Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
- apple
- cua
- lume
- macos
107,098 visible repositories in the index
1–20 of 20 · Most stars
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
The World's First Virtual Terminal for AI Agents
A security-focused library OS supporting kernel- and user-mode execution
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
chroot, mount --bind, and binfmt_misc without privilege/setup for Linux
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents
Run any Linux process in a secure, unprivileged sandbox using Landlock. Think firejail, but lightweight, user-friendly, and baked into the kernel.
Sandbox your local AI agents so they can read/write only what they need
Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation.
E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.
Sandboxes for coding agents, CI runners and RL training
Hermit launches linux x86_64 programs in a special, hermetically isolated sandbox to control their execution. Hermit translates normal, nondeterministic behavior, into deterministic, repeatable behavior. This can be used for various applications, including replay-debugging, reproducible artifacts, chaos mode concurrency testing and bug analysis.
A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by a Claude Code–based agent.
NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架,集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体,兼具高扩展性、多模态交互、实时状态推送和自动化运行能力。项目支持 QQ、Discord、Telegram、Minecraft、BilibiliLive、WeChat、Email、SSE(SDK) 等多种平台接入,应用于构建高智能聊天机器人,可扩展为具备代码执行、工具调用、插件协作和复杂任务处理能力的通用 Agent 系统
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.
Easy to use unprivileged Linux container packed into a single portable executable
Fast, isolated machines for AI agents and dev teams, self-hosted in your own cloud. Use them as agent sandboxes, dev environments or servers, on GCP, AWS or bare metal.