computer-use

Autonomous Android and computer use using any LLM (local or remote)

Open-source benchmark for browser AI agents on daily tasks.

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas, Perplexity Comet, Dia and Microsoft CoPilot Edge Browser

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

A general AI agent framework that can be adapted to various tasks and environments.

Your computer was paying attention the whole time. 14-modality capture. Proactive intelligence. Computer-use training data. Native macOS. All on-device. Open source.

Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ tools. Companion-first alternative to Hermes Agent / OpenClaw / Claude Code.

Open-source, local-first desktop AI agent for voice, gesture, gaze, browser and system automation with permission gates and verification.

Mark web pages for use with vision-language models

Self-hosted voice assistant. Speak to your computer: it answers aloud, types your dictation, and operates your apps.

macOS computer-use agent in the notch. Long-press, talk, Claude drives the mouse.

Apache-2.0, model-agnostic macOS agent: bring your own model to deliver verified code, docs, slides, and computer actions.

AOI: a model-agnostic perception layer giving computer-use agents adaptive video + audio perception with zero retraining, plus DynaCU-Bench (100 dynamic browser tasks). Paper + benchmark + code.