Open source · MIT · v2.0.2 · On the official MCP Registry

Accountable, vault-native
memory for Claude Code

Your Markdown vault stays the source of truth. Everything derived from it is rebuildable — never authoritative. No LLM on the critical path. Redaction before every store.

Open source, MIT. Any MCP client.

MIT PyPI npm MCP Registry

Three things that never change

These guarantees hold regardless of configuration. A user config can never override a built-in invariant.

Markdown is the source of truth

Your .md files live in your vault. Every derived store — full-text index, embeddings, knowledge graph, summaries — is computed from them and fully rebuildable from scratch. Nothing derived is ever authoritative.

vault-native · rebuildable

No LLM on the Stop or critical path

Capture is fully deterministic. The Stop hook never calls a model or makes a network request. Work is captured synchronously and heavy processing happens in the background — off the hot path entirely.

p95 ~3 ms · seed-42 benchmark

Redaction before every derived store

Configured redaction patterns run before anything is written to any index, embedding store, or knowledge graph. A user-level config can never weaken a built-in privacy mode — the gate is enforced at the system layer.

privacy-first · config-safe

How it works

A deterministic pipeline from your vault to queryable, rebuildable derived stores. No model on the write path.

SOURCE HOOK DERIVED Markdown Vault .md .md .md source of truth Stop Hook deterministic · no LLM no network · p95 ~3 ms sync capture → bg processing Redaction Gate before every store PRIVACY GATE rebuildable · never authoritative FTS5 full-text search Dense embeddings KG knowledge graph Σ summaries mneme rebuild --all

Get started in three commands

Install whichever components fit your setup — the Claude Code plugin, the core engine, or the standalone MCP server for any MCP client.

Claude Code

Plugin

pipx install mneme-cc-plugin && mneme install .
Installs the plugin and wires the Stop hook into your local Claude Code instance.
Python

Core Engine

pip install mneme-core
Standalone engine: vault indexing, FTS5, dense retrieval, redaction, and the benchmark harness. Available on PyPI.
npm

MCP Server

npm install -g mneme-mcp-server
Provides the mneme-mcp command. Use with any MCP-compatible client. On npm.

Benchmarks

Reproducible regression anchors measured on a seeded synthetic corpus. Not real-world generalizability claims.

Benchmark results — seed 42 synthetic corpus make bench-all
Reproducible regression anchors on a seeded synthetic corpus (seed 42). Not real-world or superiority measurements. Reproduce locally with make bench-all.
0.893 out of 1.0
Retrieval nDCG@5
score = 0.893 · seed-42 corpus
1.000 perfect ★ ★ ★ ★ ★
Recall@10
score = 1.000 · all relevant docs found
Stop Hook Latency — p95 headroom vs CI budget ~3 ms actual · 1000 ms CI budget
0 ms 250 ms 500 ms 750 ms 1000 ms
~3 ms — 99.7% of the CI budget left unused
~3 MILLISECONDS p95
Shell-output compression
88% reduction in stored bytes
Injection deduplication
95% duplicate context blocks removed
claude-mem migration — assertion coverage
Vault structure preserved
Index rebuilt correctly
Redaction rules migrated
Query results consistent
4 / 4 assertions passed on seeded migration fixture. Reproduce with make bench-migration.

How it compares

This compares architectural capabilities across the dimensions mneme commits to. The cells describe design properties that are publicly verifiable from each tool documentation. They are not a benchmarked ranking, and the table deliberately includes rows where another tool leads.

Dimension mneme claude-mem mem0 Letta Zep Supermemory
Plain-markdown store you can git diff and grep ~
Built-in private-tag redaction with SHA256 audit
Deterministic Stop capture, no LLM call n/a n/a n/a n/a
Hybrid retrieval, FTS5 plus local dense, RRF-fused ~ ~ ~
Temporal claim lifecycle (valid-from/to, supersedes) gated ~ ~ ~
Project and code graph (tree-sitter, PR-impact) gated ~
Adaptive token and context budget
Agent security: capability firewall, taint, approval gate
One-command lossless migration from claude-mem n/a
Local-first, no cloud account required ~
Runs in Claude Code, Codex, Antigravity, any MCP client ~ ~ ~ ~ ~
License MIT Apache-2.0 Apache-2.0 Apache-2.0 cloud open source
Cloud-hosted team memory with a web graph UI today ~
Agent autonomously rewrites its own memory ~ ~
Auto-summarization at session end, on by default ~ ~ ~
Localized observation-prompt presets
Built in (shipped, no flag needed)
gated Shipped, needs opt-in dependency or flag
~ Partial
Not available
n/a Not applicable

Opt-in, local-first extensions

All modules are off by default. Nothing phones home. Enable only what you need.

Project & Code Graph

tree-sitter parsing for Python, JavaScript, and TypeScript. Extracts symbols, call graphs, and module boundaries from your codebase into the knowledge graph.

tree-sitter Python/JS/TS opt-in

Code Memory

Parses AGENTS.md conventions and captures failure-and-fix pairs across sessions. Surfaces relevant prior solutions when patterns recur.

AGENTS.md opt-in local

Domain Privacy Modes

Clinical and security-review modes that enforce stricter redaction policies and block external extraction at the config layer — not overrideable by user config.

clinical sec-review opt-in

Agent-Security Layer

Capability firewall, taint tracking, and human-approval gate. Ships with a poisoned-vault benchmark for regression testing security controls.

taint tracking opt-in local

Offline Audit Console

Read-only HTML audit console. Inspect your vault index, redaction log, and retrieval results entirely offline — no server, no external calls.

HTML opt-in offline

Hybrid Retrieval (RRF)

Local dense retrieval fused with FTS5 via Reciprocal Rank Fusion. Combines semantic similarity and keyword precision in a single ranked result set.

RRF opt-in local

Temporal Extraction

Extracts temporal claims from vault notes and exports them to Graphiti-compatible format for timeline reasoning and knowledge-graph queries.

Graphiti opt-in local

Obsidian & GitHub Connectors

Sync vault structure from Obsidian and ingest GitHub issue and PR context. Both connectors are opt-in and off by default — no data leaves your machine unless you enable them.

Obsidian GitHub opt-in

On the MCP Registry

Discovery from a single, ownership-verified source — not a random GitHub link.

mneme is listed on the official MCP Registry — the canonical, project-maintained directory of Model Context Protocol servers. Any MCP client can discover and install mneme from a single verified source.

io.github.TheGoatPsy/mneme

The io.github.TheGoatPsy namespace is bound to the GitHub account that owns the project — so the entry is ownership-verified, not self-asserted.

Visit MCP Registry
MCP Registry registry.modelcontextprotocol.io io.github.TheGoatPsy /mneme GitHub account TheGoatPsy namespace ownership verified

Honest about where mneme fits

mneme publishes a straightforward account of where it is — and is not — the right tool for a given use case. No marketing hedging, no cherry-picked scenarios. Read the full capability matrix: github.com/TheGoatPsy/mneme/blob/main/docs/COMPETITIVE.md →

Frequently asked questions

Honest answers. No aspirational claims.