Coding Agents tools for Codex / OpenAI

OpenAI's official autonomous coding agent CLI — the open-source reference implementation of the Codex harness with sandboxed tool execution, multi-file editing, and a streaming agent loop. Worth studying because it is the most widely adopted terminal-native coding agent harness and exposes the same loop architecture that OpenAI documents in its harness engineering posts

OpenDevin is an open-source initiative aimed at replicating and enhancing the autonomous AI software engineer Devin, focusing on collaboration and complex task execution in software development, emphasizing its relevance to advancing agentic AI technologies github | github profile

GPT-Engineer is an AI-powered tool allowing users to specify software in natural language, automatically generating and executing code, with options for improvement suggestions, and fostering collaboration within the open-source community github | github profile | website

AI pair-programmer harness with an Architect mode that splits planning (one LLM) from coding (another), and git-aware tooling that uses version control as the undo mechanism instead of custom state rollback. The best reference for multi-file editing tool design and planner/coder layer separation

Alibaba's production-grade code review agent combining deterministic pipelines with LLM reasoning: built-in fine-tuned rules catch NPE, thread-safety, and injection vulnerabilities at line-level precision, while the LLM layer handles nuanced design feedback. Demonstrates how hybrid harnesses can outperform purely model-driven or purely static-analysis approaches by assigning each layer the problem

Harness control surface available as web, mobile, and desktop app. Claude Code, Codex, Cursor, Grok Build, OpenCode.

Continue is an open-source autopilot plugin for VS Code and JetBrains, enhancing coding with LLMs through features like task and tab autocomplete, natural language edits, file generation, and customization options, available under the Apache 2.0 license github | website

GPT Pilot is an open-source AI developer tool that aims to provide a comprehensive development companion, capable of writing features, debugging, and interacting with users, presenting itself as an alternative to Devin, the world's first AI software engineer developed by Cognition Labs github | discord

Open-source terminal AI agent optimized for Qwen3-Coder; multi-protocol support (OpenAI/Anthropic/Gemini APIs), 1,000 free requests/day. ~21K+ ⭐

Open-source Cursor alternative (VS Code fork); any model or local hosting with change visualization. ~28K+ ⭐

A Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Features notification rings, in-app browser, SSH support, and Claude Code Teams integration

程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP / A2A）、AI 编程教程（Harness Engineering）、AI 工具用法（Cursor / Claude Code / TRAE / Codex / Copilot）、AI 开发框架教程（Spring AI / LangChain）、AI 产品变现指南，帮你快速掌握 AI 技术，走在时代前沿。本项目为开源文档 aiguide，已升级为鱼皮 AI 导航网站

High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows

Coding agent whose Agent-Computer Interface (ACI) — purpose-built file viewer, search, and editor tools with explicit state constraints and error feedback — is the reference design for adapting a tool interface to a specific task domain rather than using generic bash

DB-GPT revolutionizes database interactions using private LLM technology, enabling streamlined AI-native data app development with multi-model management, Text2SQL optimization, and fine-tuning, facilitating enterprises and developers to create bespoke applications in the Data 3.0 era github | github profile

Terminal-based AI coding agent with REPL mode for planning and executing complex tasks across multiple files, 2M token context

Desktop app to orchestrate multiple AI coding agents in parallel (Claude Code, Codex, etc.) with Git worktree isolation

Y Combinator's open-source multiplayer agent harness for startups: isolated per-person workspaces plus shared Slack channels and projects, with pluggable harness backends (Claude Code, Codex, OpenCode, Pi) and scope-owned skills. The clearest reference for building team-wide agent deployments where personal customization and collaborative context coexist without vendor lock-in

Open-source terminal AI agent (95K+ GitHub stars) supporting 75+ providers. Free, privacy-first, with LSP integration

ChatGPT integration for shell command generation and system administration

Invoked from Slack, Linear, or GitHub comments; each task runs in its own cloud sandbox and ends in a draft PR linked to the ticket.

All-in-one LLM CLI tool featuring shell assistant, REPL mode, RAG, AI tools and agents, supporting 20+ providers

Bloop is a GPT-4-based coding assistant that boosts engineer productivity by allowing natural language interactions with codebases for explanations, feature writing, error troubleshooting, and more, featuring a code-centric AI playground, fast regex search, and comprehensive code navigation tools github

✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

Neovim plugin for AI-assisted coding with agents, slash commands, and multiple LLM support

A Socratic interview gates the spec on an ambiguity score, then one command drives execution, a staged evaluation gate, and a budgeted evolution loop that runs the semantic stage only

A terminal window manager that knows what your agents are doing. Tile panes across nine workspaces in the terminal you already use. A daemon keeps sessions running when you detach and reaches your other machines. The coding agents in your panes report what they are doing, and one Inbox holds everything they are waiting on. Agent integration for claude-code, codex, gemini-cli, opencode, amp, antig…

Open-source agentic dev environment (YC W26) for running multiple coding agents in parallel in isolated Git worktrees

Multi-model collaboration system for Claude Code. Orchestrates Claude + Codex + Gemini with 28 slash commands, smart routing (Gemini for frontend, Codex for backend), Agent Teams for parallel development, and 6 built-in quality gate skills. One-command install via npx

Matt Pocock skills 的简体中文本地化：人工审核每一次更新，定期同步上游，支持 Claude、Codex 和 DSH 插件。

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex

Workflow plugin for Hermes Agent adding specialist skills, project memory, and task-specific model and reasoning routing

Self-controlling agentic IDE that orchestrates multiple coding agents in live threads you can follow, steer, or hand off, driven from a desktop app, web app, CLI, or HTTP API.

