Code agents

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven, evidence-gated, parallel feature voyages.

Local-first, resumable AI maintenance pipelines with single-writer safety and deterministic verification.

the first open-source platform for simulation testing, monitoring and self-improving voice agents

A personal VM cloud in one Go binary: persistent Linux VMs on macOS, Linux and Windows, AI coding agents working inside them, any port published to HTTPS through Cloudflare Tunnel. Driven from a Mac OS 9 desktop in the browser, over SSH, or by an agent.

基于 FastAPI 多 Agent 协同的拟真 AI模拟面试平台，支持多面试官切换、实时语音交互与 9 阶段面试流程，内置 5 层安全防护。

DSH 自动化插件：让 Coding 任务按计划在全新 Agent Session 中运行，并由用户或 Agent 创建和管理定时任务。 / Run coding tasks in fresh Agent sessions and manage schedules from DSH Web or an Agent.

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

Jailbreaker is a local evaluation tool for testing chatbot and agent-style systems against jailbreak, prompt-injection, and related failure modes.

MCP server that drives real Chrome with your real logged-in sessions — genuine fingerprint (passes bot.sannysoft), human-like input, bot-wall aware. 43 tools, single static Rust binary.

Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely replay verified routines with agent-browser.

Lego-RL: Harness-Native Reinforcement Learning for Coding Agents

基本可用 Universal context-compression proxy for AI coding agents

Python SDK for DefuzeX agent behavior testing.

Brand Design Skill 是一个 image-first 的 Codex 品牌设计 Skill。它通过对话式流程引导 Agent 完成苏格拉底式需求澄清、Logo 图像探索、最终图像 Logo 资产、行业化 VI 应用场景，以及高质量 HTML 品牌手册。|

Thea brings coding agents to the physical world.

Local, fail-closed policy enforcement and human approval for MCP tool calls.

The open-source trading harness for agents

轻量级终端 Coding Agent，支持多模型接入与 MCP 标准扩展。

Pytorch Implementation of Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

A course on context engineering with code agents.

Multi-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact verification for Codex.

Evidence-first game operations incident investigation agent with read-only MCP tools and reproducible evaluations.

CraftBot is an architect AI agent. It interprets design briefs, grounds its thinking in domain knowledge through ingesting documents, images and other references, and outputs Python code that procedurally defines a building design.

Java-powered open source coding agent CLI with an explicit agent runtime and unified tool pipeline.

Portable, verifiable work state for coding agents

Scan, classify (A/B/C/D) and sync AI-agent SKILL.md files across toolchains (Codex, Claude Code, WorkBuddy). Zero-dependency Python CLI.

⚡ Modular prompt-engineering framework for AI Agents (Cursor, Claude Code, Copilot). Forces structured SDLC, linear execution, context isolation, and systematic debugging via a standalone Windows launcher. Stop vibe coding, start agentic discipline! 🚀

Type a movie, get a captioned speech + beat-cut fan edit. Local-first, no API keys, works with your AI bot (Claude Code / Codex).

A multi-agent academic paper workflow for structured writing, iterative polishing, fact-checking and rule-based academic compliance optimization. Suitable for 0–30 pages course papers and seminar theses.

Who's working, who's waiting on you — grouped by project, each agent in its vendor's logo and colour. Worktrees nest under their repo, rows order by activity, idle sessions fade. Light and dark.

LangGraph 显式状态机实现的 coding agent 平台：人审、统一权限、事务性写入、审计——企业级治理链的单机参考实现（cody-harness 的姊妹项目）

AAI Gateway — Install MCP servers and skills once, share across all your AI agents. One-time setup, 90% less context overhead. The unified gateway for AI agent tooling.

Rust client for OpenAI API

Rust-first reimplementation of a local agent CLI inspired by Claude Code.

All in One AI Chat Tool( GPT-4 / GPT-3.5 /OpenAI API/Azure OpenAI/Prompt Template Engine)

An example of a chatbot built with Microsoft Bot Framework and featuring e-commerce capabilities via Moltin, Azure Search, Recommendations API, and LUIS

Build and deploy AI-driven assistants with our OpenAI Assistants Template. This tutorial provides a hands-on approach to using OpenAI's Assistant API, complete with code modules, interactive Jupyter Notebook examples, and best practices to get you started on creating intelligent conversational agents.

Powerful Web and Omni Search inside Emacs

Make WhatsApp Chatbot and use WhatsApp API to send the WhatsApp messages in c# .

Transcription and TTS Rest API (OpenAI Whisper, Speechbrain)

Bring the power of pre-signed URLs to your apps. Signway is a gateway for redirecting ephimeral signed URLs to the requested API

A sample app to demonstrate Function calling using the latest format in Chat Completions API and also in Assistants API.

A MCP server allowing LLM agents to easily connect and retrieve data from any database

DAG-based Deterministic Context Compiler for AI Coding Agents

BCP-MAPF – branch-and-cut-and-price for multi-agent path finding

IntelliSense Designed for Coding Agent

an immersive browser dev environment with a seamless click-to-locate + agent edit loop.

