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.
-
基于 MCP 协议的团队经验数据库。AI 在开发过程中自动提取、存储和检索团队的历史经验,解决 AI 编程助手"每次对话都从零开始"的核心痛点。
pypi MIT ★ 1 -
知序:中文团队 AI Session 记忆工作台,证据归档、候选审核、知识版本治理与权限隔离的 MCP 召回。
MIT -
team-memory-mcpgithub.com/gustavolira/team-memory-mcpupdated this year
Shared team memory for AI coding agents. Bayesian confidence scoring with temporal decay. Works with Claude Code, Devin, Cursor, and any MCP-compatible client.
npm MIT ★ 18 -
Self-hosted, permission-aware shared memory for developers and AI coding agents, served over MCP. Go, PostgreSQL + pgvector. Personal proof of concept.
Apache-2.0 -
Shared memory for AI coding tools and teams that stays true to your code. Local, free, open source.
pypi MIT ★ 5 -
claude-memorygithub.com/Codex-v/claude-memoryupdated this year
Persistent AI Memory MCP Server for Claude - Team collaboration with shared rules and knowledge
MIT -
Klear-Team-Braingithub.com/Asklear/Klear-Team-Brainupdated this year
Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query right from your editor over MCP.
Apache-2.0 ★ 83 -
The memory Codex is missing: shared, permanent memory for your team
NOASSERTION -
Self-hosted shared memory for AI coding agents and their team: MCP tools for Claude Code, Cursor, Codex and Gemini CLI, plus a web UI for people. Docker, Postgres + pgvector.
MIT -
Open-source, self-hosted team memory for AI coding agents. Share, search, and audit project context through MCP.
MIT ★ 2 -
Team-aware memory for AI coding assistants — intent tracking, decision history, real-time team conflict detection.
NOASSERTION -
SyncContextgithub.com/infinitylabs-io/SyncContextupdated this year
Shared team memory MCP server with semantic search — sync context across AI coding agents
MIT ★ 1 -
Shared memory and switchboard for teams whose members each run their own AI agents. Meetings → decisions and action items, team knowledge graph, MCP tool surface, A2A broker with human oversight.
Apache-2.0 ★ 2 -
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.
Apache-2.0 ★ 9 -
Self-hostable, MCP-native memory backend for teams of humans and AI agents. A FastAPI service enforces a tagging contract (team/project scope, visibility, confidence, truth level, source, validation) over PostgreSQL, Qdrant, and Neo4j, with team-scoped, truth-filtered retrieval across multiple chat frontends.
MIT ★ 2 -
krimtogithub.com/krimto-labs/krimtoupdated this year
Open-source team memory layer for AI coding agents — markdown files in git, user→team→org hierarchy, cross-vendor MCP server. Apache-2.0.
npm Apache-2.0 ★ 7 -
ai-dev-teamgithub.com/JoeSoep/ai-dev-teamupdated this year
Local-first AI development team cockpit for Codex, Claude Code, MCP shared memory, Telegram inbox tasks, and evidence-based maintainer workflows.
MIT ★ 2 -
Shared Memory MCP server for agentic teams - solving coordination tax with 6x token efficiency
MIT ★ 8 -
Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.
Apache-2.0 ★ 39 -
Give every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.
NOASSERTION ★ 103 -
DSH for Teams — Deploy DSH once on your LAN; memory, knowledge base & document search included. Team-ready, up to ~20 users. MIT-licensed.
MIT ★ 11 -
distillgithub.com/5queezer/distillupdated this year
Privacy-first team memory MCP server — local LLM distillation before team sync
pypi MIT ★ 1 -
Self-hosted MCP memory server for personal use and teams
pypi AGPL-3.0 ★ 30 -
Self-hosted AI memory gateway — MCP server for loose teams
NOASSERTION -
Shared, encrypted, verifiable team memory for coding agents (MCP server)
Apache-2.0 ★ 1 -
Self-hosted AI teammate for Slack and Microsoft Teams: proactive, team memory, MCP tools, coding sessions with draft MRs. Any LLM, your infrastructure.
Apache-2.0 -
teamemgithub.com/RubiYH/teamemupdated this year
Team Memory For Human And Agent
npm Apache-2.0 ★ 1 -
Shared team memory and run control for coding agents: Claude Code, Codex, Cursor, OpenCode
npm Apache-2.0 -
RCLL — self-hosted, hierarchical shared memory for a team of AI agents over MCP (rooms, L0-L3 depth, pgvector). Fork of vectorize-io/hindsight.
npm MIT -
Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253
npm AGPL-3.0 ★ 277 -
LITSAN (formerly Memhub): self-hosted AI memory for people and teams: project continuity, traceable evidence, private workspaces, and MCP integration.
NOASSERTION ★ 17 -
knowitgithub.com/ismaelkedir/knowitupdated this year
Shared team memory for AI coding agents — MCP server and CLI for persistent, queryable knowledge across sessions and teammates
npm MIT -
Evidence-based agent memory layer for Codex, Claude Code, and development teams
pypi Apache Software License -
Sechelgithub.com/SamuelCastrillon/Sechelupdated this year
Serverless MCP memory server for AI coding agents. Next.js + Turso on Vercel, with team access admin panel.
