AI Agent 源码深度研究报告

practice made claude perfect

The fastest repo in history to surpass 100K stars ⭐. Better Harness Tools that make real things done. Built in Rust using oh-my-codex.

Research on Coding Agents

Instructions to use Garry Tan's gstack with Opencode instead of Claude Code

Feature-packed native macOS screenshot tool: annotate, auto-redact PII, record GIFs, OCR + translate, scroll capture, beautify, and more. No Electron, no subscription.

Open-source 2D IDE for managing AI agents in native CLIs, terminal, gits, beads issues, and files across multiple projects and machines. Self-host on a single machine via localhost OR host on a clu…

AI agents running research on single-GPU nanochat training automatically

Turn Claude Code into a full game dev studio — 48 AI agents, 36 workflow skills, and a complete coordination system mirroring real studio hierarchy.

The personal AI that actually learns from its mistakes. 51 monitors, temporal KG, DPO fine-tuning. Runs on your GPU.

A programming framework for agentic AI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Open-source orchestration for zero-human companies

JavaScript in-page GUI agent. Control web interfaces with natural language.

Warcraft III Peon voice notifications (+ more!) for Claude Code, Codex, IDEs, and any AI agent. Stop babysitting your terminal. Employ a Peon today.

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows

Open protocol for cryptographically verifiable human intent — AI agent authorization, local-first, offline-capable, no central authority.

Enable AI Coding workflows: spin up concurrent nodes per Git branch, each with independent worktrees and tmux sessions.

Hundreds of models & providers. One command to find what runs on your hardware.

DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。​让安全不再昂贵，让审计不再复杂。

Opsy - Your AI-Powered SRE Colleague

Build, run, manage agentic software at scale.

⚙️🗑️ A GitHub Action to free disk space on an Ubuntu runner.

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

The Claude Agent Skill for Terraform and OpenTofu - testing, modules, CI/CD, and production patterns

Fast, modern traceroute with real-time TUI, per-hop stats, ASN/geo lookup, ECMP detection, and MPLS label parsing. A better mtr.

A tool for in-depth analysis of container checkpoints

CUDA checkpoint and restore utility

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7 and MiroThinker-H1, achieve 74.0 and 88.2 on the BrowseComp, respectively.