mnemo-mcp
About
Persistent AI memory: store, search, and recall knowledge across sessions
Details
- Author
- n24q02m
- Categories
- AI, Knowledge Base
Jump to
Setup
Install mnemo-mcp in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/n24q02m/mnemo-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.
- Features
- Status
- Documentation
- Smithery
- Tools
- Security
- Build from Source
- CLI
- Remote (HTTP mode)
- Deploy to Cloudflare
- Trust Model
- License
- Hybrid retrieval-- FTS5 + vector search (sqlite-vec locally, Vectorize on Cloudflare), fused via Reciprocal Rank Fusion (k=60), then re-ranked by a configurable rerank chain (RERANK_MODELS, order = litellm fallback; empty -> local qwen3-reranker) with temporal decay and importance boost
- Typed capture--memory(action="capture")with 6 context_types (conversation/fact/preference/skill/task/decision), embedding-based dedup, and a configurable LLM chain (LLM_MODELS, order = litellm fallback)
- Knowledge graph-- Automatic entity extraction and relation tracking; top results boosted by graph proximity
- Importance scoring + archive policy-- LLM-scored 0.0-1.0 importance; soft-archive whenrecency_factor (1 - importance) > 1.0; restore action available
- Auto-archive trigger-- Background sweep every Nth capture (default 100) -- no cron required
- STM-to-LTM consolidation-- LLM summarization of related memories in a category
- Duplicate detection-- Warns before adding semantically similar memories
- Zero config-- Built-in local Qwen3 ONNX embedding + reranking, no API keys needed. Optional cloud providers (Jina AI, Gemini, OpenAI, Cohere)
- Multi-machine sync-- JSONL-based merge sync via Google Drive (bundled Desktop OAuth public client)
- Plugin trinity-- Ships/recall-context+/memory-commitskills and SessionStart + opt-in PostToolUse hooks (seedocs/ARCHITECTURE.md)
- Proactive memory-- Tool descriptions and skills guide AI to save preferences, decisions, facts at the right moment
- LLM compression-- Per-turn compression via the multi-provider dispatcher targets ~3x token reduction at >=0.9 fact retention; graceful skip when no provider configured (seedocs/compression.md)
- Encrypted passport sync-- AES-256-GCM bundles + Argon2id KDF, S3 (R2 / B2 / MinIO) and Google Drive backends, delta-sync with last-write-wins per row (seedocs/passport.md). Bootstrap via thepassport-bootstrapskill.
- Temporal knowledge graph-- Bitemporal columns (valid_from/valid_to/superseded_by) on every memory + entity-resolution dedup (embedding KNN at default 0.85 cosine threshold) + audit trail (memory_audittable with prev/new state hashes) + new actions (entity_search/entity_graph/history) + opt-inKG_AUTO_ENABLEDauto-extract on capture.BREAKINGfor clients that calledmemory.getexpecting historical-inclusive results: passas_offor time-travel; default now filters to current-state (valid_to IS NULL).
2026-05-02 -- Architecture stabilization update
Past months saw significant churn around credential handling and the daemon-bridge auto-spawn pattern. This caused multi-process races, browser tab spam, and inconsistent setup UX across plugins.The architecture is now stable: 2 clean modes (stdio + HTTP), no daemon-bridge layer, no auto-spawn from stdio.
Apologies for the instability period. If you encountered issues with prior versions, please update to the latest release and follow the currentsetup docs-- most prior workarounds are no longer needed.
- wet-mcp-- Web search + content extraction
- imagine-mcp-- Image/video understanding + generation
- better-notion-mcp-- Notion API
- better-email-mcp-- Email management
- better-telegram-mcp-- Telegram
- better-godot-mcp-- Godot Engine
- better-code-review-graph-- Code review knowledge graph
All plugins share the same architecture -- install once, learn pattern transfers.
Full docs atmcp.n24q02m.com/servers/mnemo-mcp/setup/:
- Setup-- install methods for Claude Code, Codex, Gemini CLI, Cursor, Windsurf, mcp.json
- Modes overview-- stdio / local-relay / remote-relay / remote-oauth
- Multi-user setup-- per-JWT-sub credential model
Install with AI agent-- paste this to your AI coding agent:
Install MCP servermnemo-mcpfollowing the steps athttps://raw.githubusercontent.com/n24q02m/claude-plugins/main/plugins/mnemo-mcp/setup-with-agent.md
mnemo-mcp is packaged forSmithery-- install or run it straight from the registry. It starts over stdio viauvx mnemo-mcpwith no configuration required to launch; credentials are configured at runtime through the server's own config flow (seeDocumentation). The published start command lives insmithery.yaml.
