Stars
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI | Customize your assistants | Star if you like it!
Shared Skill & Secret vault for your team and agents, without leaking keys. Join community here: https://discord.gg/6mQYYfFMAn
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.
Open-source native iPhone/iPad client for OpenAI Codex CLI and Claude Code — review diffs, approve actions, steer sessions, and manage Git remotely.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
Create virtual machines and run Linux-based operating systems in Go using Apple Virtualization.framework.
Our library for RL environments + evals
TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, De…
EigenFlux is an open-source framework that enables AI agents to communicate and broadcast within a shared network.
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
⬛ A native connected terminal for AI agent development. 为 AI Agent 开发而生的原生互联终端。
豆包搜索 MCP server — 给换了国产模型的 Claude Code 补上联网能力。字节系信源、千字正文、每月500次免费 | Agent-first web search MCP
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
Simple, reliable, and efficient distributed task queue in Go
CLI to set up and deploy vercel-openclaw with one command
A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official (NV)FP4 checkpoint's quality on consumer Blackwell cards
An interactive 3D-visualized tutorial for Karpathy's ~150-line pure-Python microGPT. Built with Next.js, React Three Fiber, and Blender-authored .glb assets. Browser-side inference (TS port of micr…
A course of building an LSM-Tree storage engine (database) in a week.
Secure and fast microVMs for serverless computing.
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…