convez.ai
MCP ServerIntegração & APIsIntermediário
proticom

Gnosys — Memória Persistente para Agentes IA

proticom/gnosys

Memória persistente centralizada com busca federada para agentes IA

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que fornece memória persistente para agentes IA, armazenada em SQLite local com buscas híbridas (keyword + semantic) em sub-10ms. Funciona como servidor MCP, CLI e se integra nativamente com Claude, Cursor e outros clientes, permitindo que agentes mantenham contexto através de sessões, projetos e máquinas.

Instalação

$npx convez-ai proticom/gnosys

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
5
Forks
1
Acompanhando
0
Saúde
100%
Último commit
há 3 dias
Versão
v7.0.0
Issues abertas
12
Contribuidores
2

Casos de uso

  • Manter contexto de projeto através de múltiplas sessões de desenvolvimento
  • Recuperar decisões arquiteturais e documentação relevante em tempo real
  • Consolidar conhecimento com análise de confiança e relacionamentos (Dream Mode)
  • Sincronizar memória entre máquinas de desenvolvimento diferentes

Veredito

Gnosys resolve um problema real: agentes IA perdem contexto sem memória estruturada. A implementação é sólida (SQLite local, sem dependências cloud), bem documentada e oferece integração MCP nativa. Ideal para quem quer contexto persistente sem overhead de vector DBs externos.

README

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


Gnosys — One Brain. Zero Context Bloat.

Gnosys gives AI agents persistent memory that survives across sessions, projects, and machines.

The central brain is a single SQLite database at ~/.gnosys/gnosys.db with sub-10ms reads — no vector DBs, no black boxes, no external services. Federated search ranks results across project, user, and global scopes. It runs as a CLI and as a full MCP server that drops straight into Claude Code, Claude Desktop (Chat / Cowork / Code), Cursor, Codex, Gemini CLI, Antigravity, Grok Build, or any MCP client. When you want a human-readable view, gnosys export regenerates a full Obsidian vault on demand.

Install

Requires Node.js ≥ 20.12.

npm install -g gnosys
gnosys setup          # configures provider, API key, and your IDE/agent

Optional native deps. Gnosys auto-installs better-sqlite3 (the SQLite engine) and @huggingface/transformers (local embeddings). If your environment lacks build tools and either fails to install, run npm install better-sqlite3 @huggingface/transformers — or configure an external embedding API. Both degrade gracefully if absent.

Quick start

gnosys setup ides                                        # wire MCP into your IDEs (once)
cd your-project
gnosys init                                              # register the project
gnosys add "We chose PostgreSQL over MySQL for JSON support"
gnosys recall "database selection"                       # what's relevant right now
gnosys chat                                              # memory-aware terminal chat

That's the 60-second tour. Everything else lives on gnosys.ai.

What you get

  • Central brain — one ~/.gnosys/gnosys.db unifies every project (project / user / global scopes). Sub-10ms reads, SQLite as the sole source of truth.
  • Federated search — tier-boosted hybrid (FTS5 keyword + semantic) search across scopes, with recency and reinforcement.
  • MCP server — gnosys serve exposes 50+ memory tools to any MCP client. Sandbox-first runtime keeps context cost near zero.
  • Web Knowledge Base — gnosys web build turns any site into a searchable index for serverless chatbots. Zero runtime deps.
  • Dream Mode — idle-time consolidation: confidence decay, summaries, relationship discovery. Never deletes — only suggests.
  • Multi-machine sync — share your brain across machines; conflict detection with skip-and-flag resolution.
  • Obsidian export — gnosys export regenerates a full vault with frontmatter, [[wikilinks]], and graph data.

MCP Tool Reference

All tools are exposed over stdio and HTTP transports. Many tools accept an optional projectRoot parameter to target a specific project store.

