Venere-Labs/ragfs
A FUSE semantic filesystem for LLM/AI AgentsAgentic FUSE filesystem for LLM agents. Structured file operations with JSON feedback, audit logging, undo support, and semantic search.
Implements vector embeddings entirely offline using Candle's `gte-small` model, with syntax-aware code chunking via tree-sitter and multimodal support (text, PDF, images). Exposes agent operations through special `.ops/`, `.safety/`, and `.semantic/` FUSE directories for JSON-structured file interactions, undo/audit trails, and auto-organization. Includes MCP server integration for Claude Desktop and Python bindings via PyO3, with LanceDB for hybrid vector+full-text search across 40+ file formats.
Stars
7
Forks
2
Language
Rust
License
Apache-2.0
Category
Last pushed
Jan 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Venere-Labs/ragfs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
dappros/rag_demos
Examples of RAG (Retrieval-Augmented Generation) with Ethora, LangChain, and OpenAI. Build...
beauseant/patchwork
pAtChWoRK is system that combines traditional NLP and LLMs to extract, enrich, and index public...
varun29ankuS/shodhRAG
Local-first AI assistant with RAG — built with Rust, Tauri, and LanceDB
davicqueiroz/claude-rag-skills
🛠️ Build, audit, and optimize RAG systems efficiently with professional skills for Claude Code....
Krish-afk-bot/narrative-consistency-verifier
Constraint-based AI system for verifying character backstory consistency in long-form novels...