MIT -
Memory Bank is an MCP server that helps teams create, manage, and access structured project documentation. It generates and maintains a set of interconnected Markdown documents that capture different aspects of project knowledge, from high-level goals to technical details and day-to-day progress.
★ 101 -
cambium-mcpgithub.com/jarmstrong158/cambiumupdated this year
Knowledge-lifecycle MCP: distill agentsync + context-keeper events into memory, recall across projects, promote local -> team -> org
pypi PolyForm-Noncommercial-1.0.0 -
Self-improving, self-hosted memory across every AI coding tool, project, and team (Claude Code, Cursor, Copilot, any MCP client). Autoskill proposes new skills from your sessions, so each project improves automatically. Inspectable, grounded, and yours. Built for teams and enterprise. Open source, MIT.
MIT ★ 4 -
ai-memory-vaultgithub.com/munikumar-pulikanti/ai-memory-vaultupdated this year
Persistent memory layer for AI coding agents — SQLite + FTS, ChromaDB semantic search, and optional DynamoDB team sync. Query-first, so agents check accumulated knowledge before touching Jira, AWS, or code.
MIT ★ 1 -
@ambih/coding-agent-memoryactive
Memory for AI coding agents: the plans, tasks, decisions, rules and bugs your agents work through, recorded automatically, shared with your team, readable by every agent through MCP, with a dashboard.
npm Apache-2.0 -
omemgithub.com/ourmem/omemupdated this year
Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.
npm NOASSERTION ★ 174 -
Auditable memory for agent teams. Self-hosted, deterministic retrieval, no LLM in the critical path. Python + MCP + Docker.
pypi MIT ★ 14 -
GoBPgithub.com/mihos3506/GoBPupdated this year
Graph-based knowledge store for AI dev teams. Shared memory across Cursor, Claude, Qodo via MCP.
-
annalgithub.com/heyhayes/annalupdated this year
Semantic memory server for AI agent teams. MCP server, ChromaDB or Qdrant, local ONNX embeddings.
MIT -
hivesharegithub.com/KB-perByte/hiveshareupdated this year
Collaborative AI memory for engineering teams - share context across Claude Code, Cursor, and teammates
MIT ★ 5 -
knowledgeplanegithub.com/camplight/knowledgeplaneupdated this year
Shared memory for AI agents and teams -- MCP server with knowledge graph, vector search, and auto-consolidation
NOASSERTION ★ 3 -
pneumagithub.com/knrl/pneumaupdated this year
Pneuma gives your AI coding assistant persistent memory. It mines your codebase, ingests Slack/Teams chat, and exposes everything via MCP tools.
MIT ★ 1 -
Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 40 MCP tools.
NOASSERTION ★ 11 -
Persistent memory, task manager and an AI agent team for Claude Code, ZCode, Codex and OpenCode — one local MCP daemon: DuckDB vector search, rule enforcement, asoode board mirror, React UI. Local-first, nothing leaves the machine.
MIT -
distillery-mcpupdated this year
Persistent shared memory for Claude Code — MCP server with DuckDB vector search, semantic dedup, and ambient intelligence for team knowledge
pypi Apache-2.0 -
Portable, human-approved memory for AI agents. Grow with you & your teams.
npm GPL-3.0-only -
Loomgithub.com/Kaushik-hub306/Loomupdated this year
Shared memory for AI agents — an MCP server that gives Claude Code, Cursor, and Claude Desktop persistent team knowledge.
MIT ★ 2 -
One shared memory for every AI coding tool your team uses. Self-hosted, single Go binary, MCP-native.
Apache-2.0 -
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Long-term memory via Model Context Protocol with semantic search, Git sync, and team collaboration.
npm MIT ★ 2 -
VERA is a shared, governed memory platform for AI agents, providing trusted, temporal knowledge across teams through MCP, with Graphiti as the underlying memory engine.
Apache-2.0 ★ 4 -
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
NOASSERTION ★ 88 -
Context engineering toolkit for AI agents. 24 MCP tools across retrieval, memory, context, and team telemetry. .NET 10. No cloud deps.
nuget MIT ★ 2 -
tribalgithub.com/tribal-memory/tribalupdated this year
Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Rust, Postgres + pgvector.
oci ★ 10 -
calq-mcpgithub.com/Calq-dev/calq-mcpupdated this year
MCP server for time tracking, project management, memory, and team collaboration
★ 1 -
RCLL — self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. We publish the measured cost of one shared store versus ten private ones. Fork of vectorize-io/hindsight (MIT).
npm MIT -
Shared project memory and handoff for teams working with AI agents. Checkpoint decisions, rehydrate context, hand work over — through MCP or the CLI, in Claude Code, Cursor, or Codex.
npm Apache-2.0 ★ 1