MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
context-memgithub.com/JubaKitiashvili/context-memupdated this year
Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, 100% on LongMemEval, 99% token savings. 44 MCP tools. Fully local, zero cost.
MIT ★ 20 -
Explainable, vectorless RAG for AI agents: BM25 + temporal knowledge graph over your files, served over MCP. R@5 0.977 on LongMemEval-S, ~2 ms queries, 0 LLM calls, zero dependencies.
MIT ★ 1 -
ompagithub.com/jmiaie/ompaactive
Persistent, citable memory for any AI agent: verbatim markdown vault, temporal knowledge graph and local hybrid search over MCP. R@5 0.981 on LongMemEval-S with 0 LLM calls.
MIT ★ 3 -
Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).
Apache-2.0 ★ 12 -
memocortexgithub.com/Justdoitfor/memocortexupdated this year
Agent-agnostic 长期记忆中间件 — 5 类分层记忆 / 4 信号 Hybrid Recall / LLM-as-Arbitrator | LongMemEval-style CN 90% / cn_scenarios 100%
MIT -
Vectorless agent memory. HTML storage + grep retrieval. LongMemEval-S R@5 = 98.9%. No embedding, no vector DB.
MIT -
Persistent local MCP/CLI memory system for AI agents. CPU-only, 98.94–99.15% R@5 on LongMemEval. Named after Mnemosyne (Greek: μνήμη, memory).
MIT ★ 2 -
Local long-term memory for AI coding agents. Keeps every conversation word for word, costs nothing to save, and is shared by all your agents. 91.8% on LongMemEval.
Apache-2.0 ★ 15 -
🧠 给 AI 一个可信的第二大脑:本地 SQLite · 先审核再入库 · 不可篡改审计 · 记忆账本。🕷 蜘蛛侠皮肤 · 🔍 自建集 R@5 99.1% / LongMemEval-S 97.2% · 🧩 一个库接入 DSH / Claude Code / Codex / Cursor / 任意 MCP · ⭐ MIT 开源 · 🚀 零依赖开箱即用
MIT ★ 184 -
Local-first memory backend for AI agents · 99.2% LongMemEval-S retrieval @ k=8 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable
Apache-2.0 ★ 31 -
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.
MIT ★ 77 -
Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.
Apache-2.0 ★ 55 -
Executable agent memory reference implementation and research workbench
Apache-2.0 -
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
npm MIT ★ 64