The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS

MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

Replace port numbers with stable, named local URLs. For humans and agents.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

AI Agent Framework, the Pydantic way

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Clean, filter and sample URLs to optimize data collection – Python & command-line – Deduplication, spam, content and language filters

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Shannon is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before t…

Public repository for Agent Skills

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Anthony Fu's curated collection of agent skills.

Autonomous AI development loop for Claude Code with intelligent exit detection

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Fast and accurate AI powered file content types detection

Open-source inference server and production cluster for all the models your agent needs.

Get the main content of any page as Markdown.

The absolute trainer to light up AI agents.

A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.

A collection of datasets and other resources for legal text processing.

High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts stru…

multiple GNOME terminals in one window

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

An open-source visual programming environment for battle-testing prompts to LLMs.