ChengRang

CUA-Lite

AI Platforms Open Source

Berkeley RDI's open-source platform for computer-use agents: Lite.Gym, Lite.Sample and per-model harnesses unify environments, data and training pipelines; 15+ benchmarks plug in directly, VM-free desktop sandboxes ship 30k+ verifiable tasks, and 14 model families are supported for evaluation and training

Open sourceAgentEvaluationCUABenchmarkBerkeley
Visit CUA-Lite

Disclaimer: Review content represents our editorial team's views and experience, not commercial recommendation or investment advice. Product info and pricing may change; refer to official sources.

Overview

In September 2026, Berkeley RDI open-sourced CUA-Lite, an open platform for developing and evaluating computer-use agents, i.e. AI systems that operate desktop software, browsers and mobile apps the way a human would, a track represented by CUA-class models from OpenAI, Anthropic, Qwen and others. Historically this development chain was deeply fragmented: every environment had its own interface and runtime, every supervised dataset its own format, and every model its own action space, prompt format and rollout code, so connecting a model to an environment meant rewriting the same glue again and again. CUA-Lite unifies all three with three standardized abstractions.

Lite.Gym is the unified environment interface that folds 15+ benchmarks such as OSWorld, WebArena, AndroidWorld and WebGym into one reset/step/close loop with a shared screenshot observation and a single GUI action space of click/type on desktop and browser plus tap/swipe on mobile. Lite.Sample is the unified supervised data format; 10+ datasets such as Mind2Web and GUIOdyssey have been preprocessed and published free on Hugging Face. Each model family ships one harness that carries the same code across evaluation, SFT and RL, currently implemented for 14 model families including GPT, Claude, Qwen and Gemini.

The most practical contribution of CUA-Lite is its VM-free desktop sandbox: Docker containers that replicate the OSWorld desktop without requiring hardware virtualization such as /dev/kvm, so they run on any host with Docker, and ship 30k+ verifiable training tasks. Lite.OSWorld runs OSWorld's own tasks and evaluators unchanged. The project publishes a reproducible leaderboard across 13 agents and 325 tasks, with gpt-5.5 leading at 72.3% and Qwen3.5-27B first among open models at 46.2%.

Key Features

Use Cases

Pros

Pricing

Fully open source and free; datasets are publicly downloadable on Hugging Face, and the evaluation environments and model adapters are open-source components.

Summary

CUA-Lite is an open platform for computer-use agents from Berkeley RDI. Its three abstractions, Lite.Gym, Lite.Sample and per-model harnesses, unify the environment, data and training pipeline so that any model can be plugged into any benchmark without rewriting code. The VM-free desktop sandbox with 30k+ verifiable tasks is what sets it apart from similar open-source projects, making it well suited for research institutions and developers who want to evaluate, fine-tune or reinforce CUA agents.

Category
AI Platforms
Pricing
Open Source
Tags
Open source · Agent · Evaluation

Related Tools