Tools
onefilellm
jimmc414/onefilellm
A command-line aggregator that scrapes repositories, web docs, papers and video transcripts into a single structured file for LLM context.
Topics
Related projects
arxiv-mcp-server3.3kA local MCP server that lets AI assistants search arXiv, read full text and LaTeX by section, and manage citations and alerts.
text-extract-api3.2ktext-extract-api is a FastAPI service that combines OCR engines and Ollama-hosted vision models to convert PDFs, Office files and images into Markdown or structured JSON, including PII anonymization.
markpdfdown2.3kA tool that converts PDFs and images into clean Markdown using multimodal LLMs, available as a CLI, Docker image and desktop app.
arxiv.py1.6karxiv.py is a small Python wrapper around the arXiv API that lets developers search papers by keyword or ID and retrieve metadata, PDFs and source archives.
raglite1.2kA Python toolkit for retrieval-augmented generation with DuckDB or PostgreSQL. It handles document ingestion, hybrid search, reranking, evaluation, and an MCP knowledge-search server for AI assistants.
llm.pdf876A proof-of-concept that embeds a compiled llama.cpp model into a PDF, demonstrating that LLM inference can run entirely inside a PDF file.