playwright for windows computer use

Build AI applications that can see, hear, and speak using your screens, microphones, and cameras as inputs.

📚 Benchmark your browser agent on ~2.5k READ and ACTION based tasks

Cocommit is a command-line tool that works with your HEAD commit and leverages an LLM of your choice to enhance commit quality.

Agent S: an open agentic framework that uses computers like a human

Towards Human-Sounding Speech

A fully customizable and self-hosted sandboxing solution for AI agent code execution and computer use. It features out-of-the-box support for backtracking, a simple REST API and Python SDK, automat…

Rust SDK for the Model Context Protocol (MCP)

This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities

WhatsApp MCP server

Go library for the WhatsApp web multidevice API

native OCR for MacOS, Windows, Linux

Free, simple, fast interactive diagrams for any GitHub repository

Swift wrapper for accessibility clients

A Model Context Protocol (MCP) server for Windows desktop automation using AutoIt.

a tool for taking screenshots automatically in the background and then searching for words in them

24/7 local AI screen & mic recording. Build AI apps that have the full context. Works with Ollama. Alternative to Rewind.ai. Open. Secure. You own your data. Rust.

World's first AI meeting copilot → The Invisible Companion for Work + Life

A single API for all your integrations.

Building a modern alternative to Salesforce, powered by the community.

Odoo. Open Source Apps To Grow Your Business.

Make Mac apps accessible for AI agents

An intuitive spreadsheet-like interface that lets users of all technical skill levels view, edit, query, and collaborate on Postgres data directly—100% open source and self hosted, with native Post…

[ICLR Workshop 2025] An official source code for paper "GuardReasoner: Towards Reasoning-based LLM Safeguards".

Code for Parametric RAG, SIGIR 2025 Full Paper

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Examples and guides for using the Gemini API

Screen2Vec is a new self-supervised technique for generating more comprehensive semantic embeddings of GUI screens and components using their textual content, visual design and layout patterns, and…

Rust library for generating vector embeddings, reranking. Re-write of qdrant/fastembed.