matryca-plumber
Active·★ 33·Apache-2.0·Updated 2026-05-29
★ Trending★ RAG / Knowledge Base★ Memory & Context
Bringing Andrej Karpathy's LLM Wiki to the Outliner Paradigm. Turn any AI Agent into a spatial Knowledge Architect using Logseq's atomic nodes.
Matryca is a headless MCP server and CLI that turns a local Logseq graph into an agentic workspace. It operates without network APIs or background desktop app, using atomic AST writes and X-Ray token compression. It provides spatial intelligence, sandboxed privacy, and zero-database lexical engine.
#agentic-memory#ai-agents#andrej-karpathy#autonomous-agents#knowledge-graph#llm#llm-wiki#llm-wiki-karpathy
01
Features
01AST Spatial Intelligence
02100% Headless & Local-First
03X-Ray Token Economy
04Sandboxed Privacy
05Agent-Native CLI
02
Compatibility
Python
Python 3.12+
Verified via docs
macOS
macOS via LaunchAgent
Verified via docs
Linux
Linux via systemd
Verified via docs
Claude Desktop
MCP host
Verified via docs
03
Quick start
1
$ git clone https://github.com/MarcoPorcellato/matryca-logseq-llm-wiki.git
2
$ cd matryca-logseq-llm-wiki
3
$ make install
04
Use cases
↳Privacy-preserving AI knowledge management
↳Agentic writing and refactoring of Logseq pages
↳Local-first automation with MCP clients like Claude Desktop
05
Alternatives
letta★ 23.0k
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
DesktopCommanderMCP★ 6.1k
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
agents-best-practices★ 1.1k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
awesome-claude★ 250
HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
initrunner★ 38
Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon
Related searches
Comments
Log in to leave a comment
- JJesse ThompsonMay 25, 2026
Karpathy's LLM Wiki concept applied to an outliner paradigm is a creative combination.
- HHarley GarciaApr 5, 2026
Good for turning AI agents into structured knowledge organizers.
- DDylan BrownMar 18, 2026
Outliner format makes knowledge hierarchical and navigable, not flat.
- SSkyler LewisMar 1, 2026
Works with standard AI agent frameworks without modification.