pingcap/tidbTiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
Go★ 40.5K2026年9月16日
topoteretes/cogneeCognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Python · TypeScript★ 30.7K↓ 126.6K/月2026年9月16日
PyPI · crates.io · npm97卓越健康指数
volcengine/OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python · Rust★ 37.7K↓ 376K/月2026年9月16日
TypeScript★ 357↓ 272.5K/月2026年9月9日
Python★ 7,208↓ 2,744/月2026年9月17日
EverMind-AI/EverOSOne portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Python★ 13.4K↓ 20.4K/月2026年10月14日
doobidoo/mcp-memory-serviceOpen-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
Python · HTML · JavaScript★ 2,016↓ 8,649/月2026年10月15日
letta-ai/letta-codeStateful agents that are like people, with memory, identity, and the ability to learn and adapt
TypeScript★ 3,261↓ 284.9K/月2026年9月10日
PyPI · npm · crates.io92优秀健康指数
infino-ai/infinoEmbedded retrieval library built on Parquet. Fast, efficient, and scalable.
Rust★ 81↓ 8,183/月2026年9月18日
Python · HTML★ 1,859↓ 4,158/月2026年9月5日
Lyellr88/marm-memoryLocal-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.
Python · TypeScript★ 402↓ 2,902/月2026年9月24日
npm · PyPI · crates.io91优秀健康指数
MemoriLabs/MemoriMemori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
Python · TypeScript · Rust★ 16.8K↓ 250/月2026年9月17日
zilliztech/memsearchA persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Python · JavaScript · Shell★ 2,5842026年9月10日
Python★ 155↓ 2,902/月2026年8月25日
AISquare-Studio/aisquare-cliPortable memory layer for coding agents — persistent user & project context across sessions, installed into Claude Code.
Python★ 5↓ 4,969/月2026年10月19日
Smart-AI-Memory/attune-aiPersistent memory and receipt-verified workflows for Claude Code — plugin, MCP server, and spec-driven dev framework in one pip install.
HTML · Python★ 10↓ 4,371/月2026年9月15日
TypeScript★ 743↓ 6,837/月2026年9月5日
Go · Shell★ 24.4K2026年9月16日
raphaelmansuy/edgequakeEdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation
Rust · TypeScript★ 2,092↓ 28/月2026年9月13日
supermemoryai/supermemoryMemory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
TypeScript · MDX · Python★ 29.7K↓ 128K/月2026年9月16日
npm · PyPI · RubyGems87优秀健康指数
TypeScript · Python★ 1,299↓ 3,994/月2026年9月5日
npm · crates.io · PyPI87优秀健康指数
cyberlife-coder/VelesDBThe explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.
Rust · Python★ 91↓ 4,233/月2026年9月5日
jagoff/memoYour coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.
Python★ 18↓ 4,408/月2026年9月12日
TypeScript★ 270↓ 1,412/月2026年9月12日
klarlabs-studio/mnemosSelf-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.
Go★ 42026年9月9日
sageox/oxThe hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
Go★ 552026年9月14日
PyPI · npm · crates.io86优秀健康指数
juyterman1000/entrolyCut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
Python · Rust★ 443↓ 9,156/月2026年9月12日
Python★ 5↓ 856/月2026年10月20日
Python★ 224↓ 12.4K/月2026年9月11日
remete618/widemem-aiLocal-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware retrieval.
Python★ 49↓ 4,603/月2026年10月21日