A futures research and report review agent pipeline.

let coding agents use ncu skills analysis cuda program automatically!

Ghost 👻 is an experimental CLI that uses AI to generate GitHub Actions workflows, using OpenAI

Code and prompts for AI-augmented obsidian usecases

Headless AI agent for deterministic reverse engineering.

This repository is used to collect papers and code in the field of AI.

learn-claude-code js version 且只保留中文

A plugin for your agentic framework that optimizes code using the GEPA algorithm (Genetic-Pareto LLM-driven search).

A mini AI agent CLI, similar to Claude Code and Gemini CLI

A modular AI agent framework built with FastAPI (backend) and TypeScript (frontend), integrating LangChain/LangGraph-based agents for conversational intelligence, reasoning, and tool orchestration.

A lightweight autonomous AI coding agent with terminal-based UI, inspired by Codex and Cline.

Code repo for "LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners"

Run LLM-generated one-off scripts via the "Run Code Here" option in the Windows 11 context menu.

The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.

Open-source marketing skills for founders. Keyword research, growth strategy, social search audit, competitor analysis. Install with npx skills.

The Ultimate Claude Code Toolkit — 127 skills, 86 agents, 109 marketplace repos (11,700+ community skills), 30 commands, 8 hooks, GSD framework. Drop-in ~/.claude config that auto-activates the right resources from your prompt. Zero config required.

A unified pi-coding-agent extension combining hash-anchored file editing with structural code maps

Let AI agents control Windows applications. Click buttons, type text, toggle settings — all by name, not coordinates. Uses the Windows UI Automation API to find UI elements reliably, regardless of DPI, theme, resolution, or window position.

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.js, Python, C FFI and no_std. Token-exact with the JAX reference. No backend, no API key.

tested hermes agent recipes: configs, deploys, mcp, automations. copy, run, build.

An infinite-canvas workspace for coding with AI agents.

Human and AI Agent friendly print utility with syntax highlighting, markdown support, multiple pages-up, headers/footers. Cross platform (Mac, Linux, Windows) GUI and TUI. Print source code, web pages, and reports generated by legacy systems.

A curated list of practical resources for Agentic Engineering

Curated reusable skills, workflows, and tool-backed capabilities for AI agents.

AI agent skill that remembers every technical decision & bug fix across sessions — and learns from them. v4.0, MIT. | 跨会话记忆的AI编程助手知识大脑

Andy's Soul - AI Agent 核心操作指令 | Universal core directives for AI agents (Claude, Codex, Cursor) - Cognitive axioms + Musk's methodology + Karpathy's principles

AI Agent 面试知识库：覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。

X (Twitter) marketing skills for Claude Code and Codex: write tweets, threads, and replies in your voice, strip AI tells, and publish via Publora. Open source, MIT. Content engineering by Creative Content Crafts.

A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。

一个面向 Coding Agents 的轻量插件：帮你说清问题、冷静判断开发必要性，并认真寻找已经存在的产品、开源项目和可复用组件。

OpenAFW is a local agent firewall — keep your secrets off the model, the API relay, and the supply chain. Local credential masking, per-route model routing, and security detectors on the wire.

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Windows 托盘上的 Kimi Code 用量监控：左键看额度，低额变红提醒。Tauri 2 + Rust，安装包仅 4 MB。

Anti-slop skills for AI agents: slopbeth cleans the shipped writing, slopgent cleans the conversation.

A simple but powerful TUI coding agent. Fully native rust, cross-compatible.

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

Native macOS agent control for Codex and Claude — monitor, approve, ask, and jump back from the menu bar.

Sandboxed code execution API for AI agents: powers LibreChat's Code Interpreter

A polished TUI for Pi coding agent: animated logo header, Starship-style footer, rounded editor with model metadata, and prompt-box user messages.

Coordinate multiple AI coding agents through a local-first, recoverable Agent Bus.

一个用于国家自然科学基金（NSFC/国自然）申请书初稿诊断的 Agent Skill

Subject-aware minimal-zine image production for Agent Skills: art direction, generation, series, evidence, and real-bitmap QA.

Benchmarking Agentic Procedural 3D Modeling Via Code

A Command-Line Interface (CLI) and Skill to interact with Papers with Code. For agents and humans.

SEO Landing: Give your AI coding agent the capabilities of a senior Technical SEO engineer. An agent skill for building high-performance, technically optimized SEO landing pages. Turn an AI coding agent into a technical SEO specialist. Build and improve landing pages with: • 🚀 100/100 Google PageSpeed target • ⚡ Core Web Vitals optimization

An open-source multi-agent platform for GitLab MR code review, governance, and CI self-healing.

把代码探索、实现、修复、评审和测试交给持久化编码 Agent，支持继续同一任务。

简洁高效的代码审计agent

Versioned operating principles for coding agents

Local-first AI canvas and timeline. Any MCP agent. Open-source alternative to Higgsfield.

An agent skill for creating and refining SVG logos through guided exploration and iteration.