors: Added `package.json` file to fix deployment errors
#713	- Tools: Fixed tools issues and improved formatting
#714	- Docs: Updated API reference section for `expiration date`
#715	</Update>
#716
#717	<Update label="2025-03-19" description="v0.1.76">
#718	New Features:
#719	- Supabase Vector Store: Added support for Supabase Vector Store
#720	- Supabase History DB: Added Supabase History DB to run Mem0 OSS on Serverless
#721	- Feedback Method: Added feedback method to client
#722
#723	Bug Fixes:
#724	- Azure OpenAI: Fixed issues with Azure OpenAI
#725	- Azure AI Search: Fixed test cases for Azure AI Search
#726	</Update>
#727
#728	</Tab>
#729
#730	<Tab title="TypeScript">
#731
#732	<Update label="2026-03-09" description="v2.3.0">
#733
#734	Breaking Changes:
#735	- Dependencies: Minimum Node.js version for OSS sqlite features is now Node 20+ (due to `better-sqlite3` v12)
#736
#737	Bug Fixes:
#738	- OSS Storage: Replaced `sqlite3` with `better-sqlite3` to fix native binding resolution failures under jiti-based loaders (e.g. OpenClaw plugin system). Fixes issues where the `bindings` module walked V8 stack frames with synthetic filenames, failing to locate the native `.node` addon.
#739	- OSS Storage: Fixed async init race condition in `SQLiteManager` — `init()` is now synchronous
#740	- OSS Vector Store: Migrated `MemoryVectorStore` from `sqlite3` to `better-sqlite3` with transactional batch inserts
#741
#742	Improvements:
#743	- Performance: Cached prepared statements in `SQLiteManager` for faster history operations
#744	- Performance: Batch `insert()` in `MemoryVectorStore` wrapped in a transaction for atomicity
#745	- Build: Updated `tsup.config.ts` externals from `sqlite3` to `better-sqlite3`
#746
#747	</Update>
#748
#749	<Update label="2026-02-17" description="v2.2.3">
#750
#751	New Features & Updates:
#752	- Memory Update:
#753	- Added `timestamp` parameter to `update()` — accepts Unix epoch or ISO 8601 string
#754
#755	</Update>
#756
#757	<Update label="2026-01-29" description="v2.2.2">
#758
#759	New Features & Updates:
#760	- Project Settings:
#761	- Added inclusion prompt, exclusion prompt, memory depth, and usecase setting
#762
#763	</Update>
#764
#765	<Update label="2025-12-30" description="v2.2.1">
#766
#767	Improvements:
#768	- Client: Added support for keyword arguments in `add` and `search` methods, allowing additional properties beyond defined options for experimental features
#769
#770	</Update>
#771
#772	<Update label="2025-12-29" description="v2.2.0">
#773
#774	New Features:
#775	- Vector Stores: Added Azure AI Search vector store support
#776
#777	Improvements:
#778	- Config: Fixed embedder config schema to support `embeddingDims` and `url` parameters
#779	- Graph Memory: Replaced hardcoded LLM provider with provider from configuration
#780
#781	Bug Fixes:
#782	- Embedders: Fixed hardcoded `embeddingDims` values in embedders (OpenAI, Ollama, Google, Azure)
#783	- Build: Fixed TypeScript build errors
#784
#785	</Update>
#786
#787	<Update label="2025-09-04" description="v2.1.38">
#788	New Features:
#789	- Client: Added `metadata` param to `update` method.
#790	</Update>
#791
#792	<Update label="2025-08-04" description="v2.1.37">
#793	New Features:
#794	- OSS: Added `RedisCloud` search module check
#795	</Update>
#796
#797	<Update label="2025-07-08" description="v2.1.36">
#798	New Features:
#799	- Client: Added `structured_data_schema` param to `add` method.
#800	</Update>
#801
#802	<Update label="2025-07-08" description="v2.1.35">
#803	New Features:
#804	- Client: Added `createMemoryExport` and `getMemoryExport` methods.
#805	</Update>
#806
#807	<Update label="2025-07-03" description="v2.1.34">
#808	New Features:
#809	- OSS: Added Gemini support
#810	</Update>
#811
#812	<Update label="2025-06-24" description="v2.1.33">
#813	Improvement:
#814	- Client: Added `immutable` param to `add` method.
