Code agents

A curated list of agent skills, resources, and tools for building customizable AI workflows (Claude Code, Codex, Kiro-CLI)

Make AI writing sound like you, not like AI. Two Claude Code skills that audit text against your own voice and fix only what fails.

Local-first AI coding agent runtime — your models, fail-closed safety, evidence-gated self-improvement

Governance kernel for AI coding agents. One command → safety rules + scenario packs, synced to 15 platforms (Claude Code, Cursor, Copilot, Windsurf, Trae, Gemini, Cline, and more).

The most complete Dify MCP server + CLI — 174 tools that let any AI agent build, test & ship Dify workflows autonomously.

Repo Steward AI: safety-conscious PR review, issue triage, release notes, and verifiable maintainer pilots with the OpenAI Responses API.

天枢 · 可治理、可验证、持续成长的自进化 Agent OS —— A governable, verifiable, self-evolving Agent OS with built-in audit trails and evidence chains

Software engineering discipline grounded in named primary standards (OWASP, ITIL, IETF RFCs, ISO, BABOK, SBAR, and more), shipped as a Claude Code plugin and an MCP server.

Estimate token usage after every agent step, trigger configurable alerts, and suggest practical ways to save context.

Karpathy-inspired LLM Wiki demo: AI agents compile raw sources into a persistent, self-linking Markdown knowledge base. The Agent writes. The Wiki remembers. Live interactive walkthrough + local Streamlit app (Gemini).

An Overleaf alternative with an inbuilt agentic AI (like Antigravity) in LaTeX code editor..with unlimited collabrators for each project for free

Open-source agentic software development platform for building, orchestrating and monitoring autonomous AI coding agents.

Find out why your Codex hooks aren't firing

Embeddable Python agent loop for integrating LLM agents into your projects. Multi-provider (OpenRouter, OpenAI, Anthropic, Google, Groq), built-in tools, hooks, ACP server, and persistent sessions.

一个基于 NoneBot2, OneBot v11, Docker, and OpenAI-compatible LLM APIs 的 QQ聊天 AI agent

Control plane for your harness across many repos — durable personas, per-task workspaces, and a credential vault the model never reads from

Safe local Codex model switching for OpenCode Go models with privacy-safe routing proof.

An autonomous CLI coding agent with smart memory management and zero provider lock-in.

Fork-and-fill bootstrap for Claude Code — agents, skills, hooks, tiered rules (P0/P1/P2) and stack presets composed into one enforced pre-commit gate. 한국어/English

Finish coding-agent tasks with reviewed specs, frozen plans, bounded execution, adapter checks, and final proof. Provider-neutral lifecycle kit for Codex, Claude, Qwen, and local CLIs.

DSH Minimal reasoning-trajectory steering adapters for DeepSeek V4 Pro on Pi, Oh My Pi, and OpenCode.

Session-layer circuit breaker for LLM & agent traffic — a transparent streaming proxy that meters every session and kills the one that goes rogue, without taking down your app.

A framework for orchestrating applications powered by autonomous AI agents and LLMs.

AG-UI + LangGraph agent with a plain React and a vanilla JS frontend. No Next.js, no CopilotKit. Streaming, tool calls, shared state, human-in-the-loop interrupts, bring-your-own-key.

A Claude Code skill that catches commonly-forgotten UX/product details before you ship a screen or feature.

ABP Framework skill files for Claude Code and OpenCode, production-ready code examples.

safetensors gguf lfm2 heretic uncensored decensored

AI 驱动的多 Agent 自动化渗透测试平台：LLM 协调员+监察员编排专项子 Agent，授权边界内自动完成侦察→漏洞检测→利用验证→取证报告。Web 渗透 + C2 双作业线，45+ 原生工具，Docker 一键部署

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.

gguf dflash2 speculative-decoding draft-model rocmfp4 vulkan

Hermes-native skill for systematic coding loops, real verification, and clean agent handoffs

HR policy RAG assistant with LangChain LCEL, RunnableBranch, FAISS, FastAPI, and an OpenAI-compatible model API.

