Code agents

Inspectable engineering workflows for OpenAI Codex.

One-command Git Flow for AI coding agents — start, finish, tag and audit releases from Claude Code or Cursor.

One CLI to swap between multiple Claude Code (Anthropic) and Codex (OpenAI) accounts.

Agentic-DFIR — autonomous digital forensics & incident response agent. Architecture-first, not prompt-first: typed read-only MCP tool surface, SHA-256 audit chain, senior-analyst playbook.

Lunar Vault is a self-contained memory infrastructure for Codex. Features zero-dependency ONNX embeddings, advanced reranking, and secure one-click installation without leaking personal data

Autonomous, relationship-aware B2B receivables recovery agent for Indian MSMEs. Replaces rigid calendar dunning with AI reasoning & a deterministic compliance envelope (MSMED Act & 43B(h)). Features Razorpay checkout, Promise-to-Pay tracking, dispute triage, human operator kill switch and 7 proven receivables recovery strategies.

Observability and control plane for AI agents.

A desktop app that turns Claude Code into a visual Kanban build loop. Describe a feature, review the plan, watch it get built task by task.

Deterministic execution & evolution layer between AI intent and production software — turning structured intent into reviewable, reproducible code. 🔥

x402 (HTTP 402 Payment Required) SDK + MCP server: let any API charge for itself and any AI agent pay for itself, USDC & stablecoins across EVM, Solana & 8 more chain families, in a couple of lines. Backendless, no fee, self-custodial, paid straight to your wallet. TypeScript, MIT.

Native macOS Markdown viewer and rendered-diff reviewer for documentation-heavy GitHub PRs (design docs, ADRs, skills, runbooks)

A fast embedded graph database for AI applications and graph analytics

Native macOS deck for orchestrating AI coding agents, each in its own terminal and git worktree

Local-first AI agent hub — 自我成长的桌面端智能体：工具注册 / MCP / 技能 / 远程 API，全平台原生安装包

Dead simple token calculator for your CLI, written in Python - identify how many tokens your code base is using and where

A coding agent that brings the full development loop to your phone — code, run, test, and iterate from anywhere.

Local-first, self-hostable coordination workspace for AI coding agents. Shared tasks, claims, sync and MCP integration.

A terminal coding agent where the model writes one program instead of calling tools one at a time.

Astra, Sol, Terra and Luna — in exact motion. Architect-first orchestration for Codex and five more clients: your chat owns architecture and acceptance, Astra/xhigh and Terra/high implement on risk-routed lanes, a fresh read-only Sol returns ship, fix-first or rethink. Every model pin is checked against observed routing, never assumed.

https://buttercup.sh/ — em dashes welcome. Agent Harness in a web browser. Learn how to build AI agents with us starting mid-September 2026

The Best and most functional MacBook Dynamic Island (See the Unseen)

Exit-code guardrails for autonomous coding agents: detect fake-green test tampering, prove verifiers have teeth, stop stalled loops, and gate parallel work.

Convert between plain-text/JSON commands and iOS/macOS Shortcuts (.shortcut), both ways — plus pull from iCloud share links. Signs by default so shortcuts import intact.

`grill-me` is an agent skill that tests whether you understand the code you maintain—not merely whether your coding agent can change it.

国内风景路线 AI 行程规划 Skill（Codex/Claude/Cursor 通用）：航班核验→高德实测路线→携程+飞猪房价→点评+美团餐厅→Markdown+PDF 攻略

An AI-powered command-line interface that bridges natural language and shell execution.

macOS menu bar usage monitor for Claude Code, Codex, GLM, DeepSeek, and MiniMax

Alunixa X — cross-platform AI Agent Control System for models, providers, tools, automation, connections, themes, and Codex desktop runtime.

Autonomous agent factory — loop runner, worktree engine, and a local dashboard over the event log.

本地多模型路由器：让 Codex 桌面端 / Claude Code / 任意 OpenAI 客户端在一个菜单里共用 GPT、DeepSeek、Kimi、GLM、Gemini、Claude、ChatGPT 订阅额度 | Local multi-model router: one menu for GPT + any OpenAI-compatible model, with Claude/Gemini/ChatGPT subscription pools,纯文本模型视觉中继借眼看图

Rust SDK for Lark / Feishu (飞书) Open Platform APIs, bots, events, WebSockets, and interactive cards.

An opinionated agentic workflow to turn well-defined units of work into shippable code with minimal human input.

