run-llama/semtools
Semantic search and document parsing tools for the command line
Built in Rust for high performance, it provides document parsing via LlamaParse, local semantic search using multilingual embeddings with configurable distance thresholds, and an AI agent interface that integrates with OpenAI-compatible APIs. The tool embraces Unix philosophy with stdin/stdout piping, workspace-based caching for large document collections, and multi-format support (PDF, DOCX, PPTX). Commands compose naturally: parse documents to markdown, search results with per-line context, or ask questions with the agent reading from both files and stdin.
1,697 stars. Actively maintained with 1 commit in the last 30 days.
Stars
1,697
Forks
124
Language
Rust
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/run-llama/semtools"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
winkjs/wink-bm25-text-search
Fast Full Text Search based on BM25
Hamza5/file-brain
Smart local file search app that understands your files
Dicklesworthstone/frankensearch
Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M,...
OpenConceptLab/oclmap
OCL Mapper (beta): an open-source AI-supported terminology mapping solution for the global community
filippostanghellini/DocFinder
DocFinder is a local-first indexing and searching documents using semantic embeddings stored in...