Enables syncing memories across machines via Google Drive as a storage backend for encrypted passport sync.
Supports MinIO as a storage backend for encrypted passport sync, allowing self-hosted S3-compatible storage.
Allows using OpenAI models for embedding, reranking, and LLM tasks as an alternative to the built-in local models.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Mnemo MCP remember that I prefer dark mode in my code editor"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-name: io.github.n24q02m/mnemo-mcp
Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.
Project | Tagline | Tag |
Knowledge graph for token-efficient code reviews -- semantic search and call-... | MCP | |
IMAP/SMTP email for AI agents -- read, send, organize folders, and manage att... | MCP | |
Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted g... | MCP | |
Markdown-first Notion for AI agents -- pages, databases, blocks, and comments... | MCP | |
Telegram for AI agents -- messages, chats, media, and contacts across both bo... | MCP | |
Claude Code plugin marketplace for the n24q02m MCP servers -- install web sea... | Marketplace | |
Image and video understanding + generation for AI agents -- across Gemini, Op... | MCP | |
Chrome Extension for bulk operations on Jules tasks via batchexecute API -- a... | Tooling | |
Shared foundation for building MCP servers -- Streamable HTTP transport, OAut... | MCP | |
Persistent AI memory with hybrid search and embedded sync. Open, free, unlimi... | MCP | |
Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF | Library | |
Secrets without the server. | CLI | |
TACET: a self-distilling neuro-symbolic cascade that amortises LLM cost in kn... | Tooling | |
Shared web infrastructure package for search, scraping, HTTP security, and st... | Library | |
Open-source MCP server for AI agents: web search, content extraction, and lib... | MCP |
Related MCP server: mcp-local-memory
All three phases below have shipped. The temporal knowledge graph (Phase 3) is the current major line (v2.x).
Phase | Version | Status | Highlights |
Phase 1 | v1.x | Shipped | Typed |
Phase 2 | v1.x | Shipped | LLM-driven compression of older memories + Passport sync (encrypted import/export bundle for cross-machine bootstrap) -- AES-256-GCM + Argon2id, S3 / R2 / B2 / MinIO + GDrive backends, delta-sync with LWW per row |
Phase 3 | v2.x | Shipped (BREAKING) | Temporal knowledge graph -- bitemporal |
Hybrid retrieval -- FTS5 + sqlite-vec, 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 when recency_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-commit skills and SessionStart + opt-in PostToolUse hooks (see docs/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 >=0.90 fact retention; graceful skip when no provider configured (see docs/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 (see docs/passport.md). Bootstrap via the passport-bootstrap skill.
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_audit table with prev/new state hashes) + new actions (entity_search / entity_graph / history) + opt-in KG_AUTO_ENABLED auto-extract on capture. BREAKING for clients that called memory.get expecting historical-inclusive results: pass as_of for time-travel; default now filters to current-state (valid_to IS NULL).
# Method 1 (default): plugin install via Claude Code
/plugin marketplace add n24q02m/claude-plugins
/plugin install mnemo-mcp@n24q02m-plugins
# Method 1 (CLI): direct uvx invocation (zero config -- runs on the built-in local model)
claude mcp add mnemo -- uvx mnemo-mcp
# Method 3 (HTTP / multi-device / multi-user)
docker run -d --name mnemo-mcp-http -p 8085:8080 \
-v mnemo-data:/data -e MCP_TRANSPORT=http \
-e PUBLIC_URL=https://mnemo.example.com \
n24q02m/mnemo-mcp:latestNo API keys are required: with no provider keys set, mnemo runs fully offline on the bundled local Qwen3 ONNX embedding + reranker. Add cloud provider keys only to switch embedding / rerank / LLM onto a hosted model (see Configuration).
Full setup matrices live at the canonical docs site mcp.n24q02m.com/servers/mnemo-mcp/setup/ and the paste-to-agent snippet at claude-plugins/plugins/mnemo-mcp/setup-with-agent.md.
All settings are plain environment variables (no prefix). Everything is optional -- mnemo runs zero-config on the local model. The most common knobs:
Embedding, reranking, and LLM features each take an ordered, comma-separated chain of
provider/model entries (tried in order, litellm fallback). Leave a chain empty to use
the bundled local model (embedding / rerank) or to disable the feature (LLM).
Env var | Default | Purpose |
| (empty -> local Qwen3 ONNX) | Embedding chain, e.g. |
| (empty -> local Qwen3 cross-encoder) | Rerank chain, e.g. |
| (built-in cloud chain) | LLM chain for graph extraction / importance / compression; empty disables those features |
|
| Embedding dimensions ( |
Provider is inferred from the model prefix; supply each provider's key via the litellm
<PROVIDER>_API_KEY convention:
model prefix | key env var | get it at |
|
| jina.ai/api-dashboard |
|
| aistudio.google.com/apikey |
|
| platform.openai.com/api-keys |
|
| dashboard.cohere.com/api-keys |
Any other litellm provider works via env passthrough; see
https://docs.litellm.ai/docs/providers/<provider> for its <PROVIDER>_API_KEY name.
Custom OpenAI-compatible endpoints (SSRF-guarded): LLM_API_BASE, EMBEDDING_API_BASE,
RERANK_API_BASE.
Changing the embedding model changes the vector space. A safe-by-default guard blocks boot on mismatch; set
REINDEX_ON_MODEL_CHANGE=trueto re-embed.
