convez.ai
MCP ServerIntegração & APIsIntermediário
n24q02m

Mnemo MCP — Memória Persistente com Busca Híbrida

n24q02m/mnemo-mcp

Memória persistente para IA com busca híbrida e sincronização de embeddings

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP para memória persistente em IA com recuperação híbrida avançada (FTS5 + sqlite-vec + fusão RRF + reranking cross-encoder + decaimento temporal). Armazena e recupera contexto de conversa com busca semântica e por texto completo integradas, totalmente aberto e sem limites.

Instalação

$npx convez-ai n24q02m/mnemo-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
13
Forks
7
Acompanhando
0
Saúde
100%
Último commit
há 2 dias
Versão
v2.23.0
Issues abertas
1
Contribuidores
8

Casos de uso

  • Manter contexto de longo prazo em agentes Claude
  • Recuperar informações relevantes com busca semântica + full-text
  • Construir bases de conhecimento pessoais para IA
  • Sincronizar embeddings entre diferentes agentes ou sessões

Veredito

Mnemo é uma solução robusta e produção-ready para memória persistente em sistemas IA. A implementação de busca híbrida com reranking é sofisticada e bem testada (SafeSkill 91/100), ideal para agentes que precisam de contexto duradouro e recuperação precisa de informações.

README

A tradução para o português deste README ainda está na fila.

Mnemo MCP Server

mcp-name: io.github.n24q02m/mnemo-mcp

Persistent memory MCP server with hybrid retrieval (FTS5 + sqlite-vec + RRF fusion + cross-encoder rerank + temporal decay) and embedded sync. Open, free, unlimited.

CI codecov PyPI Docker License: MIT SafeSkill 91/100

Python SQLite MCP semantic-release Renovate

ProjectTaglineTag
better-code-review-graphKnowledge graph for token-efficient code reviews -- fixed search, configurabl...MCP
better-email-mcpIMAP/SMTP email server for AI agents -- 6 composite tools with multi-account ...MCP
better-godot-mcpComposite MCP server for Godot Engine -- 17 mega-tools for AI-assisted game d...MCP
better-notion-mcpMarkdown-first Notion API server for AI agents -- 10 composite tools replacin...MCP
better-telegram-mcpMCP server for Telegram with dual-mode support: Bot API (httpx) for quick bot...MCP
claude-pluginsFull documentation: mcp.n24q02m.com — unified docs for all 8 servers + the mc...Marketplace
imagine-mcpProduction-grade MCP server for image and video understanding + generation ac...MCP
jules-task-archiverChrome Extension for bulk operations on Jules tasks via batchexecute API -- a...Tooling
mcp-coreUnified MCP Streamable HTTP 2025-11-25 transport, OAuth 2.1 Authorization Ser...MCP
mnemo-mcpPersistent AI memory with hybrid search and embedded sync. Open, free, unlimi...MCP
qwen3-embedLightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUFLibrary
skretSecrets without the server.CLI
web-coreShared web infrastructure package for search, scraping, HTTP security, and st...Library
wet-mcpOpen-source MCP Server for web search, content extraction, library docs & mul...MCP

Table of contents

Roadmap (current = Phase 1 / v1.x)

PhaseVersionStatusHighlights
Phase 1v1.xShippedTyped memory(action="capture") (6 context_types + dedup) -- RRF (k=60) hybrid fusion + cross-encoder rerank + temporal decay -- importance x recency archive policy + restore -- Alembic migrations -- multi-provider LLM dispatch -- plugin trinity (recall-context + memory-commit skills, SessionStart + opt-in PostToolUse hooks)
Phase 2v1.x+1ShippedLLM-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 3v2.0.0Shipped (BREAKING)Temporal knowledge graph -- bitemporal valid_from / valid_to columns -- entity resolution via embedding KNN -- entity_search / entity_graph / history actions -- KG-aware passport bundle sections -- KG_AUTO_ENABLED opt-in auto-extract on capture

Features

  • Hybrid retrieval -- FTS5 + sqlite-vec, fused via Reciprocal Rank Fusion (k=60), then re-ranked by a cross-encoder chain (qwen3-reranker local -> Jina -> Cohere) 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 multi-provider LLM dispatcher (Gemini > OpenAI > Anthropic > xAI)
  • 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 >=0.9 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).