#815	</Update>
#816
#817	<Update label="2025-06-20" description="v2.1.32">
#818	Improvement:
#819	- Client: Made `api_version` V2 as default.
#820	</Update>
#821
#822	<Update label="2025-06-17" description="v2.1.31">
#823	Improvement:
#824	- Client: Added param `filter_memories`.
#825	</Update>
#826
#827	<Update label="2025-06-06" description="v2.1.30">
#828	New Features:
#829	- OSS: Added Cloudflare support
#830
#831	Improvements:
#832	- OSS: Fixed baseURL param in LLM Config.
#833	</Update>
#834
#835	<Update label="2025-05-30" description="v2.1.29">
#836	Improvements:
#837	- Client: Added Async Mode Param for `add` method.
#838	</Update>
#839
#840	<Update label="2025-05-30" description="v2.1.28">
#841	Improvements:
#842	- SDK: Update Google SDK Peer Dependency Version.
#843	</Update>
#844
#845	<Update label="2025-05-27" description="v2.1.27">
#846	Improvements:
#847	- OSS: Added baseURL param in LLM Config.
#848	</Update>
#849	<Update label="2025-05-23" description="v2.1.26">
#850	Improvements:
#851	- Client: Removed type `string` from `messages` interface
#852	</Update>
#853
#854	<Update label="2025-05-08" description="v2.1.25">
#855	Improvements:
#856	- Client: Improved error handling in client.
#857	</Update>
#858
#859	<Update label="2025-05-06" description="v2.1.24">
#860	New Features:
#861	- Client: Added new param `output_format` to match Python SDK.
#862	- Client: Added new enum `OutputFormat` for `v1.0` and `v1.1`
#863	</Update>
#864
#865	<Update label="2025-05-05" description="v2.1.23">
#866	New Features:
#867	- Client: Updated `deleteUsers` to use `v2` API.
#868	- Client: Deprecated `deleteUser` and added deprecation warning.
#869	</Update>
#870
#871	<Update label="2025-05-02" description="v2.1.22">
#872	New Features:
#873	- Client: Updated `deleteUser` to use `entity_id` and `entity_type`
#874	</Update>
#875
#876	<Update label="2025-05-01" description="v2.1.21">
#877	Improvements:
#878	- OSS SDK: Bumped version of `@anthropic-ai/sdk` to `0.40.1`
#879	</Update>
#880
#881	<Update label="2025-04-28" description="v2.1.20">
#882	Improvements:
#883	- Client: Fixed `organizationId` and `projectId` being assigned to default in `ping` method
#884	</Update>
#885
#886	<Update label="2025-04-22" description="v2.1.19">
#887	Improvements:
#888	- Client: Added support for `timestamps`
#889	</Update>
#890
#891	<Update label="2025-04-17" description="v2.1.18">
#892	Improvements:
#893	- Client: Added support for custom instructions
#894	</Update>
#895
#896	<Update label="2025-04-15" description="v2.1.17">
#897	New Features:
#898	- OSS SDK: Added support for Langchain LLM
#899	- OSS SDK: Added support for Langchain Embedder
#900	- OSS SDK: Added support for Langchain Vector Store
#901	- OSS SDK: Added support for Azure OpenAI Embedder
#902
#903
#904	Improvements:
#905	- OSS SDK: Changed `model` in LLM and Embedder to use type any from `string` to use langchain llm models
#906	- OSS SDK: Added client to vector store config for langchain vector store
#907	- OSS SDK: - Updated Azure OpenAI to use new OpenAI SDK
#908	</Update>
#909
#910	<Update label="2025-04-11" description="v2.1.16-patch.1">
#911	Bug Fixes:
#912	- Azure OpenAI: Fixed issues with Azure OpenAI
#913	</Update>
#914
#915	<Update label="2025-04-11" description="v2.1.16">
#916	New Features:
#917	- Azure OpenAI: Added support for Azure OpenAI
#918	- Mistral LLM: Added Mistral LLM integration in OSS
#919
#920	Improvements:
#921	- Zod: Updated Zod to 3.24.1 to avoid conflicts with other packages
#922	</Update>
#923
#924	<Update label="2025-04-09" description="v2.1.15">
#925	Improvements:
#926	- Client: Added support for Mem0 to work with Chrome Extensions
#927	</Update>
#928
#929	<Update label="2025-04-01" description="v2.1.14">
#930	New Features:
#931	- Mastra Example: Added Mastra example
#932	- Integrations: Added Flowise integration documentation for Mem0 memory setup
#933
#934	Improvements:
#935	- Demo: Updated Demo Mem0AI
#936	- Client: Enhanced Ping method in Mem0 Client
#937	- AI SDK: Updated AI SDK implementation
#938	</Update>
#939
#940	<Update label="2025-03-29" description="v2.1.13">
#941	Improvements:
#942	- Introduced `ping` method to check if API key is valid and populate org/project id
#943	</Update>
#944
#945	<Update label="2025-03-29" description="AI SDK v1.0.0">
#946	New Features:
#947	- Vercel AI SDK Update: Support threshold and rerank
#948
#949	Improvements:
#950	- Made add calls async to avoid blocking
#951	- Bump `mem0ai` to use `2.1.12`
#952
#953	</Update>
#954
#955	<Update label="2025-03-26" description="v2.1.12">
#956	New Features:
#957	- Mem0 OSS: Support infer param
#958
#959	Improvements:
#960	- Updated Supabase TS Docs
#961	- Made package size smaller
#962
#963	</Update>
#964
#965	<Update label="2025-03-19" description="v2.1.11">
#966	New Features:
#967	- Supabase Vector Store Integration
#968	- Feedback Method
#969	</Update>
#970
#971	</Tab>
#972
#973	<Tab title="Platform">
#974
#975	<Update label="2025-07-23" description="">
#976
#977	Bug Fixes:
#978	- Memory: Fixed ADD functionality
#979
#980	</Update>
#981
#982	<Update label="2025-07-19" description="">
#983
#984	New Features:
#985	- UI: Added Settings UI and latency display
#986	- Performance: Neo4j query optimization
#987
#988	Bug Fixes:
#989	- OpenMemory: Fixed OMM raising unnecessary exceptions
#990
#991	</Update>
#992
#993	<Update label="2025-07-18" description="">
#994
#995	Improvements:
#996	- UI: Updated Event UI
#997	- Performance: Fixed N+1 query issue in semantic_search_v2 by optimizing MemorySerializer field selection
#998
#999	Bug Fixes:
#1000	- Memory: Fixed duplicate memory index sentry error
#1001
#1002	</Update>
#1003
#1004	<Update label="2025-07-17" description="">
#1005
#1006	New Features:
#1007	- UI: New Settings Page
#1008	- Memory: Duplicate memories entities support
#1009
#1010	Improvements:
#1011	- Performance: Optimized semantic search and get_all APIs by eliminating N+1 queries
#1012
#1013	</Update>
#1014
#1015	<Update label="2025-07-16" description="">
#1016
#1017	New Features:
#1018	- Database: Implemented read replica routing with enhanced logging and app-specific DB routing
#1019
#1020	Improvements:
#1021	- Performance: Improved query performance in search v2 and get all v2 endpoints
#1022
#1023	Bug Fixes:
#1024	- API: Fixed pagination for get all API
#1025
#1026	</Update>
#1027
#1028	<Update label="2025-07-12" description="">
#1029
#1030	Bug Fixes:
#1031	- Graph: Fixed social graph bugs and connection issues
#1032
#1033	</Update>
#1034
#1035	<Update label="2025-07-11" description="">
#1036
#1037	Improvements:
#1038	- Rate Limiting: New rate limit for V2 Search
#1039
#1040	Bug Fixes:
#1041	- Slack: Fixed Slack rate limit error with backend improvements
#1042
#1043	</Update>
#1044
#1045	<Update label="2025-07-10" description="">
#1046
#1047	Improvements:
#1048	- Performance:
#1049	- Changed connection pooling time to 5 minutes
#1050	- Separated graph lambdas for better performance
#1051
#1052	</Update>
#1053
#1054	<Update label="2025-07-09" description="">
#1055
#1056	Improvements:
#1057	- Graph: Graph Optimizations V2 and memory improvements
#1058
#1059	</Update>
#1060
#1061	<Update label="2025-07-08" description="">
#1062
#1063	New Features:
#1064	- Database: Added read replica support for improved database performance
#1065	- UI: Implemented UI changes for Users Page
#1066	- Feedback: Enabled feedback functionality
#1067
#1068	Bug Fixes:
#1069	- Serializer: Fixed GET ALL Serializer
#1070
#1071	</Update>
#1072
#1073	<Update label="2025-07-05" description="">
#1074
#1075	New Features:
#1076	- UI: User Page Revamp and New Users Page
#1077
#1078	</Update>
#1079
#1080	<Update label="2025-07-04" description="">
#1081
#1082	New Features:
#1083	- Users: New Users Page implementation
#1084	- Tools: Added script to backfill memory categories
#1085
#1086	Bug Fixes:
#1087	- Filters: Fixed Filters Get All functionality
#1088
#1089	</Update>
#1090
#1091	<Update label="2025-07-03" description="">
#1092
#1093	Improvements:
#1094	- Graph: Graph Memory optimization
#1095	- Memory: Fixed exact memories and semantically similar memories retrieval
#1096
#1097	</Update>
#1098
#1099	<Update label="2025-07-02" description="">
#1100
#1101	Improvements:
#1102	- Categorization: Refactored categorization logic to utilize Gemini 2.5 Flash and improve message handling
#1103
#1104	</Update>
#1105
#1106	<Update label="2025-07-01" description="">
#1107
#1108	Bug Fixes:
#1109	- Memory: Fixed old_memory issue in Async memory addition lambda
#1110	- Events: Fixed missing events
#1111
#1112	</Update>
#1113
#1114	<Update label="2025-06-30" description="">
#1115
#1116	Improvements:
#1117	- Graph: Improvements to graph memory and added user to LTM-STM
#1118
#1119	</Update>
#1120
#1121	<Update label="2025-06-28" description="">
#1122
#1123	New Features:
#1124	- Graph: Added support for SQS in graph memory addition
#1125	- Testing: Added Locust load testing script and Grafana Dashboard
#1126
#1127	</Update>
#1128
#1129	<Update label="2025-06-27" description="">
#1130
#1131	Improvements:
#1132	- Rate Limiting: Updated rate limiting for ADD API to 1000/min
#1133	- Performance: Improved Neo4j performance
#1134
#1135	</Update>
#1136
#1137	<Update label="2025-06-26" description="">
#1138
#1139	New Features:
#1140	- Memory: Edit Memory From Drawer functionality
#1141	- API: Added Topic Suggestions API Endpoint
#1142
#1143	</Update>
#1144
#1145	<Update label="2025-06-25" description="">
#1146
#1147	New Features:
#1148	- Group Chat: Group-Chat v2 with Actor-Aware Memories
#1149	- Memory: Editable Metadata in Memories
#1150	- UI: Memory Actions Badges
#1151
#1152	</Update>
#1153
#1154	<Update label="2025-06-19" description="">
#1155
#1156	New Features:
#1157	- Rate Limiting: Implemented comprehensive rate limiting system
#1158
#1159	Improvements:
#1160	- Performance: Added performance indexes for memory stats query
#1161
#1162	Bug Fixes:
#1163	- Search: Fixed search events not respecting top-k parameter
#1164
#1165	</Update>
#1166
#1167	<Update label="2025-06-18" description="">
#1168
#1169	New Features:
#1170	- Memory Management: Implemented OpenAI Batch API for Memory Cleaning with fallback
#1171	- Playground: Added Claude 4 support on Playground
#1172
#1173	Improvements:
#1174	- Memory: Added ability to update memory metadata
#1175
#1176	</Update>
#1177
#1178	<Update label="2025-06-17" description="">
#1179
#1180	New Features:
#1181	- UI: New Memories Page UI design
#1182
#1183	</Update>
#1184
#1185	<Update label="2025-06-16" description="">
#1186
#1187	Improvements:
#1188	- Infrastructure: Migrated to Application Load Balancer (ALB)
#1189
#1190	</Update>
#1191
#1192	<Update label="2025-06-13" description="">
#1193
#1194	Improvements:
#1195	- Memory Management: Enhanced Memory Management with Cosine Similarity Fallback
#1196
#1197	</Update>
#1198
#1199	<Update label="2025-06-11" description="">