15 MCP tools, 17 memory actions. The memory surface is exposed both as 11 specialized single-purpose tools and a deprecated legacymemorydispatcher (same actions), plusconfig,help, andconfig__open_relay:
Plugin trinity (Claude Code marketplace install):
- Graceful fallbacks-- Cloud → Local embedding, no cross-mode fallback
- Sync token security-- OAuth tokens stored at~/.mnemo-mcp/tokens/with 600 permissions
- Input validation-- Sync provider, folder, remote validated against allowlists
- Error sanitization-- No credentials in error messages
git clone https://github.com/n24q02m/mnemo-mcp.git cd mnemo-mcp uv sync uv run mnemo-mcp
Themnemo-mcpconsole script both starts the server and exposes a few one-shot operator subcommands. A bare invocation (or any---prefixed flag) starts the server; a leading subcommand runs an action and exits.
mnemo-mcp # start the stdio server (default transport) mnemo-mcp --http # start the Streamable HTTP server # (also via MCP_TRANSPORT=http or TRANSPORT_MODE=http) mnemo-mcp auth google # authorize Google Drive sync via OAuth mnemo-mcp auth google --client-id <ID> --client-secret <SECRET> # bring-your-own OAuth client mnemo-mcp logout # clear the local Google Drive sync token mnemo-mcp warmup # pre-download the bundled local embedding + rerank model mnemo-mcp config status # report whether stored config exists mnemo-mcp config delete --yes # delete the stored (encrypted) config mnemo-mcp relay status # show the active browser-setup relay session mnemo-mcp relay open # open the relay setup form in a browser mnemo-mcp relay reset # clear relay session state mnemo-mcp doctor # environment diagnostics (Python, backend, store, mode)
Deployed over HTTP, mnemo speaks Streamable HTTP transport and is OAuth-gated. Point any MCP client that supports remote HTTP + OAuth athttps://<your-host>/mcpand authenticate on first connect; each authenticated user gets an isolated per-user credential store (seeTrust Model). To stand up an instance, seeDeploy to Cloudflare.
Run your own mnemo instance serverless on Cloudflare (Containers + D1 + Vectorize + KV).
Prerequisites:a Cloudflare account on theWorkers Paid plan— required for Containers, D1, and Vectorize (the Cloudflare free tier does not include them) — and thewranglerCLI.
- git clone https://github.com/n24q02m/mnemo-mcp && cd mnemo-mcp
- wrangler login
- Provision the storage bindings mnemo uses -- the memories database, the embedding index, and the encrypted credential store:
wrangler d1 create mnemo-memories wrangler vectorize create mnemo-memory-vectors --dimensions 768 --metric cosine wrangler kv namespace create mnemo-kv
wrangler d1 migrations apply mnemo-memories --remote
docker pull ghcr.io/n24q02m/mnemo-mcp:beta docker tag ghcr.io/n24q02m/mnemo-mcp:beta mnemo-mcp:beta wrangler containers push mnemo-mcp:beta # prints registry.cloudflare.com/<ACCOUNT_ID>/mnemo-mcp:beta
wrangler secret put CREDENTIAL_SECRET # per-user vault key (encrypts the cf-kv credential store) wrangler secret put MCP_RELAY_PASSWORD # shared password gating the browser setup form wrangler secret put MCP_DCR_SERVER_SECRET # required once PUBLIC_URL is set (multi-user, per-JWT-sub) wrangler secret put JINA_AI_API_KEY # EMBEDDING_MODELS + RERANK_MODELS (cloud embed / rerank) wrangler secret put GOOGLE_VERTEX_EXPRESS_API_KEY # LLM_MODELS (graph extraction, importance, consolidation)
Storage maps to Cloudflare viaMCP_STORAGE_BACKEND=cf-kv(credentials / tokens, encrypted),MEMORY_DB_BACKEND=cf-d1(the memories database + FTS5 full-text; unset orsqlitekeeps the local SQLite file atDB_PATH), and Vectorize (embeddings, cosine). Embedding and reranking are forced cloud through theEMBEDDING_MODELS/RERANK_MODELSchains (jina_ai/...) so the container never downloads the local Qwen3 ONNX models, and graph / LLM features run through theLLM_MODELSchain (vertex_express/...).
This plugin implementsTC-Local(machine-bound, single trust principal). The mode/storage/encryption breakdown below is the full classification.
The browser setup form has an optionalworkspace usernamefield. Entering the same username always lands you in the same per-subbucket, so your credentials and memories stay reachable across a re-authorization and across devices, instead of being tied to the one-off subject minted for each/authorizeround-trip. Leaving it blank keeps the previous per-authorize behaviour.
Trust boundary: when the form is gated by ashared*MCP_RELAY_PASSWORD, the username is a partition key, not a secret -- anyone who knows that password can type any username and reach that bucket. That is fine for a trusted group; an untrusted multi-tenant deployment needs a per-user secret or delegated OAuth instead.
One-time migration:existing users must re-enter their credentials once after this change. Nothing is deleted; credentials stored under the old random subject are simply no longer addressed.
Local Work Model for AI agents that learns from real outcomes.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.
MCP (Model Context Protocol) server that exposes 70 tools spanning cognitive memory, working memory, sessions, agents, the L0–L3 knowledge hierarchy, orchestration tasks, and training pipelines. The server speaks stdio and is consumed by Claude Desktop, Claude Code, OpenCodex, and any MCP-aware client.
Set up a private AI memory vault in about a minute. No migration, no setup call, no card required.
mem0-mcp-server — exposes Mem0 persistent semantic memory as an MCP HTTP server; supports add/search/read/update/delete operations and semantic search for agent memory.
Personal memory layer for AI assistants. Store, search and recall preferences, decisions and facts — available from any MCP-compatible client.
A living memory that decays, learns, and evolves with your AI.
Hosted MCP memory across Claude Code, Cursor, ChatGPT and any MCP client. Community-hosted instance of the MIT-licensed MemPalace engine. EU-hosted, GDPR-compliant. Free tier with 200 memories.
Long-term memory system for AI agents with semantic search, context management, and multi-format storage.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