Comparison vs. peers

Featuremnemo-mcpMem0LettaOpenMemory
Hybrid retrieval (FTS + vec)yes (FTS5 + sqlite-vec + RRF)yespartialyes
Cross-encoder rerank chainyes (qwen3 local + Jina + Cohere)partial (Cohere only)nono
Temporal decay scoringyes (exp half-life)nonono
Importance boost in rankyes (LLM 0.0-1.0)nonono
Soft-archive + restore policyyes (importance x recency)nonono
Self-hostable (single SQLite file)yes (zero ext deps)partial (cloud-first)yes (Postgres)yes (Postgres + Qdrant)
Multi-provider LLM dispatchyes (Gemini/OpenAI/Anthropic/xAI auto-detect)partialyespartial
Plugin trinity (skills + hooks)yes (recall-context + memory-commit)n/an/an/a
Multi-machine syncyes (GDrive bundled OAuth)yes (cloud)n/an/a
E2E-encrypted passport syncyes (AES-256-GCM + Argon2id, S3 + GDrive)nonono
LLM compression on captureyes (multi-provider, ~3x at >=0.90 retention)nonono
Backend-pluggable sync architectureyes (S3 / R2 / B2 / MinIO + GDrive)nonono
Bitemporal valid_from / valid_to queriesyes (as_of time-travel)nopartial (events only)no
Entity resolution via embedding KNNyes (cosine threshold tunable)nonono
Audit trail with state hashesyes (memory_audit table)nonono

Status

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. As of v, the architecture is 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 v+ and follow the current setup docs -- most prior workarounds are no longer needed.

Related plugins from the same author:

All plugins share the same architecture -- install once, learn pattern transfers.

Documentation

Full docs at mcp.n24q02m.com/servers/mnemo-mcp/:

  • 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 server mnemo-mcp following the steps at https://raw.githubusercontent.com/n24q02m/claude-plugins/main/plugins/mnemo-mcp/setup-with-agent.md

Tools

3 MCP tools, 17 memory actions:

ToolActionsDescription
memoryadd, capture, search, list, update, delete, export, import, stats, restore, archived, archive_now, consolidate, compress, entity_search, entity_graph, historyCore 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)
configstatus, sync, set, warmup, setup_sync, setup_status, setup_start, setup_skip, setup_reset, setup_complete, setup_relay, sync_now, export_passport, import_passportServer status, trigger sync, update settings, pre-download embedding model, authenticate sync provider, manage HTTP setup form lifecycle, passport export/import
helptopic="memory" or topic="config"Full documentation for any tool

Plugin trinity (Claude Code marketplace install):

ComponentTriggerPurpose
mnemo:recall-context skillsession start, before significant decisions, "what do I know about X?"Pulls cwd / topic-relevant memories with context_type filtering
mnemo:memory-commit skill"remember this" / "save this" / "ghi nho" / "luu lai"Typed manual capture with context_type decision tree
mnemo:knowledge-audit skillperiodic / "audit memory"Find duplicates, contradictions, stale entries; consolidate
mnemo:session-handoff skillend of sessionCapture decisions / preferences / corrections / conventions / open questions
SessionStart hookevery session initNon-blocking nudge to invoke recall-context
PostToolUse hook (opt-in)CAPTURE_AUTO_ENABLED=trueHint memory-commit after Write/Edit of CLAUDE.md / AGENTS.md / ARCHITECTURE.md / docs/*.md

MCP Resources

URIDescription
mnemo://statsDatabase statistics and server status

MCP Prompts

PromptParametersDescription
save_summarysummaryGenerate prompt to save a conversation summary as memory
recall_contexttopicGenerate prompt to recall relevant memories about a topic

Security

  • 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

Build from Source

git clone https://github.com/n24q02m/mnemo-mcp.git
cd mnemo-mcp
uv sync
uv run mnemo-mcp

Trust Model

This plugin implements TC-Local (machine-bound, single trust principal). See mcp-core/docs/TRUST-MODEL.md for full classification.

ModeStorageEncryptionWho can read your data?
stdio (default)~/.mnemo-mcp/config.jsonAES-GCM, machine-bound keyOnly your OS user (file perm 0600)
HTTP self-hostSame as stdioSameOnly you (admin = user)

License

MIT -- See LICENSE.

Ver o original no GitHub

Bom para

Relacionados