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.

36
/ 100
Emerging

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.

No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 9 / 25
Community 13 / 25

How are scores calculated?

Stars

7

Forks

2

Language

Rust

License

Apache-2.0

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.