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.
-
Auditable memory (memory3l)no update data
Audited memory over MCP: an append-only fact ledger plus verifiable invariants I1-I5.
pypi -
MCP server for auditable long-term memory in AI workspaces. JSON-RPC over stdio, stdlib only.
MIT -
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 -
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. SQLite local storage. Every mutation audited.
npm Apache-2.0 ★ 7 -
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 -
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 -
Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem
pypi Apache-2.0 ★ 14 -
@weavory/mcpgithub.com/deepakkts/weavory.aiupdated this year
weavory.ai — Responsible-AI memory for agent swarms. Every belief signed, every decision auditable. MCP-native.
npm Apache-2.0 -
MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.
MIT ★ 29 -
Recall — a user-controlled memory layer for your ChatGPT agent, built natively on WebMCP. A website that IS the agent's memory: visible, editable, auditable, and revocable.
MIT -
FedCtx — Federated Semantic Infrastructure: HNSW + Graph + Audit + Memory + gRPC + REST + MCP
NOASSERTION -
Agent memory write controls with audit decisions, a durable hold queue and explicit approve or reject operations
MIT -
Self-hosted MCP memory for AI agents: redaction before write, append-only audit, local embeddings, one static binary.
mcpb AGPL-3.0 -
attestlygithub.com/justinhsu1477/attestlyupdated this year
Java-native memory layer for AI agents — Spring Boot Starter with audit trail, MCP-native for Claude Desktop / Cursor
MIT -
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 -
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 -
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 -
Open Agent Context Standard: portable, governed memory and context for AI agents. Python reference implementation with CLI, SQLite, evidence, audit, and MCP adapters.
pypi Apache-2.0 ★ 1 -
Structured, portable, auditable memory for AI agents — plain Markdown (.mem.md) you can read, diff and audit. Spec + CLI + MCP server for Claude Code, Cursor, and any MCP client.
npm Apache-2.0 -
Telarch for ChatGPT and Codex: a hosted MCP app at telarch.ai/mcp and a local stdio plugin for Harpe context budgets, Kibisis memory and Argus audit records.
MIT -
Persistent memory + security layer for Claude Code (MCP plugin). Agents remember your project across sessions (~87% fewer context tokens), every tool call lands in a tamper-evident HMAC audit chain, and skills are AST-scanned + HMAC-verified before they run. 100% local: PostgreSQL + Ollama, no cloud, MIT.
MIT ★ 8 -
Local SQLite memory for AI agents with bilingual search, TTL, audit, CLI and MCP
MIT -
RL & control-aware MCP memory system for structured experiment tracking, theory audit, and safe pattern reuse.
MIT -
acm-memoryupdated this year
Consented, local, auditable autobiographical memory for MCP hosts (Claude Desktop and others), judged by a local model
pypi acm-memory — Proprietary Evaluation License Copyright (c) 202 -
memory-quality-mcpgithub.com/ladyiceberg/memory-quality-mcpupdated this year
A Claude Code MCP plugin that audits and cleans up your AI memory store
pypi MIT ★ 1 -
Local-first MCP memory server with SQLite storage, scoped retrieval, governance, and audit trail for agents.
MIT -
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
npm MIT -
Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.
MIT ★ 5 -
让 AI 跨对话记住你。Local-first, auditable AI memory for OpenAI-compatible clients and MCP.
Apache-2.0 ★ 2 -
Native XMemo cloud-memory provider for OpenClaw agents: long-term memory, semantic recall, TODOs, snapshots, and audit tools.
npm -
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 -
Has a human checked this? Seal/serve/audit over verified-match memory — ledger, MCP, and CLI.
Apache-2.0 ★ 1 -
Orenylgithub.com/edison-zhou-nc/Orenylupdated this year
Orenyl - A compliance-grade MCP memory with deterministic deletion and auditable lineage
pypi NOASSERTION -
octopodagithub.com/ryjoxtechnologies/octopoda-osupdated this year
Persistent Memory Kernel for AI Agents — crash recovery, shared memory, audit trail, real-time dashboard
pypi MIT -
Local-first neural memory for AI agents: private Markdown/Obsidian vaults, auditable retrieval, and MCP access.
