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.
-
memory-governancegithub.com/mzyag/memory-governanceupdated this year
A governance layer for AI agent memory — access control, audit trails, retention policies, and PII redaction via MCP.
MIT -
MCP server for auditable long-term memory in AI workspaces. JSON-RPC over stdio, stdlib only.
MIT -
Governed memory + Obsidian knowledge base plugin for Hermes Agent: 4-layer memory (L1 rules / L2 semantic / L3 archive / L4 persona), auto-distillation with a review gate, MCP + CLI, multi-agent shared store.
MIT -
pi-governance-enginegithub.com/mont3ll/pi-governance-rsupdated this year
Local-first governed memory CLI and MCP stdio server for AI agents.
cargo MIT OR Apache-2.0 -
governedmemorygithub.com/Metaworkers-ai/governedmemoryupdated this year
Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.
pypi MIT ★ 10 -
Official Lucy MCP runtime for governed agent memory. Three tools only: recall, propose, proposal status.
npm Apache-2.0 -
governed-contextgithub.com/leonardoeverling-spec/governed-contextupdated this year
Governed memory for AI agents: explicit states, fail-closed sensitivity gates, quarantine-only writes (dependency-free MCP server) + a blind-evaluation protocol skill
MIT -
Heartwood Memory — governed memory for AI agents. Provenance-first recall, policy-gated retrieval, tenant isolation.
pypi NOASSERTION -
Local-first, reviewable memory layer for Codex with MCP, lifecycle hooks, and memory governance.
pypi MIT ★ 1 -
@threadline/mcpupdated this year
MCP server for Threadline — memory governance for AI agents
npm MIT -
AGI-Memorygithub.com/PrecipAI/AGI-Memoryupdated this year
Unified long-term memory and knowledge platform for AI agents with MCP, governance, and graph-oriented knowledge evolution.
NOASSERTION ★ 8 -
@iflow-mcp/beach55607-max-mcp-memory-serverupdated this year
MCP Memory Server — semantic memory with governance for AI coding agents. Cloudflare Workers + D1 + Vectorize + Workers AI.
npm MIT -
sovant-claude-code-mcpgithub.com/sovant-ai/sovant-claude-code-mcpupdated this year
Governed, explicit memory adapter for Claude Code (MCP).
MIT ★ 2 -
Governed multi-agent memory for AI agents — hybrid markdown+SQLite, FTS, vector search, LLM reranking. One Go binary, MCP stdio + HTTP + SSE.
Apache-2.0 ★ 1 -
vault-for-llmgithub.com/zycaskevin/vault-agent-memoryupdated this year
Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.
pypi Apache-2.0 -
Local-first control plane for evidence-linked decision memory, governed tasks, deterministic evals, and human-approved actions.
MIT -
panellaupdated this year
Governed, self-hosted memory for AI agents — a standard MCP server.
pypi Apache-2.0 -
hermorah-plugingithub.com/lornn-inc/hermorah-pluginupdated this year
Memory & governance for AI agents — the open hermorah connector for Claude Code: always-loaded memory at session start, live MCP memory tools, automatic pool sync.
Apache-2.0 ★ 1 -
@sgraal/mcpgithub.com/sgraal-ai/coreupdated this year
AI agent memory governance MCP server — preflight validation before every action. Works with Claude Desktop, LangGraph, and any MCP-compatible client.
npm Apache-2.0 -
Zdravo — enterprise AI governance infrastructure. MCP server for governed memory, context, and workspace capabilities.
npm MIT -
humane-intelligencegithub.com/sammyboi81/humane-intelligenceupdated this year
Governed, tamper-evident memory for any AI — an MCP server. Memory so it doesn't lose itself; governance so it can't lose us.
pypi Apache-2.0 -
Local-first MCP memory backend and governance console for coding agents
pypi MIT -
MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.
MIT ★ 29 -
Local-first MCP memory governance for coding agents — Codex, Claude Code, Cursor, Grok, and Trae. Shared rules, deduplication, token insights, audit, and rollback.
MIT ★ 4 -
mori MCP server — a governed memory layer for AI coding agents.
AGPL-3.0 ★ 32 -
Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.
go Apache-2.0 ★ 22 -
agentlawgithub.com/paranmir/agentlaw-workspaceupdated this year
Law-first governance kit for AI coding agents: installable scaffold + memory MCP server that lets agents read project rules before they write code.
pypi MIT -
Check agent memory against the Vercy Governance Overlay, plus a read-only MCP server over the Vercy model catalogue.
Apache-2.0 -
Zdravo AI MCP Server — governed memory, context, and workspace capabilities for AI agents (stdio + SSE)
npm MIT -
AI Engineering Governance Platform — Session memory, feature registry, code intelligence, and rule enforcement for AI coding assistants.
npm NOASSERTION ★ 2 -
ArkHive — local-first governed memory for AI agents: tamper-evident SHA-256 ledger for identity, audit history, verification, and constraint-aware decisions. Apache-2.0.
pypi Apache-2.0 ★ 1 -
The context quality layer for AI agents — memory that checks itself: lifecycle governance, calibrated confidence, and staged claim gates. Local-first, MCP 13 tools, DeepSeek Harness plugin.
npm Apache-2.0 ★ 12 -
mayrosgithub.com/ApiliumCode/mayrosupdated this year
The governed AI agent platform: semantic memory, intelligent model routing, an MCP server, and 67+ integrations.
npm MIT ★ 13 -
A governance layer for agent memory: write gate, read gate, verifiable forgetting, hash-chained audit trail. Sits in front of the memory store you already run.