This package installs two binaries:

  • gnosys — the CLI. gnosys serve starts the MCP server (stdio by default, --transport http for the central-server topology). gnosys setup ides wires gnosys-mcp into your IDE/agent configs.
  • gnosys-mcp — a direct alias for the MCP stdio server entry, for MCP clients that prefer to spawn the server binary directly (e.g. npx -y gnosys-mcp). Equivalent to gnosys serve.
ToolDescription
gnosys_discoverDiscover relevant memories by describing what you're working on.
gnosys_readRead a specific memory.
gnosys_searchSearch memories by keyword across all stores.
gnosys_listList memories across all stores, optionally filtered by category, tag, or store layer.
gnosys_addAdd a new memory.
gnosys_add_structuredAdd a memory with structured input (no LLM needed).
gnosys_tagsList all tags in the registry, grouped by category.
gnosys_tags_addAdd a new tag to the registry.
gnosys_reinforceSignal whether a memory was useful.
gnosys_initInitialize Gnosys in a project directory.
gnosys_migrateMigrate a Gnosys store (.gnosys/) from one directory to another.
gnosys_updateUpdate an existing memory's frontmatter and/or content.
gnosys_staleFind memories that haven't been modified or reviewed within a given number of days.
gnosys_commit_contextPre-compaction memory sweep.
gnosys_historyView audit history for a memory.
gnosys_lensFiltered view of memories.
gnosys_timelineView memory creation and modification activity over time.
gnosys_statsSummary statistics across all memories — totals by category, status, author, authority, average confidence, and date ranges.
gnosys_linksShow wikilinks for a specific memory — outgoing [[links]] and backlinks from other memories.
gnosys_graphShow the full cross-reference graph across all memories.
gnosys_bootstrapBatch-import existing documents from a directory into the memory store.
gnosys_importBulk import structured data (CSV, JSON, JSONL) into Gnosys memories.
gnosys_hybrid_searchSearch memories using hybrid keyword + semantic search with Reciprocal Rank Fusion.
gnosys_semantic_searchSearch memories using semantic similarity only (no keyword matching).
gnosys_reindexRebuild all semantic embeddings from every memory file.
gnosys_askAsk a natural-language question and get a synthesized answer with citations from the entire vault.
gnosys_maintainRun vault maintenance: detect duplicate memories, apply confidence decay, consolidate similar memories.
gnosys_dearchiveForce-dearchive memories from archive.db back to active.
gnosys_reindex_graphBuild or rebuild the wikilink graph (.gnosys/graph.json).
gnosys_dreamRun a Dream Mode cycle — idle-time consolidation that decays confidence, generates category summaries, discovers relationships, and creates review suggestions.
gnosys_exportExport gnosys.db to Obsidian-compatible vault — atomic Markdown files with YAML frontmatter, [[wikilinks]], category summaries, and relationship graph.
gnosys_dashboardShow the Gnosys system dashboard: memory counts, maintenance health, graph stats, LLM provider status.
gnosys_storesDebug tool — lists all detected Gnosys stores across registered projects, MCP workspace roots, cwd, and environment variables.
gnosys_recallFast memory recall — inject relevant memories as context.
gnosys_auditView the audit trail of all memory operations (reads, writes, reinforcements, dearchives, maintenance).
gnosys_preference_setSet a user preference.
gnosys_preference_getGet a user preference by key, or list all preferences.
gnosys_preference_deleteDelete a user preference by key.
gnosys_syncGet the current user preferences + project conventions formatted as a GNOSYS:START/GNOSYS:END block.
gnosys_federated_searchSearch across all scopes (project → user → global) with tier boosting.
gnosys_detect_ambiguityCheck if a query matches memories in multiple projects.
gnosys_briefingGenerate a project briefing — a summary of memory state, categories, recent activity, and top tags.
gnosys_portfolioPortfolio dashboard — shows all registered projects with memory counts, categories, status snapshots, roadmap items, and recent activity.
gnosys_remote_statusCheck the status of remote sync (multi-machine).
gnosys_remote_pushPush local memory changes to the remote (NAS) database.
gnosys_remote_pullPull remote memory changes to the local database.
gnosys_remote_resolveResolve a sync conflict by choosing which version to keep.
gnosys_update_statusGet the prompt/template for writing a dashboard-compatible status memory for this project.
gnosys_working_setGet the implicit working set — recently modified memories for the current project.
gnosys_ingest_fileIngest a file (PDF, DOCX, TXT, MD) into Gnosys memory.

Documentation

Full docs & guideshttps://gnosys.ai
Complete CLI + MCP referencehttps://gnosys.ai/guide.html
ChangelogCHANGELOG.md
ContributingCONTRIBUTING.md
Security policySECURITY.md
Report a bug / request a featureGitHub Issues

License

MIT © Proticom. See LICENSE.

Ver o original no GitHub

Bom para

Relacionados