HR policy RAG workflow with LangGraph StateGraph, conditional routing, FAISS, FastAPI, and an OpenAI-compatible model API.

Self-hosted document library and PWA reader for PDF, Markdown, and text files, with NAS folder watching, full-text search, sharing, annotations, and optional AI tools.

Claude Code skills for microcontrollers (MCU): STM32, ESP32, RP2040, nRF52840, AVR board-specific Agent Skills (SKILL.md) for embedded firmware

Community troubleshooting knowledge layer for OpenAI Codex

Feishu/Lark-first local AI agent gateway and native DeepSeek Harness plugin for Codex, Claude Code, Kimi Code, DeepSeek Harness, and Antigravity; Telegram optional.

AI 短剧生成平台｜AI Short-Drama Video Generator — 从剧本到成片一站式生产：LLM 剧本解析、智能分镜、@引用提示词、多模型视频生成（MiniMax-H3 r2va 多模态参考）、React-Flow 节点画布、剪映式三轨道在线剪辑、团队协作与积分计费。text-to-video · storyboard · AI filmmaking

Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude Code and Codex.

面向长篇小说创作的桌面 AI 写作 IDE——对话式 Agent、多视角审稿、定向修订、diff 确认写回、canon 防漂移；BookRun 生成流水线降级为后台工具。

AI research agent for nuclear physics: 23 expert skills that install, run, and verify open-source codes (FRESCO, TALYS, SMASH, ...) plus a 61k-paper offline nucl-th knowledge base

Learn vibe coding free: the roadmap, 170 interactive lessons (Claude Code, OpenAI Codex, Google Antigravity, agentic AI, prompt engineering, Claude Cowork, ChatGPT Work), an 81-term AI coding dictionary, templates and an awesome list.

Redpen makes coding agents prove they are actually done.

ImagineX: Your AI-driven Telegram bot for questions and image generation.

Local-first code navigation for large codebases. Parse, index, search, and understand millions of lines of code using structural and semantic retrieval.

Detect and Deny - Deterministic Function-Level Guardrails for AI Agents

The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed.

基于 AgentScope 2.0 的电商智能客服 Agent：17 个业务工具覆盖售前到售后，业务数据全部经工具查询、不做生成；含自研 Fire Trace 调试平台。无需 API Key 即可完整跑通

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.

Developed a Multi-Agent Research Assistant that coordinates specialized AI agents to search, analyze, summarize, and synthesize information from multiple sources, delivering comprehensive, citation-backed research reports and actionable insights.

Full-text Asian financial reports (China, Japan, Korea, Taiwan) as clean Markdown — REST API + MCP server for LLMs, RAG and quant

Source-available Salesforce knowledge layer for AI coding assistants. 1,039 skill packages, 50 runtime agents, 69 slash commands/MCP prompts, and a 38-tool MCP server with live-org metadata.

Official CLI for Lila: the testing framework for startups

A multi-mode terminal AI agent supporting GPT-5/Ollama for vision, image creation and edition, video generation,web search, code generation, and autonomous pentesting with persistent history and zero API costs.

A human-scale interface for multi-agent development

A canvas-first, agentic IDE for designers and developers, for fully autonomous web app development

AI Assistant, real-time AI chat and voice assistant.

🖤 The API Backend of the Curiosone bot.

CodeFramer is a versatile code editor built to enhance your coding experience with its intuitive interface and powerful features.

An interactive AI-powered CV that turns job search into a joyful adventure. #ForTheLoveOfCode

Welcome to our SaaS AI platform repository! 🚀 Our SaaS AI platform is designed to empower businesses with cutting-edge Artificial Intelligence capabilities, providing seamless integration of Next.js 13, React, Tailwind CSS, Prisma, and Stripe.

🤖 A WhatsApp bot to transcribe and summarize audio messages.

Proxy for OpenAI api using python flask, supports SSE streaming.