MIT ★ 1 -
Persistent, governed memory for AI clients over MCP, built as a rahi cell. Recalled content is data; only a human-recorded promotion makes a memory instruction grade. Specified, being built one spec per PR. Apache-2.0.
Apache-2.0 -
MCP server for H1VE — gives Claude Code / Cursor your project's memory (recall), branch context, and delivery workflow. The governance & memory layer for teams building with AI.
npm MIT -
Persistent, source-backed memory for AI coding assistants. Local-first Rust CLI, MCP server, REST API, and governed retrieval.
Apache-2.0 ★ 5 -
ctxlayer-releasegithub.com/abhilashsblai/ctxlayer-releaseupdated this year
CTX Layer: context engineering, memory, governance, MCP, and impact analysis for AI coding agents like Codex.
NOASSERTION -
procheiron-coregithub.com/logotheusneuro-cpu/procheiron-coreupdated this year
Governance and provenance layer for agent memory: enforced independent-review lifecycle with a tamper-evident, optionally-signed audit trail. Spec + reference implementation, stdlib-only core.
pypi MIT -
@myth-os/mcpgithub.com/starhub-studios/mythos-mcpupdated this year
MCP server for narrative identity, governance, eval quality, and memory. Gives your AI agent a persistent understanding of who it's working for.
npm MIT -
Kütüphane — a governed knowledge catalog and memory layer for AI agents: one copy for people, agents and applications, with origin, acceptance and use rights on every item. MCP + HTTP, on-prem.
Apache-2.0 -
enterlockgithub.com/enterlock/enterlockupdated this year
Name reserved for enterLOCK: a local-first memory governance kernel for AI agents — tamper-evident HMAC audit chain, a memory immune system that quarantines poisoned content, externally anchorable Merkle checkpoints, and cryptographic deletion receipts. Full v0.12.0 release (CLI + MCP server) coming soon.
cargo MIT OR Apache-2.0 -
Governance layer in front of an agent memory store — promotes per-actor memories into reviewed, audited, namespace-scoped facts served to agents over MCP.
MIT -
touchgrass-mcp-servergithub.com/chrbailey/touchgrassupdated this year
AI Chief of Staff — emotional memory, Bayesian belief tracking, dual-engine gap analysis, voice-adaptive briefings, and governed memory. MCP server for Claude Code.
pypi MIT -
Local-first MCP server for persistent engineering memory, 26 specialist agents and repository dependency graphs. Human-governed learning for Claude Code, Codex and VS Code.
pypi Apache-2.0 -
novyx-mcpupdated this year
MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows. Local SQLite memory works zero-config; hosted governance and approvals use Novyx Cloud.
pypi MIT -
@radix-ai/ai-memorygithub.com/radix-ai/ai-memoryupdated this year
Persistent AI memory for any project. MCP server, compound protocol, governance enforcement.
npm MIT -
vgxnessgithub.com/uzielvgx/vgxnessupdated this year
Local-first governance OS, CLI and MCP control plane for existing coding agents, SDD, memory, runs, permissions, and OpenCode setup.
npm SEE LICENSE IN LICENSE -
@torknetwork/mcp-servergithub.com/torkjacobs/tork-governanceupdated this year
TORK MCP Server - 49 governance tools for AI agents including Memory Integrity, Supply Chain, Cost Controls, and MCP Auditing
npm MIT -
delimitgithub.com/delimit-ai/delimitupdated this year
One workspace for every AI coding assistant. Governance, memory, and tasks across Claude Code, Codex, Cursor, and Gemini CLI.
pypi MIT -
Local-first MCP memory server with SQLite storage, scoped retrieval, governance, and audit trail for agents.
MIT -
RWIF-backed federated semantic memory over MCP: compact disk-native semantic stores with governed writes, Docker-ready deployment, and benchmarked retrieval without a heavyweight vector database tier.
MIT ★ 1 -
Portable, governed, model-agnostic memory for AI agents: facts invalidated never deleted, raw text as truth, one documented export format.
npm Apache-2.0 ★ 3 -
Local-first shared memory for AI agents — zero-dependency, governed writes, citations, MCP. Source behind the ihow-memory npm package.
npm Apache-2.0 ★ 5 -
mimir-mcpgithub.com/buildepicshit/mimirupdated this year
Mimir MCP (Model Context Protocol) stdio server for governed local memory access.
cargo Apache-2.0 -
@l-agence/mcp-server-agencegithub.com/l-agence/agenceupdated this year
MCP server for Agence — AI governance framework with policy enforcement, skills, memory, and multi-LLM consensus
npm MIT -
agentcache-mcpactive
Agent-facing MCP for the AgentCache control plane — cache, pre-spend governance gate, verifiable savings, and cross-run reasoning memory.
npm MIT -
PruneMemgithub.com/Wpoithge/PruneMemupdated this year
MCP-compatible memory governance for AI agents — with structure, state, and lifecycle.
MIT ★ 3 -
MCP server for AI memory, governance, and continuity across session-death. A self-verifying chronicle: honest on write, on read, on reach, and about itself — a failed write can't report success, a partial answer can't pass as complete, and the capability surface is generated from the live registry, not typed. 100% local.
NOASSERTION ★ 3 -
Mnemosyne-AI-Memorygithub.com/nianpangzhi233/Mnemosyne-AI-Memoryupdated this year
Bionic memory for AI agents: GraphRAG, predictive memory, dream consolidation, governed skill evolution, MCP, REST API, and dashboard.
MIT ★ 4