Env var | Default | Purpose |
|
| SQLite database path (also accepts |
|
| Enable Google Drive multi-machine sync |
| (none) | OAuth client ID required for sync |
|
| Google Drive folder name |
|
| Auto-sync interval in seconds ( |
|
| Enable reranking of fused results |
|
| Number of reranked results to keep |
|
| Enable importance x recency soft-archive sweeps |
|
| Age before a memory is eligible for archive |
|
| Similarity above which a new memory is a duplicate |
|
| Half-life for temporal decay scoring |
|
| Auto-extract entities + relations on capture |
|
| Log verbosity |
{
"mcpServers": {
"mnemo": {
"command": "uvx",
"args": ["mnemo-mcp"],
"env": {
"EMBEDDING_MODELS": "jina_ai/jina-embeddings-v5-text-small,gemini/gemini-embedding-001",
"RERANK_MODELS": "jina_ai/jina-reranker-v3",
"LLM_MODELS": "gemini/gemini-3-flash-preview",
"JINA_AI_API_KEY": "jina_xxx",
"GEMINI_API_KEY": "AIza_xxx"
}
}
}
}Feature | mnemo-mcp | Mem0 | Letta | OpenMemory |
Hybrid retrieval (FTS + vec) | yes (FTS5 + sqlite-vec + RRF) | yes | partial | yes |
Cross-encoder rerank chain | yes (qwen3 local + Jina + Cohere) | partial (Cohere only) | no | no |
Temporal decay scoring | yes (exp half-life) | no | no | no |
Importance boost in rank | yes (LLM 0.0-1.0) | no | no | no |
Soft-archive + restore policy | yes (importance x recency) | no | no | no |
Self-hostable (single SQLite file) | yes (zero ext deps) | partial (cloud-first) | yes (Postgres) | yes (Postgres + Qdrant) |
Multi-provider LLM dispatch | yes ( | partial | yes | partial |
Plugin trinity (skills + hooks) | yes (recall-context + memory-commit) | n/a | n/a | n/a |
Multi-machine sync | yes (GDrive bundled OAuth) | yes (cloud) | n/a | n/a |
E2E-encrypted passport sync | yes (AES-256-GCM + Argon2id, S3 + GDrive) | no | no | no |
LLM compression on capture | yes (multi-provider, ~3x at >=0.90 retention) | no | no | no |
Backend-pluggable sync architecture | yes (S3 / R2 / B2 / MinIO + GDrive) | no | no | no |
Bitemporal | yes ( | no | partial (events only) | no |
Entity resolution via embedding KNN | yes (cosine threshold tunable) | no | no | no |
Audit trail with state hashes | yes ( | no | no | no |
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 current setup docs -- most prior workarounds are no longer needed.
Related plugins from the same author:
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 at mcp.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
In-repo references:
docs/ARCHITECTURE.md -- storage layout, embedding / rerank dispatch, knowledge graph, plugin trinity
docs/compression.md -- LLM compression pipeline
docs/passport.md -- encrypted passport sync (S3 / GDrive backends)
docs/BENCHMARKS.md -- retrieval quality + latency metrics
Install with AI agent -- paste this to your AI coding agent:
Install MCP server
mnemo-mcpfollowing the steps at https://raw.githubusercontent.com/n24q02m/claude-plugins/main/plugins/mnemo-mcp/setup-with-agent.md
15 MCP tools, 17 memory actions. The memory surface is exposed both as 11 specialized single-purpose tools and a legacy memory dispatcher (same actions), plus config, help, and config__open_relay:
Tool | Actions | Description |
| (one action each) | Specialized single-purpose memory tools -- the recommended surface |
|
| Core CRUD + typed capture (6 context_types) + hybrid search (RRF + rerank + temporal decay) + import/export + soft-archive + restore + on-demand archive sweep + LLM consolidation + LLM compression + temporal KG (entity search / graph / history) |
|
| Server status, trigger sync, update settings, pre-download embedding model, authenticate sync provider, manage HTTP setup form lifecycle, passport export/import |
|
| Full documentation for any tool |
| (HTTP relay mode) | Open the zero-config relay setup form (registered via mcp-core) |
Plugin trinity (Claude Code marketplace install):
Component | Trigger | Purpose |
| session start, before significant decisions, "what do I know about X?" | Pulls cwd / topic-relevant memories with |
| "remember this" / "save this" / "ghi nho" / "luu lai" | Typed manual capture with |
| periodic / "audit memory" | Find duplicates, contradictions, stale entries; consolidate |
| end of session | Capture decisions / preferences / corrections / conventions / open questions |
SessionStart hook | every session init | Non-blocking nudge to invoke |
PostToolUse hook (opt-in) |
| Hint |
URI | Description |
| Database statistics and server status |
Prompt | Parameters | Description |
|
| Generate prompt to save a conversation summary as memory |
|
| Generate prompt to recall relevant memories about a topic |
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-mcpThis plugin implements TC-Local (machine-bound, single trust principal). The mode/storage/encryption breakdown below is the full classification.
Mode | Credentials | Memory data | Who can read your data? |
stdio (default) | Read from environment variables (no credential file written) | Local SQLite at | Only your OS user |
HTTP self-host (single user) | Encrypted | Local SQLite (same host) | Only you (admin = user) |
HTTP multi-user remote ( | Per-JWT- | Per- | Only the authenticated user (per- |
Passport sync bundles are always end-to-end encrypted (AES-256-GCM + Argon2id); backends never see plaintext.
MIT -- See LICENSE.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Persistent memory for AI agents. Search, store, and recall across sessions.
Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/expandingideas-ai/Mnemo-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server