MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
memory-xx 是一套面向 AI Agent 的长期记忆框架，用来让 Codex、Claude Code、OpenClaw 等本地或多 Agent 系统安全地记录、更新和召回长期记忆。
SkillMIT★ 1Few starsNo key
Persistent semantic memory service and MCP adapter for AI agents, powered by PostgreSQL and local Ollama models.
SkillApache-2.0★ 1Few starsNo key
A local-first AI memory system with hybrid search, MCP integration, and a knowledge graph.
DockerMIT★ 65Needs a key
Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how
OfficialSkillMIT★ 40k in collectionNo key
Local-first engineering memory built for OpenAI Codex, reusable by other coding agents.
PythonMIT★ 4Few starsNo key
Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how
OfficialSkillApache-2.0★ 256 in collectionNo key
Local, approval-based memory for coding agents, with MCP integration and reproducible evaluation.
PythonGPL-3.0Few starsNo key
Local-first persistent memory for AI agents: Chinese-first recall, forgetting-aware ranking, conflict candidates, SDK + CLI.
PythonMIT★ 5No key
A local-first, generic persistent memory layer for MCP agents, with semantic search, revisions, provenance, temporal recall, and relationships.
Node.jsMIT★ 1Few starsNo key
Source-backed memory for AI agents: Git citations, local retrieval, CLI, and MCP.
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
Brain-inspired persistent memory for AI coding assistants. Hybrid BM25+vector search, ACT-R activation scoring, FadeMem decay, knowledge graphs, multi-agent coordination. Successor to claude-memory.
PythonMIT★ 3Few starsNo key
Persistent, per-project memory for Claude Code — a vector-search MCP server with semantic recall, rule enforcement, a React management UI, and Docker/Homebrew installs.
PythonMITFew starsNo key
Local-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, priva
SkillApache-2.0★ 422No key
Memory Operations Platform for AI agents — ingestion, lifecycle, token-aware retrieval, and control UI
SkillMIT★ 4Few starsNo key
Persistent conversational memory for AI via MCP — built by humans and AI, for humans and AI.
SkillAGPL-3.0Few starsNo key
A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Node.jsMIT★ 2Few starsNo key
MCP server for persistent context management in AI coding assistants
Node.jsMIT★ 136No key
四层记忆引擎 (Memory Engine) — 让 Agent 越用越聪明
SkillMIT★ 1Few starsNo key
One local, searchable memory of every AI coding-agent conversation on the machine, for Hermes Agent and MCP.
PythonMIT★ 1Few starsNo key
Local-first, audited memory MCP for Claude Code, OpenAI Codex, Gemini CLI, Cursor, Cline, Continue and OpenCode. Your agent gets a navigable cognitive map instead of a bloated context file. Zero cloud
SkillApache-2.0★ 7No key
MemoryMCP supercharges AI assistants with persistent memory, semantic caching, and hybrid MongoDB search capabilities. Store conversations, cache responses, and search knowledge bases to provide conte
PythonApache-2.0★ 3Few starsNo key
Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.
PythonApache-2.0★ 7No key
Who stands behind it
