Stars
An agent runtime and tool protocol for principled agent concurrency
An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 50 other agents.
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
A Virtual Machine Monitor for modern Cloud workloads. Features include CPU, memory and device hotplug, support for running Windows and Linux guests, device offload with vhost-user and a minimal com…
Writing a container in a few lines of Go code, as seen at DockerCon 2017 and on O'Reilly Safari
Manage secure microVMs — one command from zero to secure sessions, locally and remotely.
A persistent, policy-guarded Playwright browser for AI agents — network policy, encrypted credential vault, proof screenshots, and CAPTCHA solving.
DeepSeek Harness: Everything is a Plugin.
A Programming Paradigm for Spatiotemporal Composability
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
RL environments + evals for AI agents. Define once, train anything.
Standards for defining and evaluating agent behavior
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Agent S: the state-of-the-art open source computer use agents
Review-first terminal diff viewer for agentic coders
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A PyTorch native platform for training generative AI models