Distributed agent coordination platform where agents live, connect, coordinate, execute, and evolve together.

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executa…

Skills for Designers and Engineers.

Manage, review, and migrate cloud AI agents with Git and YAML. The open-source IaC control plane for managed AI agents.

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

Open-source, multi-platform harness for AI agents — a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, edit…

Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…

《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

Let Pi control your apps on MacOS & Windows

Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.

💫 Toolkit to help you get started with Spec-Driven Development

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…

Backport of Apple’s Liquid Glass system for iOS 13–18 with native API parity. Includes a reimplementation for iOS 26+ that unlocks advanced customization beyond the native system's limits.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

my agent skills

QA harness built for Claude Code | E2E testing with screen recordings, console logs, network HARs, and Playwright traces

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

AgentFlow: In-the-Flow Agentic System Optimization

micro-agent orchestrator for local agents

AI Context Takt: A pipeline tool for structural control over LLM context. Escape the black box of chat history, maximize token efficiency, and enforce precise reasoning for complex development tasks.

Desktop control center for ChatGPT Codex: launch, provider switching, enhancements, repairs, and diagnostics.

Task-oriented AI Agent productivity platform

Restate is the platform for building resilient applications that tolerate all infrastructure faults w/o the need for a PhD.

Effortlessly compose, extend, and observe every service in real-time for the first time ever.

gstack 中文深度注解学习指南 — Chinese annotated guide to garrytan/gstack

One-command bootstrap for a maximally efficient Claude Code dev environment. Installs GSD + gstack + Superpowers + Claude-Mem + UI/UX Pro Max + /flow unified command router.

Semi-Autonomous gstack Orchestration: Build with a strong product spec and let Garry Tan's gstack figure out the rest.