MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Memory Router is a local-first context optimization layer and LLM aggregator. It is not a coding assistant, an IDE, a Claude Code replacement, or a shell-runner. It does not execute commands, modify y
PythonMIT★ 1Few starsNo key
File-first MCP memory for coding agents
PythonMIT★ 1Few starsNo key
Portable local memory system and MCP search tooling for file-reading AI coding agents.
PythonMIT★ 1Few starsNo key
Memory that reviews itself: a markdown wiki for coding agents over MCP, plus drift reports and digests of your own sessions.
PythonMITFew starsNo key
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
PythonApache-2.0★ 14kNo key
Shared Markdown memory server for agents over MCP
PythonMIT★ 1Few starsNo key
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
PythonAGPL-3.0★ 4.4kNo key
Persistent memory for AI agents over the Model Context Protocol (MCP). Filesystem-backed, dependency-light, keyword search.
PythonMITFew starsNo key
Local-first memory your AI agents share over MCP. Agents propose; only you confirm. 记忆蜂巢 / Memory Hive — plain files on your own disk.
PythonMITFew starsNeeds a key
Local markdown memory & cross-agent context engine for coding agents (MCP).
PythonMIT★ 5No key
Durable, repo-native project memory for coding agents, without context bloat.
SkillMIT★ 25No key
MCP server over the fleet markdown-memory store: read + careful-write of memories as typed tools
PythonMITFew starsNo key
Shared, git-tracked memory for AI agents on the same codebase. What one Claude/Cursor/Cline learns, the next one picks up. No DB, no SaaS — just files in your repo. CLI + MCP server.
PythonMIT★ 1Few starsNo key
A high-performance MCP Server for Network Forensics that enables AI agents to analyze PCAP files through the Model Context Protocol. Built with direct tshark integration for maximum speed.
MCPLink only★ 2Few stars
为 AI Agent 打造的透明 Markdown 白盒 + L0-L3 分层混合记忆系统，支持 CBT 心理安全与企业级多租户部署.A transparent, Markdown-backed, L0-L3 tiered hybrid memory system for AI Agents with CBT safety and Enterprise multi-tenancy support.
PythonMITFew starsNo key
Local-first Obsidian memory bank CLI for AI coding agents, with run logging, linked project notes, compaction, and search.
SkillMIT★ 7No key
Memory health monitor for AI agents — detects contradictions, duplicates, staleness, and orphan references in markdown-based memory stores - by Eli
PythonApache-2.0★ 3Few starsNo key
MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API keys, no network.
PythonMIT★ 1Few starsNo key
OpenClaw Memory is a lightweight, AI-agent-focused memory server implementing the Memory Communication Protocol (MCP). It is built on the principle that “Markdown is the single source of truth,” prior
PythonApache-2.0★ 4Few starsNo key
Your AI memory as a local folder you own. Claude, Codex, Cursor and any MCP app share it; you see every change and can undo it.
PythonApache-2.0★ 22No key
A local-first, Obsidian-compatible memory layer for persistent AI agents. Reasoner + Retriever + Recorder over a markdown vault.
PythonMIT★ 1Few starsNo key
Tree + graph memory for AI coding agents, backed by Git-syncable Markdown.
SkillApache-2.0★ 9No key
Free, local, structure-preserving memory for AI agents. No API key. No cloud. Just markdown.
PythonMIT★ 9No key
Who stands behind it