Build a secure, production-ready MCP server for any project — connect Claude, ChatGPT & any AI agent to your backend with a URL + API key. Streamable HTTP + stdio + OAuth 2.0 (PKCE).

SKILL FOR MAKE GAMES WEB BASED

The open-source agentic RTL IDE

A curated list of ready-to-use Grok bot templates across productivity, sales, marketing, ops, success, and personal workflows.

Self-deployed AI-native project management platform—requirements, acceptance, and progress stay in your instance, running synchronously across sessions, users, and Agents.

A persistent, browser-accessible Linux computer for a single Buzz agent — its own desktop, terminal, filesystem, and long-lived state, joining any Buzz workspace over its relay

A self-hosted AI agent with WebUI, CLI, MCP tools, multi-provider support, and Record & Replay for deterministic debugging.

An autonomous, AI-powered offensive security framework. DrogonClaw uses an unrestricted ReAct engine to dynamically chain reconnaissance, exploitation, and post-exploitation workflows within isolated, ephemeral sandboxes.

Agent Skills and plugins for using Relewise with AI agents, including ChatGPT/Codex, Claude, GitHub Copilot and Gemini.

archeus — the memory and workspace layer for AI coding agents. Persistent per-project memory, every session you have ever had, and control over what the next one costs. Works with Claude Code, OpenAI Codex and pi. Terminal UI and desktop GUI, zero runtime dependencies.

AI Agent Skill for building verified, citation-backed courses in Google NotebookLM

Agent skills for frontend UX/UI design that actually looks good

9 AI agent skills for academic research — evidence search, citation validation, literature expansion. Works with Claude Code, Codex, Gemini CLI. Free API tier included (OpenAlex, CrossRef).

Local, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates — no cloud.

gwae: niri's scrolling tiling for your CLI agents, in any terminal (daemon-free, MIT)

Hands-on materials for a 2-hour AI Agent Development Workshop (LangChain + Groq): a phase-by-phase Python boilerplate, three themed track projects (robotics, AI, cybersecurity), a presentation deck, and a cheat sheet — built for a mixed-skill student audience at Amrita University.

An end-to-end framework for Agentic Reinforcement Learning.

Open-source collection of shared AI agent skills for emdly.com.

A minimal, explicit, provider-safe harness for the Pi coding agent

A tiered team of engineering agents and portable workflow skills for AI coding tools.

Claude Code skill: Fable 5.1 decides, Opus 5 / Sonnet 5 / Haiku 4.5 execute. Five wiring patterns (advisor, architect+delegate, agent teams, workflows, /goal), effort routing, fallback traps, 16-block prompt kit, pinned agent lanes.

MathType 7 AI Agent skill, Codex and Claude plugin, and MCP server for editable equations, native Word numbering, references, and PowerPoint.

AI engineering agent for Mitsubishi GX Works2 with MCP support for PLC programming, project editing, validation, diagnostics, and external AI agents such as Codex.

pochete-toolkit é o conjunto de ferramentas feito pra quem codifica de forma agêntica com claude code em ambiente enterprise.

Use Meta Muse Code in Zed, IntelliJ IDEA, and other JetBrains IDEs with your existing subscription. Dependency-free Rust adapter for Agent Client Protocol (ACP), using the native Muse Session Protocol (MSP).

Runnable gpt image 2 api examples: OpenAI SDK, OpenRouter gpt-5.4-image-2, kie.ai image-to-image with env-var keys.

A Lego-style agent system template built from agent, MCP, CLI, and skills.

基于 Sub2API 的非官方可扩展衍生版，支持 Codex 5h/7d 额度透支、账号级 429 自动重试、分组并发限制、API Key 主/兜底分组、CPA 指纹出口及更多扩展功能。

RedDynasty 是一款为红队行动、渗透测试和网络攻防演练量身定制的大语言模型工具，结合精心打磨的提示工程，让 AI 以战术化、结构化的方式回应，就像一名老道的网络作战军师，协助你分析日志、提炼情报、模拟攻击链、制定作战计划。无论是迅速锁定漏洞、整理入侵痕迹，还是推演渗透路径，RedDynasty 都能在暗潮汹涌的网络战场，为你提供敏锐、精准、贴近红队思维的智力支持。

OpenCode TUI sidebar plugin that displays API usage quotas for OpenAI and Z.AI (GLM) providers.

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind it. Keep clients unchanged while swapping speech and LLM providers at runtime

A persistent, reachable resident behind Claude Code and Codex — steer it from Telegram/Slack/WhatsApp, it keeps working while you're away. It opened >1K PRs on this repo. Self-hosted, $7 hosted.

