Your autonomous engineering team in a CLI. Point Zeroshot at a GitHub issue, walk away, and return to production-grade code. Supports Claude Code, OpenAI Codex, and Gemini CLI.

Undetected version of the Playwright testing and automation library.

Utility to Automatically Link URLs, Email Addresses, Phone Numbers, Twitter handles, and Hashtags in a given block of text/HTML

Give any LLM its own display. Send JSON, get beautiful interactive UI.

Collection of Model Context Protocol servers for AI coding tools (Linear, Postgres, Notion)

Screen Recording and sharing

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Why is this running?

The open source coding agent.

Add a sound meaning to your d3 graphs to help vision impaired people

Browser automation for AI agents and humans

Press shortcut → speak → get text. Free and open source. More local-first apps soon ❤️

LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.

Generate clips from a video or youtube link

Deterministic skills-based browser agent

🔒 Zero-trust proxy that monitors and controls what your browser automation can access

Intent-based UI automation that runs locally. Record real workflows, generate reusable scripts, and safely use local credentials and files.

Open-source, vision-first browser agent

⚙️ Create and run workflows (RPA 2.0)

A Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities. This agent enables Claude to interact with web content, manipulate DOM eleme…

AI Browser Automation

Open-source platform to build and deploy AI agent workflows.

🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.

The specification for the Universal Tool Calling Protocol

Screen recording sharing for absolutely everyone.

An Open Source Cross-platform Screen Recorder for Everyone