Multi-engine AI coding desktop client (Tauri). Claude Code, Codex, Gemini, OpenCode, DeepSeek Harness and more in one GUI.

A personal AI agent in your terminal, equipped with local tools for coding, shell commands, file editing, and web browsing

The open source AI video agent: turns any coding agent into a video agent, with an editor to change anything it makes.

Experience-Driven Black-Box Cost Control for Coding Agents

Open-source desktop command center for running multiple AI coding agents (Claude Code, Codex, Gemini CLI, etc.) in parallel, with Cue event automation, Auto Run playbooks, Group Chat across local and remote agents, and a maestro-cli that agents can drive themselves

Tauri desktop UI where tabs are agent sessions, running Claude Code, Codex, Cursor, Grok Build, OpenCode, Pi, omp, and fx on your existing subscriptions. macOS, Linux, and Windows.

Stop That Shit（别再造史了）｜面向 Codex/GPT 场景的多平台 Hook + Skill Guard：拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

Devon, not Devin, aims to perfect code correction for fill-in-the-middle, bug spotting, and completion tasks, using JSON for metadata in edits, and incorporates looping until user termination in function updates github

Cross-device control plane for coding agents, syncing sessions across machines and keeping agents running on an always-on daemon. Claude Code, Codex, Cursor, Grok, Hermes, Pi.

WorkBuddy 国际国内多账号反代网关，支持 Codex / Claude Code / DSH与标准 OpenAI 客户端。

Pezzo is the open-source LLMOps platform built for developers and teams. In just two lines of code, you can seamlessly troubleshoot your AI operations, collaborate and manage your prompts in one place, and instantly deploy changes to any environment

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

Arranges terminals, editors, and files as tiles on an infinite pan-and-zoom canvas instead of tabs.

Ruler — apply the same rules to all coding agents

by Alisa Qian - Vox Director is an open-source skill that turns a one-line topic into a finished Vox-style paper-collage explainer or ad video. It automates the full pipeline — script, collage keyframes, motion, voice-over, music, and captions — on the Atlas Cloud API plus local ffmpeg, with two human approval gates for the beat map and visual style

Local-first CLI coding agent built with React and Ink

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.

Autonomous AI agent, inspired by Devin, designed for complex task execution with features like a secure sandboxed Docker environment, integrated browser for real-time web information, text editor, and PostgreSQL database for history tracking, highlighting its relevance to agentic AI through its ability to autonomously navigate and perform actions across terminal, browser, and editor interfaces git

Desktop app and web server to browse, search and analyze your AI coding assistant history — Claude Code, Codex CLI, GitHub Copilot, Gemini CLI, Cursor, OpenCode and more. 100% offline.

Native macOS control center for AI coding agents — monitor sessions, approve actions, and jump back instantly.

by Greg Hinkle - A visual workspace for building with Claude Code (and Codex) where you and the agent co-edit *visually* — markdown, mockups, mermaid, Excalidraw, CSV, and data models — approving the agent's changes as red/green WYSIWYG diffs, with session/task kanban, worktrees, an extension SDK, and a native iOS companion app. A distinctive higher-bandwidth take on agent collaboration, open sour

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.

(1.8k ⭐) - A simple SDK for safely running Codex, Gemini CLI, and Claude Code in a secure sandbox

Dev agent multiplexer: isolated tmux pane + Git worktree per task. Supports 11+ agents including Codex

Ovis (formerly herdr web UI): free, open-source browser and phone client for herdr. Chat and live terminal for Claude Code, Codex and every agent pane, remote PCs over SSH, web push alerts

CLI control plane that runs agent sessions in managed tmux, sends prompts and logs to running agents from the terminal or a TUI console, and gives every agent one setup with shared local memory, verification skills, and lifecycle workflows. Claude Code, Codex, Pi, and more.

Native macOS desktop app for working with local coding agents, keeping projects, sessions, and transcripts on your machine. Supports Amp, Claude Code, Codex CLI, Cursor CLI, Grok Build, OpenCode, and Pi.

Native macOS workspace (Rust/GPUI) running CLI agents side by side in low-RAM Ghostty terminals, with embedded browser and editor panes, a Kanban board, and iOS/Android session access. Claude Code, Codex, OpenCode.