#1200
#1201	New Features:
#1202	- OMM: Added OMM Script and UI functionality
#1203
#1204	Improvements:
#1205	- API: Added filters validation to semantic_search_v2 endpoint
#1206
#1207	</Update>
#1208
#1209	<Update label="2025-06-09" description="">
#1210
#1211	New Features:
#1212	- Intercom: Set Intercom events for ADD and SEARCH operations
#1213	- OpenMemory: Added Posthog integration and feedback functionality
#1214	- MCP: New JavaScript MCP Server with feedback support
#1215
#1216	Improvements:
#1217	- Structured Data: Enhanced structured data handling in memory management
#1218
#1219	</Update>
#1220
#1221	<Update label="2025-06-06" description="">
#1222
#1223	New Features:
#1224	- OAuth: Added Mem0 OAuth integration
#1225	- OMM: Added OMM-Mem0 sync for deleted memories
#1226
#1227	</Update>
#1228
#1229	<Update label="2025-06-05" description="">
#1230
#1231	New Features:
#1232	- Filters: Implemented Wildcard Filters and refactored filter logic in V2 Views
#1233
#1234	</Update>
#1235
#1236	<Update label="2025-06-02" description="">
#1237
#1238	New Features:
#1239	- OpenMemory Cloud: Added OpenMemory Cloud support
#1240	- Structured Data: Added 'structured_attributes' field to Memory model
#1241
#1242	</Update>
#1243
#1244	<Update label="2025-05-30" description="">
#1245
#1246	New Features:
#1247	- Projects: Added version and enable_graph to project views
#1248	- OpenMemory: Added Postgres support for OpenMemory
#1249
#1250	</Update>
#1251
#1252	<Update label="2025-05-19" description="">
#1253
#1254	Bug Fixes:
#1255	- Core: Fixed unicode error in user_id, agent_id, run_id and app_id
#1256
#1257	</Update>
#1258
#1259	</Tab>
#1260
#1261	<Tab title="Vercel AI SDK">
#1262
#1263	<Update label="2025-12-26" description="v2.0.5">
#1264	Bug Fix:
#1265	- Vercel AI SDK: Removed unnecessary dependencies to make the package lighter.
#1266	</Update>
#1267
#1268	<Update label="2025-09-25" description="v2.0.4">
#1269	Bug Fix:
#1270	- Vercel AI SDK: Fixed version parameter in the AI SDK to use V2 for addition.
#1271	</Update>
#1272
#1273	<Update label="2025-09-25" description="v2.0.3">
#1274	New Features:
#1275	- Vercel AI SDK: Added file support for multimodal capabilities with memory context
#1276	</Update>
#1277
#1278	<Update label="2025-09-03" description="v2.0.2">
#1279	Bug Fix:
#1280	- Vercel AI SDK: Fixed streaming response in the AI SDK.
#1281	</Update>
#1282
#1283	<Update label="2025-08-05" description="v2.0.1">
#1284	New Features:
#1285	- Vercel AI SDK: Added a new param `host` to the config.
#1286	</Update>
#1287
#1288	<Update label="2025-08-05" description="v2.0.0">
#1289	New Features:
#1290	- Vercel AI SDK: Migration to AI SDK V5.
#1291	</Update>
#1292
#1293	<Update label="2025-06-15" description="v1.0.6">
#1294	New Features:
#1295	- Vercel AI SDK: Added param `filter_memories`.
#1296	</Update>
#1297
#1298	<Update label="2025-05-23" description="v1.0.5">
#1299	New Features:
#1300	- Vercel AI SDK: Added support for Google provider.
#1301	</Update>
#1302
#1303	<Update label="2025-05-10" description="v1.0.4">
#1304	New Features:
#1305	- Vercel AI SDK: Added support for new param `output_format`.
#1306	</Update>
#1307
#1308	<Update label="2025-05-08" description="v1.0.3">
#1309	Improvements:
#1310	- Vercel AI SDK: Added support for graceful failure in cases services are down.
#1311	</Update>
#1312
#1313	<Update label="2025-05-01" description="v1.0.1">
#1314	New Features:
#1315	- Vercel AI SDK: Added support for graph memories
#1316	</Update>
#1317
#1318	</Tab>
#1319
#1320	</Tabs>
#1321
#1322

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public