Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
AI Coders search blindly. Be their guide.
PythonMIT★ 40No key
Long-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.
Node.jsMIT★ 9No key
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /compact + hook-based capture (claude-mem, etc.).
PythonMIT★ 5No key
Persistent semantic memory for AI agents on Raspberry Pi 5 — local Qdrant + MCP, no cloud, ~3s per query
SkillMIT★ 15No key
Persistent memory for agents. Agents learn from failures. Deja remembers.
Node.jsMIT★ 7No key
BrainRouter is a cognitive memory and multi-agent orchestration platform for AI coding agents. It provides a first-party terminal CLI, MCP-based memory tools, layered recall, context compaction, graph
SkillMIT★ 3Few starsNo key
mcp plugin for claude code to do classic/sementic search in transcripts/docs/code to easy remember discussions, doing better search, etc...
Node.jsMIT★ 1Few starsNo key
Experimental local-first canonical memory layer for AI agents. Go + SQLite + HTTP API + MCP.
GoMIT★ 1Few starsNo key
NotNative Memory Server — semantic memory with embedding search
SkillMPL-2.0★ 3Few starsNo key
🦛 A hippocampus for your AI. Long-term memory for Claude & any MCP client, stored as Markdown in your own GitHub repo: hybrid semantic search, knowledge graph, auto-memory, compaction-proof, token-le
Node.jsMIT★ 1Few starsNo key
Build one shared, permission-aware, auditable AI memory for an entire organization. A vendor-neutral blueprint you hand to a coding agent: 13 pillars, 70 decision forks, an M0-M15 build order. The org
SkillMIT★ 4Few starsNo key
Single-binary Rust WebSocket gateway for a self-hosted AI assistant: streaming, sessions that survive a reconnect, human-in-the-loop permissions, RAG memory and tool execution.
SkillAGPL-3.0Few starsNo key
Persistent memory for AI agents — powered by VectLite. Hybrid search, context compaction, multi-agent swarm, memory teleportation, MCP server, skill engine, decay & conflict resolution, and worktree-a
MCPLink only★ 4Few stars
Production-grade persistent memory for AI agents. Hybrid BM25 + vector search, knowledge graph, lifecycle hooks. 250K+ memories. Built by an AI, for AIs.
SkillMITFew starsNo key
书内 BOOKNOTE · 多账户教材 RAG 学习助手 —— 回答必引原文:C/W 双引用校验、批注阅读器、长对话自动压缩、可选联网补充(MCP)
SkillGPL-3.0★ 45No key
Persistent long-term memory for Agents — an MCP server with an associative memory bank, a canonical-fact cortex, sleep-like dream consolidation, and a web console. Not quite alive.
PythonApache-2.0★ 6No key
Persistent vector memory for AI coding agents. Hybrid search (FTS5 + semantic vectors) in a single Rust binary.
SkillMIT★ 3Few starsNo key
Shared memory bus for MCP-compatible agents with permissions, subscriptions, and optional payments.
PythonMIT★ 22No key
Local-first memory and governance layer for AI agents, with per-agent vaults, hybrid recall, review-first learning, handoffs, audit trails, and native AFM/bridge provider support.
PythonMIT★ 2Few starsNo key
Your code changed. Your agent's memory should too. Adaptive working context for Claude Code, local repository memory, and verifier-backed runs for Claude Code, Codex, and OpenCode.
PythonMIT★ 1Few starsNo key
Local-first, human-editable memory infrastructure for AI agents. Git for AI memory.
PythonGPL-3.0★ 1Few starsNo key
A different approach to solve AI agent memory
SkillApache-2.0★ 2Few starsNo key
Who stands behind it
