Runtime-neutral driver for Claude Code, Codex, and ACP. Compatible with Claude Managed Agents (CMA) API.

Programmatic video for coding agents — HTML to video on your laptop. Turn HTML, CSS & data into real MP4s with pluggable render engines, 21 templates, AI soundtrack. Apache-2.0, no per-render fees.…

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

MIT(MI-Terminal): A lightweight TUI and CLI for MiJia. 轻量化的米家设备控制 CLI

Virtual Kubelet is an open source Kubernetes kubelet implementation.

Google's open source distributed agent runtime

s6 overlay for containers (includes execline, s6-linux-utils & a custom init)

A unified framework for building, running, and training general agents at scale.

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Horust is a supervisor / init system written in rust and designed to run inside containers.

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

Rust Developer AI Assistance System — Meta-Problem-Driven Knowledge Indexing

Heuristic Learning Blog Post

Harbor is a framework for running agent evaluations and creating and using RL environments.

“Zero setup” cross compilation and “cross testing” of Rust crates

A Unified Virtual Filesystem For AI Agents

Linux virtual machines, with a focus on running containers

Multimodal RL training framework for diffusion & omni models

Container runtimes on macOS (and Linux) with minimal setup

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。

OCI registry client - managing content like artifacts, images, packages

Inspect: A framework for large language model evaluations

NVIDIA Isaac Sim™ is an open-source application on NVIDIA Omniverse for developing, simulating, and testing AI-driven robots in realistic virtual environments.

Kubernetes controller for GitHub Actions self-hosted runners

Opinionated skills for AI coding agents to create stunning diagrams and visualizations directly in Markdown. These skills extend agent capabilities across diagram generation, data visualization, an…

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

Ongoing research training transformer models at scale

The best-benchmarked open-source AI memory system. And it's free.

A sandboxed POSIX shell with a concurrent JSON-line RPC mode