TypeScript OSS SDK: 26 New Providers, Reranking, and Zero-Dependency ImportsTypeScript SDK v3.1.0 is the largest provider release for the OSS SDK so far, closing most of the remaining gap with the Python SDK. Python SDK v2.0.12 ships alongside it with fixes and security patches.
- 17 new vector stores: Pinecone, Weaviate, Milvus, Chroma, MongoDB, Elasticsearch, OpenSearch, Databricks, AWS Neptune Analytics, S3 Vectors, Azure MySQL, Google Vertex AI Vector Search, Turbopuffer, Upstash Vector, Valkey, Cassandra, and Baidu Mochow.
- 5 new LLM providers: AWS Bedrock, xAI Grok, Together, vLLM, and Sarvam.
- 4 new embedding providers: Vertex AI, HuggingFace, FastEmbed, and Together.
- Reranking in TypeScript: Four rerankers (Cohere, ZeroEntropy, cross-encoder, and LLM-based) with per-search rerank via a
rerankoption onsearch(). - Install only what you use: Importing
mem0ai/ossno longer pulls in any provider SDK. Provider packages are resolved lazily on first use, so an app that configures only OpenAI and Qdrant does not need the other provider SDKs installed.
SDK Memory Expiration: Expiring Memories Across Python and TypeScriptThe latest SDK releases add first-class expiration controls to memory writes, updates, and reads, plus new TypeScript provider coverage for production deployments.
- Python client updates:
MemoryClient.update()andAsyncMemoryClient.update()now acceptexpiration_date, includingNoneto clear an existing expiration. - TypeScript client updates:
AddMemoryOptions,update(), andMemorynow supportexpirationDate;search()andgetAll()can include expired memories withshowExpired. - New TypeScript LLM providers:
MiniMaxLLMandLiteLLMare now available for OpenAI-compatible MiniMax and LiteLLM proxy deployments. - PGVector deployment flexibility: TypeScript PGVector config now supports
connectionStringandssl, so apps can use a managed Postgres URI instead of separate connection fields.
Mem0 Plugin: Shared Memory for Claude Code, Cursor, Codex, and AntigravityThe shared Mem0 editor plugin is current through v0.2.11:
- Automatic context injection: File reads, bash errors, session resume prompts, and startup timelines can retrieve relevant memories automatically.
- Project and global scopes: Project-scoped memories remain the default, while
global_searchsupports team-wide recall across users and app scopes. - Coding categories: A 17-category coding taxonomy installs in the background and is cached per Mem0 account.
- Reliable capture: Auto-capture, compaction summaries, session summaries, and metadata defaults keep memories scoped and readable.
- Editor correctness: Telemetry now reports Claude Code, Cursor, Codex, and Antigravity separately with each editor’s real plugin version.
Antigravity Plugin: Mem0 for Google AntigravityAntigravity support in the shared Mem0 editor plugin family is current through v0.1.3:
- Self-contained plugin: Includes its own plugin manifest, MCP config, hooks, shared scripts, and skills.
- AGENTS.md convention: Uses Antigravity’s
contextFileName: "AGENTS.md"convention. - Lifecycle hooks: Wires session start, prompt recall, file-read context, memory-tool metadata enforcement, bash-error lookup, post-tool tracking, and stop summaries.
- Shared memory layer: Reuses the Mem0 Platform MCP tools and the shared 16-skill command bundle.
- Better automatic recall: v0.1.3 adds reranked injected context and clean
files_touchedmetadata in session summaries. - Telemetry correctness: v0.1.2 reports Antigravity as
antigravitywith the plugin’s own version.
OpenCode Plugin: Native SDK Memory Tools for OpenCode
@mem0/opencode-plugin adds memory to OpenCode and is current through v0.2.0:- Native SDK tools: Memory tools register through
@opencode-ai/pluginand call themem0aiSDK directly, so the plugin no longer depends onmcp.mem0.ai. - Memory scopes: Operations support
project,session, andglobalscope, with/mem0-scopeto change the default. - Automatic context: File-context injection, structured compaction summaries, and a recent-activity timeline surface relevant memories without manual recall.
- Auto-dream consolidation: Gated consolidation merges duplicates, drops stale or sensitive entries, and rewrites vague memories.
- Skills load in place: The
confighook adds bundled skills toskills.pathsinstead of copying them into user config directories. - Safety controls: Blocks
MEMORY.mdwrites and redacts secrets before storing memories.
Pi Agent Plugin: Persistent Memory for Pi Agent
@mem0/pi-agent-plugin adds semantic memory to Pi Agent and has been updated through v0.1.2:- Agent memory tool: Registers
mem0_memoryfor scoped search, add, get, delete, and delete-all operations. - Slash commands: Adds
/mem0-remember,/mem0-search,/mem0-forget,/mem0-tour,/mem0-dream,/mem0-pin,/mem0-scope, and/mem0-status. - Auto-capture: Stores user and assistant memories after agent turns.
- Dream consolidation: Merges duplicates, resolves contradictions, and prunes stale memories behind session, time, and memory-count gates.
- Project scoping: Uses git-root detection for stable
app_idvalues across monorepos. - Relevant command results: v0.1.2 adds visible command feedback and thresholded, reranked search for search, forget, and pin commands.
OpenClaw Plugin: Current Memory Backend for OpenClaw
@mem0/openclaw-mem0 is current through v1.0.13, with the original production-ready memory backend plus newer setup, security, and runtime work:- Skills-based memory architecture: Triage, recall, and dream skills handle extraction, recall, consolidation, and tool guidance.
- Chat and CLI setup: Supports chat-based platform setup,
openclaw mem0 init, direct API keys, email OTP, autonomous agent setup, and OSS onboarding. - Platform and OSS modes: Works with Mem0 Platform or self-hosted OSS providers including OpenAI, Anthropic, Ollama, Qdrant, and PGVector.
