run-llama/semtools

CLI tools for parsing documents and running local semantic search

fastRAG helps you build efficient retrieval-augmented generation pipelines with optimized LLMs and search tools
IntelLabs/fastRAG
lightweight Python tool for website scraping with LLMs
raznem/parsera
AI framework for semantic search, workflows, and large language models
neuml/txtai
LLM-powered CLI for automating software engineering tasks
bytedance/trae-agent
deep research automation with language models, tools, web search, and Python execution
bytedance/deer-flow
LLocalSearch: local search aggregator using LLM agents, runs without external API keys
nilsherzig/LLocalSearch
Structured data extraction for LLMs
shcherbak-ai/contextgem
no-code platform for building LLM APIs and ETL pipelines from unstructured docs
Zipstack/unstract
Python toolkit for running LLMs on sensitive documents locally or via cloud, supports Ollama, OpenAI, Anthropic, with RAG and document intelligence features
amaiya/onprem
Open-source tool for web crawling, scraping, and data extraction for LLMs and AI pipelines
unclecode/crawl4ai