Gnosys gives LLMs a centralized brain that survives across sessions and projects. 47+ MCP tools, federated search with scope boosting, user preferences, project briefings, and Dream Mode consolidation. Works with any MCP client.
npm install -g gnosys
copy
A centralized brain with 47+ MCP tools. Sub-10ms reads, federated cross-project search, user preferences, project briefings, and Dream Mode consolidation. No vector databases, no black boxes.
One ~/.gnosys/gnosys.db shared across all projects. 6-table schema with project_id and scope columns. Sub-10ms reads, automatic backups, one-command Obsidian export.
Cross-scope search with tier boosting: current project 1.8x, project 1.5x, user 1.0x, global 0.7x. Recency and reinforcement boosting. Ambiguity detection across projects.
Project, user, and global scopes in one central DB. Project memory stays with code, user preferences follow you everywhere, global knowledge spans the org.
Filter by category, tags, status, author, confidence, dates. Compound lenses combine criteria with AND/OR logic.
Dual-write keeps human-readable .md copies alongside the central DB. View full version history, diff between versions, and non-destructively rollback any memory.
Cross-reference memories with [[wikilinks]]. Build a knowledge graph with backlinks, see connections, find orphaned links.
Feed raw text and an LLM structures it into an atomic memory with title, tags, category, and relevance keywords.
Idle-time consolidation: confidence decay, self-critique, summaries, and relationship discovery. Like biological sleep for your knowledge base.
Import thousands of records from CSV, JSON, or JSONL. LLM-powered ingestion generates keyword clouds automatically. Batch commits, dedup, and resume support.
Central project registry, auto-detection from .git/package.json, project briefings, user preferences, and agent rules generation for Cursor and Claude Code.
Gnosys is an MCP server. Point your AI client at it, and your agent gains persistent memory.
{ "mcpServers": { "gnosys": { "command": "gnosys", "args": ["serve"], "env": { "ANTHROPIC_API_KEY": "sk-..." } } } }
{ "mcpServers": { "gnosys": { "command": "gnosys", "args": ["serve"], "env": { "ANTHROPIC_API_KEY": "sk-..." } } } }
$ claude mcp add gnosys gnosys serve
[mcp.gnosys] type = "local" command = ["gnosys", "serve"] [mcp.gnosys.env] ANTHROPIC_API_KEY = "your-key-here"
{ "mcp": { "gnosys": { "type": "local", "command": ["gnosys", "serve"], "env": { "ANTHROPIC_API_KEY": "your-key-here" } } } }
--- description: Gnosys persistent memory alwaysApply: true --- # Gnosys Memory System ## Retrieve memories - At task start, call gnosys_discover with keywords - Load results with gnosys_read - Trigger on: "recall", "remember when", "what did we decide" ## Write memories - Trigger on: "remember", "memorize", "save this", "don't forget" - Also write on decisions, preferences, specs, post-task findings ## Key Tools gnosys_discover → find memories gnosys_add → write gnosys_read → load content gnosys_update → modify gnosys_hybrid_search → best search gnosys_ask → Q&A with citations … plus 25 more tools (maintain, history, graph, etc.)
# Gnosys Memory This project uses Gnosys for persistent memory via MCP. ## Read first - At task start, call gnosys_discover with keywords - Load results with gnosys_read - On "recall", "remember when", "what did we decide" → search first ## Write automatically - On "remember", "memorize", "save this" → call gnosys_add - Decisions/preferences → commit to decisions/ - Specs → commit BEFORE starting work - After implementation → commit findings ## Key tools | Action | Tool | | Find | gnosys_discover → gnosys_read | | Search | gnosys_hybrid_search, gnosys_ask | | Write | gnosys_add, gnosys_add_structured | | Update | gnosys_update, gnosys_reinforce |
One command: npm install -g gnosys. Zero config needed to start.
Works with Claude Desktop, Cursor, Claude Code, Codex, OpenCode, or any MCP-compatible client on macOS, Linux, or Windows. Just add the server config.
Ask your agent to run gnosys_init in your project. It creates a .gnosys/ directory with git tracking.
Decisions, architecture choices, conventions, requirements — all persisted as atomic markdown files your agent can discover and reference.
SQLite is the source of truth. Markdown files are dual-written as a safety net. Dream Mode consolidates knowledge while you sleep. Export to Obsidian with one command.
Open source, MIT licensed. Built for developers who want their AI to remember what matters.