- Agent-friendly CLI: All 16 CLI commands support
--jsonfor machine-driven setup and diagnostics. - Runtime integration: Exposes OpenClaw memory capability APIs for search manager and backend config status.
- Security and compliance: Added path containment checks, sensitive config metadata, dependency overrides, telemetry hashing, and metadata-only registration safety.
Vercel AI SDK Provider: Memory-Augmented Generation for AI SDK v6The Vercel AI SDK provider moved to the v6 provider contract and Mem0 v3 APIs:
- AI SDK v6 support: Migrated to
LanguageModelV3/ProviderV3, including v3 stream lifecycle events and content arrays. - Mem0 v3 API support: Memory writes and searches now use
/v3/memories/add/and/v3/memories/search/. - Mem0 sources in responses:
generateTextandstreamTextresponses include memories as sources withproviderMetadata.mem0.memories. - Safer prompt handling: Prompts are cloned before memory injection, avoiding caller-side mutation.
- Async storage fix:
addMemoriesis awaited so generated memories are not silently dropped. - Raw memory utilities: Exports
searchMemories,retrieveMemories,getMemories, andaddMemoriesfor apps that need direct memory control. - Deployment controls: Per-request
mem0ApiKeyandhostsupport Mem0 Platform, custom API keys, and self-hosted API endpoints.
Temporal Reasoning: Time-Aware Retrieval for Platform v3Mem0 Platform v3 can now interpret time-aware memories and queries so assistants retrieve the right information for questions about the past, upcoming plans, and current state.
- Search intent parsing: Queries like
last week,upcoming,right now, andas of March 2025now resolve against memory timestamps automatically. - Default v3 behavior: No per-request toggle is needed for v3 writes or searches.
- Deterministic testing: Pass
reference_dateto anchor relative phrases in tests, backfills, and demos. - Stable API shape: Temporal reasoning changes ranking, not the client response contract.
Memory Decay: Recently-Used Memories Surface HigherPer-project search-time ranking bias that boosts recently-touched memories and gently dampens stale ones. Off by default; opt in per project via the
decay field on the project endpoint, or via client.project.update(decay=True) in the SDKs (Python v2.0.2 / TypeScript v3.0.3).- Soft bias, never a filter. The scaling factor stays in
0.3×–1.5×. Decay can reorder candidates but never removes them; anything that surfaced before decay can still surface after. - Reinforcement loop. Every memory returned in a search has its access history updated, so frequently-used facts naturally float to the top over time.
- Public score still clamped to
[0, 1]. Existing API contract preserved; no client-side changes needed. - v3 search only, fully reversible. See Memory Decay docs.
New Memory Algorithm: State-of-the-Art Accuracy at ~3-4x Lower CostGround-up rewrite of the memory pipeline with 20+ point benchmark improvements:
- LoCoMo: 71.4 → 91.6 (+20) for multi-turn conversation recall.
- LongMemEval: 67.8 → 93.4 (+26) for long-term memory across sessions.
- BEAM (1M tokens): 64.1 on production-scale memory evaluation.
- Agent memories: Assistant recall moves from 46% to 100%.
- Temporal reasoning: “Where did I live before SF?” improves from 51% to 93%.
- Lower token use: Retrieval stays under 7K tokens versus 25K+ for full-context approaches.
- ADD-only extraction: Memories accumulate; nothing is overwritten or deleted.
- Hybrid retrieval: Semantic search, BM25 keyword search, and entity boost are scored in parallel.
- Graph memory (built-in): entities extracted, embedded, and linked across memories, with no external graph store required
search() defaults changed, deprecated params removed. See migration guide.Mem0 Skill Graph: In-Context Documentation for AI AgentsAI coding agents in Claude Code, Cursor, and Codex can now access Mem0 knowledge directly in their workflow without leaving the editor. Three interconnected skills launched:
- mem0 Core Skill: Python and TypeScript SDK reference, REST API patterns, and integration guides for LangChain, CrewAI, Autogen, and more.
- mem0-cli Skill: Terminal command reference, configuration walkthroughs, and CI/CD recipes.
- mem0-vercel-ai-sdk Skill: Vercel AI SDK provider API, memory-augmented generation patterns, and multi-provider setup.
Official Mem0 CLI: Now on PyPI and npmA full-featured command-line interface for Mem0, available in both Python and Node.js:
- Install:
pip install mem0-cliornpm install -g @mem0/cli - Full command suite:
add,search,list,get,update,delete,import,config,init,status,entity,event. - Interactive setup:
mem0 initsupports email verification and direct API key entry. - Runtime coverage: Works with Mem0 Platform and self-hosted OSS modes.
- Automation support: Use
--jsonfor CI/CD pipelines and agent workflows. - Dual implementation: Same commands and behavior across Python and Node.js.
Apache AGE, Turbopuffer, MiniMax, and pgvector for Node.jsMajor expansion of the provider ecosystem:
- Apache AGE: New graph store support, bringing the total to 4 graph store backends (Neo4j, Memgraph, Kuzu, Apache AGE). Note: All external graph store backends (Neo4j, Memgraph, Kuzu, Apache AGE) were subsequently removed in v2.0.0 (2026-04-14). Graph memory is now built-in entity linking with no external graph store required; see the v2.0.0 entry above.
- Turbopuffer: New vector database provider for Python SDK.
- MiniMax: New LLM provider with dedicated AWS Bedrock support.
- pgvector for Node.js: PostgreSQL vector support added to the TypeScript OSS SDK.
- Reasoning models:
reasoning_effortparameter for OpenAI o1/o3-style models.