MIT ★ 2 -
Personal Memory / Context OS — local-first, auditable, readable by every MCP agent
NOASSERTION ★ 2 -
mnemicgithub.com/dongtang3/mnemicupdated this year
Local-first memory kernel for coding agents: MCP-native, temporal, auditable, source-keyed, and benchmarked.
MIT ★ 2 -
memgategithub.com/Denizayhan04/memgateupdated this year
Access control, conflict resolution, and audit for shared agent memory. An MCP server.
Apache-2.0 ★ 1 -
The memory layer that can be corrected: provenance-first agent memory with a real corrections API and a one-command junk audit.
MIT ★ 1 -
orbi-mcpupdated this year
Immutable AI Memory. Permanent storage and audit trails for AI agents on the Arweave Permaweb.
npm MIT -
Auditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai
npm MIT ★ 161 -
Local-first memory layer for OpenClaw, Codex, and Claude — capture, recall, dedupe, audit, native sync
npm MIT -
Zero-dependency cross-agent memory + session bridge for Claude Code, Codex, opencode and ZCode: one auditable MEMORY.md injected natively, a stdlib MCP server, history mining into project state files, and cross-agent session reading + scheduling.
MIT -
Remote Streamable HTTP MCP server for live checkout drift audits, UX inspection, Search Console SEO, and horizon memory
MIT -
Local-first, auditable memory layer for AI apps and coding agents — Codex, Claude Code, MCP, HTTP, TypeScript, and Python.
npm MIT ★ 21 -
Open-source, self-hosted team memory for AI coding agents. Share, search, and audit project context through MCP.
MIT ★ 2 -
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
pypi Apache-2.0 ★ 323 -
Self-hostable, GDPR-aware long-term memory for AI agents over MCP. Distills sessions into compact memories with local models on Postgres + pgvector, forgets on request with an audit trail, and ships a reproducible eval.
Apache-2.0 -
Local project memory and consistency checks for coding agents. Go CLI and MCP with explicit agreements and audited continuity.
-
Durable, private memory for AI agents. Fully offline MCP memory layer: LMDB + Tantivy/BM25, no models, no cloud. Ships with full source - audit it, extend it, make it yours.
NOASSERTION ★ 4 -
palimemgithub.com/palimem/palimemupdated this year
Governed local-first memory for coding agents — supersession, scoped recall, and audit on your machine. Spec v1.7.0, 143 validation behaviors.
Apache-2.0 ★ 2 -
Local-first memory for AI agents as an MCP server: semantic + keyword recall, typed memories, graph relations, audit log. npm: agent-memory-engine
MIT -
Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.
cargo MIT ★ 33 -
Auditable memory for agent teams. Self-hosted, deterministic retrieval, no LLM in the critical path. Python + MCP + Docker.
pypi MIT ★ 14 -
Memory patrol + lexical recall + conversation gates for long-lived agents. Auditable SQLite kernels, CLI + MCP, zero runtime deps. 记忆巡检、召回打分与群聊接话决策内核;可审计、零依赖。
MIT ★ 1 -
Miragithub.com/zxheyi/Miraactive
Local-first project memory for coding agents. Preserve context across sessions with auditable memories, MCP integration, and evidence-gated research.
-
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 -
Auditable memory for AI agents — provable deletion (crypto-shred + signed certificate), a tamper-evident audit chain, and bi-temporal time-travel recall. Runs on SQLite or Postgres.
pypi Apache-2.0 -
Persistent cross-project memory for coding agents — an agent-authored markdown vault over MCP, auditable in Obsidian.
MIT ★ 4 -
unified-memory-harness-for-claude-code-and-codexgithub.com/Justaboringname/unified-memory-harness-for-claude-code-and-codexupdated this year
Unified Memory Harness for Claude Code & Codex — local-first, auditable unified memory (SQLite/FTS5 + Memory MCP) over Claude exports & Claude Code assets, plus a streaming side-by-side ccc CLI and a Claude+Codex dual-agent council with a structural single-writer lease.