Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
- apple
- cua
- lume
- macos
47,133 repositories indexed
1–10 of 10 · Most stars
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
A command-line benchmarking tool
Code-first platform for workflows, apps and AI agents, on the fastest self-hostable orchestrator (benchmarked against Airflow, Prefect and Temporal). Business teams build with AI, engineers control what ships. Open-source alternative to Lovable, Retool and n8n.
TranslatedOhayou (おはよう, "good morning"), HTTP load generator, inspired by rakyll/hey with tui animation.
TranslatedOpen-source AI API relay benchmark, rankings & switcher for Claude Code / Codex: measured availability, latency and price
Scriptable local traffic workbench for inspecting, intercepting, replaying, and rewriting HTTP/HTTPS and WebSocket traffic.
🐰 Bencher - Continuous Benchmarking
TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".
An esoteric programming language built to break LLMs and coding agents.
Create, Read, Update and Delete benchmarks at crude hardware speeds for embedded engines and database servers, the Rust successor to UCSB & YCSB