En este repositorio encontraras de una forma centralizada y facil, para poder correr alguno de tus modelos favortios localmente usando docker

Automated Crypto Trading Signals Powered by GPT-3

locally hosted neural net chat framework with biomimetic RAG (cc0) (by luna+ada) (<3)

This project demonstrates deploying a secure, scalable Generative AI (GenAI) solution on Azure using a Retrieval-Augmented Generation (RAG) architecture and Azure best practices. Leveraging CosmosDB, Azure OpenAI, and a React + Python FastAPI framework, it ensures efficient data retrieval, security, and an intuitive user experience.

n8n community nodes for the OpenClaw Gateway API

Turn any GitHub file or issue into clear, multilingual insights instantly. This standalone AI actor explains complex code with flowcharts and generates step-by-step solution plans for issues all in your preferred language.

AI-native engineering workflow skills for Claude and Codex — repo-backed PRD-to-code orchestration, milestone delivery, and validation.

🐙 AI Agent System with RAG and outbound calling through LiveKit, OpenAI Realtime for voice chats; integrates Pinecone, JWT auth, and analytics for smart agents.

Self-hosted RAG engine for AI coding assistants. Ingests technical docs & code repositories locally with structure-aware chunking. Serves grounded context via MCP to prevent hallucinations in software development workflows.

Kendr is multi-agent orchestration which user can run in their own controlled infrastructure. Designed for long running tasks.

Autonomous AI agent built on Claude Code Channels — scheduled tasks, heartbeat monitoring, auto-recovery, and persona config for Telegram & Discord

AemeathCLI

The open platform that binds content to context.

AI-native incident response and on-call platform. PagerDuty and Opsgenie alternative for modern SRE and DevOps teams.

🛡️ A firewall for your agent's brain. Open-source security proxy that protects AI agents from prompt injection attacks. 4-stage pipeline, community threat feed, no bypass mode.

Maximize GitHub Copilot’s impact in large, legacy, and regulated codebases.

Zero-configuration way to expose LangChain/LangGraph agents as autonomous services with webhooks, cron, and HTTP triggers.

Local-first code intelligence for AI agents. Transform your codebase into a queryable knowledge graph. 85% token savings for Claude Code, Cursor, and MCP-compatible tools.

API documentation via MCP for AI coding agents

My collection of Claude Code Agents & Skills for web and iOS Development

AI-powered group finance assistant using MCP architecture, Gemini LLM and Streamlit.

A curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts across 19 skills: SpoonOS Skills for Vibe Coding (build agents) + Web3 Skills for Skill Agent Integrations (DeFi, NFT, DAO, Security).

AI-powered tool that helps you debug, analyze, and understand your applications using Pydantic Logfire.

AI dev framework: 22 agents, 100 core skills + 142 addon skill packs, 149 commands. Runs on 21 AI tools: Cursor, Claude Code, Copilot, Windsurf, Cline, Aider, Roo, Kiro, OpenHands, Gemini, Codex, Goose, Warp & more. File-based memory persists across sessions.

Replayable Browser Agent

Claude Code skills for Convex backend development. Drop-in knowledge for queries, mutations, AI agents, components, and auth patterns. Community contributions welcome!

The Best Open Source LLM Code Interpreter

A self-hosted, secure code execution sandbox for LLM agents deployed on your cloud infrastructure using SkyPilot. Built on llm-sandbox for multi-language code execution.

Deployment of chromadb into AWS resources through terraform

Translate any text using GPT.

🤖 AI Assistant fine-tuned to provide support for coding and design questions based on the latest trends in the industry.

AI-powered RAG-based tool for summarizing, extracting insights, and answering questions about research papers with high accuracy

ScrapeGraph client langchain integration

Open Server is an OpenAI API Compatible Server for generating text, images, embeddings, and storing them in vector databases. It also includes a chat functionality.

ChatPDF is a Streamlit app allowing users to query PDF & DOCX content via natural language. It indexes documents for conversational interactions using OpenAI's API & FAISS for rapid matching. Upload, ask, and get insightful responses instantly.