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

CLI token optimizer and AI context generator. Scans codebases to extract routes, schema, components, and dependencies for Claude Code, Cursor, Copilot, Codex, and Windsurf. 9x–13x token reduction, built-in MCP server, zero runtime dependencies

Open-source desktop and mobile command center for supervising Claude Code, Codex, OpenCode, and other coding agents across machines.

Desktop and web app for orchestrating agents across multiple projects and their git worktrees. Claude, Codex, OpenCode.

AutoPR autonomously wrote pull requests in response to issues

See how your app actually fits together. An interactive, plain-English map of your codebase, drawn by Claude or Codex.

Open-source CLI that scans your codebase and generates AI agent configs (CLAUDE.md, .cursorrules, skills, MCPs) for Claude Code, Cursor, and Codex. Scores your setup 0-100 and recommends MCP servers

AI Coding 福利站导航：免费白嫖 Claude Code / Codex 的中转站与公益站合集，含额度、模型、价格自动更新与一键配置脚本

cloudroom is the open-source platform to run 1,000+ agents productively

Provider-agnostic code review using AI. Use Claude, Gemini, Codex, Ollama to enforce your coding standards

One TUI covering sessions across Claude Code, Codex, Gemini, and OpenCode, with live status and resume for each.

PiDeck 是一个开源的桌面工作台，用于在本地项目目录中统一管理 PI | DSH Agent 会话，并支持导入 Codex、Claude 本地会话以便统一浏览和恢复。支持多项目工作区、会话历史、Git 集成、内置终端、模型配置和插件管理，基于 Electron 构建。

Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent

Local-first desktop workspace where agents and shells run as real PTYs in split panes and custom grids across projects, surviving pane close and app restart. Suspend idle groups to reclaim memory and resume with scrollback intact. Claude Code, Codex, OpenCode.

vibe coding 的驾驶舱：左边文件，右边/下边终端，中间看清每一次改动。 / The cockpit for vibe coding: browse files on the left, command agents on the right, watch every change in between.

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly. github

Telegram bridge that puts Codex, Claude Code, OpenCode, and Pi sessions in a chat thread.

🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥️ Browser-first · zero API keys · durable projects.

Mobile/web control layer for Claude Code, Codex, Gemini CLI, and other terminal-based coding agents, built for away-from-desk continuation with terminal access, file browsing, git views, localhost preview, notifications, and multi-agent workflows

Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

One persona, many coding agents. Replace or inject system prompts across codex, claude, opencode, grok, omp, hermes, pi, zcode - with a local web console.

Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi, and other coding agents in parallel — locally or 24/7 on your own server.

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

CLI that runs several coding agents (Claude Code, Codex) on the same task, each in an isolated git worktree sandbox, has them peer-review each other, then a neutral verifier replays every candidate, runs the tests itself, and merges the one that passes. Run metadata is versioned in the repo under refs/h5i/*. Rust, Apache-2.0

Agents Capable of Self-Editing Their Prompts / Python Code. github

A monorepo of Pi Coding Agent extensions

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.

A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, Tmux alternative

Multi-device terminal server for AI coding agents. Server-side VTE, session persistence, file browser, web preview, plugin system. Self-hosted.

Self-hosted AI runtime that orchestrates Claude Code, Codex, Gemini CLI, OpenCode, Copilot CLI, Cursor Agent, Goose, Qwen Code, and Droid with heartbeats, schedules, delegation, runtime skills, and an org chart view. Ships as a desktop app (Electron) and CLI. MIT licensed, TypeScript

Automata: A self-coding agent

OpenAI Codex: The Complete Guide · 橙皮书系列 · GPT-5.5 时代的 AI 编程实战手册

Native macOS command center for running coding agents in parallel, with vertical tabs, a live canvas view of every running session, and a command palette. Claude Code, Codex, and more.

Agent skill that draws architecture, flowchart, sequence, data-flow and lifecycle diagrams as hand-placed SVG, to one linted house style.

By a 12-year product manager who builds 0-to-1: takes a beginner from a vague idea to a buildable plan, then guides the build (GitHub basics, clean-code habits, a verify-and-iterate loop, a checkup for the mess). For Claude Code, Codex, and Antigravity. grill-me is for engineers, vibe-check is for everyone else.

Terminal UI that runs Gemini CLI alongside Claude Code, Codex, OpenCode and other coding-agent CLIs, each in its own persistent tmux session. One list shows every session's live status, prompts go into a pane without attaching, a session can spawn into its own Git worktree, and a full-file diff review sends line comments back to the agent. Launches your installed Gemini CLI unmodified, so login, c

Native C++26 terminal coding agent and drop-in claude-code alternative. Single static binary, sub-millisecond cold start, sandboxed by default, and model-agnostic (Claude, OpenAI, Groq, OpenRouter, Ollama). Runs inside Zed over ACP and drives air-gapped hosts over SSH. MIT

HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.