A native desktop coding agent built with Rust and GPUI.

Build, test, and observe AI agents inside your .NET applications.

Many Claude Code projects. One window. Zero hunting. A lean, dark, macOS-native lite IDE for the power Claude Code user.

Claude Sonnet 5 API examples in Python: claude-sonnet-5 quickstart, effort levels, and migrating from Sonnet 4.6.

For FriendliLink, our integration convenience tool.

Mission control for Claude Code: see and steer every session, subagent, /loop and todo list from one local dashboard. Zero dependencies.

企业知识助手与任务准备 Agent：面向员工上手和展厅知识交付，支持 RAG 问答、自主查阅资料、连续任务准备与用户确认的行动计划。

爪印档案｜宠物记忆管理与 AI 对话产品原型

LLM-led e-commerce content review with rule-based safeguards, tenant-isolated MySQL, Redis workers, and auditable publication decisions.

MCP server for Bing search: organic results, the ad block and the Copilot answer, with geo, market and language targeting. No Azure subscription. 1,000 free credits every month.

Amazon 跨境电商运营助手 - AI 驱动的运营分析平台

Edit a running web app from inside the page: pick elements, screenshot, preview changes, approve one, and it lands in your source.

Another agent coding tool with auto mode, auto routing and more

Kubernetes troubleshooting workflow

A read-only weekly audit for Codex automations and personal skills, with approval-gated fixes.

Lumpcode : The Open Source CLI and Library for loop engineering

A platform-agnostic, file-based multi-agent engine. Install 20 specialized AI personas directly into your repository. They plan, design, build, review, test, and ship — with structured memory that persists across sessions and two architectural moats no other framework combines.

AI assistant skill files for the HyperTracker API — cohort analytics, order flow, liquidation risk, and leaderboard data from Hyperliquid

A Visual Design that ships with your code. Agents and humans work together on the same canvas, where every change is a diffable JSX stored in a .uidx file inside your repo. Built on OpenPencil and Skia, with MCP built in.

Agent-agnostic desktop shell for CLI coding tools

mcppls — a C++20/23 modules language server: one set of module semantics on GCC, Clang, MSVC and MinGW, for editors (VS Code, Zed, CLion, Neovim), AI Agents (MCP) and CI

Give agents capabilities. Keep credentials local. A local relay that gives AI agents, scripts, and automation controlled access to HTTP, SSH, and LLM APIs — without exposing real URLs, passwords, or API keys.

Remote hands for coding agents: an MCP server that runs OpenCode / Claude Code / Codex work on a remote host over SSH, keeps credentials and the local machine closed, and audits everything

AI-native task management for humans & agents. MCP-first, CLI-native, self-hosted. Bring your own model.

Open-source adversarial verification Agent Skill for Claude Code, OpenAI Codex, and Cursor. Make AI coding agents prove bug fixes, CI, logs, and deployments.

WorkBuddy Tools — 在不同账号间无缝衔接你的工作。支持国内版/国际版多账号管理、快速切换、选择性数据迁移与 Token 用量统计，全部本地运行。

Local-first, model-neutral memory for coding agents. One shared, owner-governed store across OpenCode, Claude Code, Codex, and Cursor, with optional hosted sync through AI Passport.

Make any operation safe to retry. Crash-safe idempotency for HTTP requests, queue messages, and function calls, in Python and TypeScript. Redis, Postgres, MongoDB, DynamoDB.

AI-powered content automation for Xiaohongshu (RED) — viral topic mining, copywriting, cover prompts & data analytics. Battle-tested at 22.6% CTR.

How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to the model, did the comparison remain fair, what changed, what did it cost, and do we have enough evidence to say that confidently?”

把模糊想法整理成可直接执行的 Agent 提示词：自动选角、逐轮澄清、权限边界、验收标准与验证证据。

Docker image running OpenCode (AI coding agent) and code-server (VS Code) in a single container, with Traefik integration, mise toolchains, and SSH support -- designed for self-hosted NAS/VPS use.

Reusable TypeScript engineering skill for AI coding assistants. Practical guidance on type safety, runtime validation, architecture, security, and testing. Works with Codex, Claude Code, Copilot, Cursor, and more.

File-native Brain v8.3 for Claude Code, Codex, and ZCode — persistent identity, structured memory, cognitive loops, and local recall.

A proven methodology for building and tracking features, projects, and issues across numerous builds.