Code agents

Two agents spar over one codebase until every review finding is reconciled.

AI-powered desktop localization for game mods: Paradox games and Surviving Mars: Relaunched, with RimWorld and Project Zomboid in preview. Local-first projects, format validation, translation packages, and built-in / Codex agents.

ClawGuard is a comprehensive security toolkit designed to mitigate risks associated with autonomous agents, such as OpenClaw and other LLM Agents.

My near-autonomous workflow for coding agents

A modular simulation framework for controlling multiple drones in a PX4-based environment. It features ROS 2 integration, G-code trajectory planning, multi-agent communication, and a Dockerized setup for easy deployment and visualization.

Desktop command center for managing multiple AI coding agent sessions across codebases. Multi-agent orchestration via MCP.

A persistent management layer for Claude Code Agent Teams

Build, deploy, and orchestrate teams of Claude Code AI agents on Slack

Korean translation of "Harness Engineering: From Claude Code Internals to AI Coding Best Practices" — Claude Code 소스 코드를 체계적으로 분석하여 AI Agent 시스템의 핵심 엔지니어링 패턴을 추출한 기술서의 한국어

Long-task-oriented video analysis skill for Claude Code (/vea) — resumable staged execution, automatic parallel scoring, OpenClaw orchestration, audiovisual analysis with agent handoff

Free Gemini web interface proxy for OpenCode - Use your free Gemini subscription as an OpenAI-compatible API with full tool calling support

A coding agent with a new context-engineering framework — bounded, deterministic, reconstructed context (the Slice), built for long-horizon work.

An MCP server for safer coding agents: skill routing, C4 workflow gates, memory checks, and verification before completion.

Mission control for parallel Claude Code & Codex sessions — a live grid of coding agents that glow when they need you, across multiple accounts, resumed after restart.

Cybersecurity knowledge graph for code review with evidence-backed answers

Self-hosted, Elixir-native alternative to LiteLLM: one API for multi-provider routing, fallbacks, budgets, keys, and observability.

Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

Read-only trading journal and review harness: Jev typed judgments, agent integration, and a reproducible finance benchmark. No orders, no advice.

Talk to your coding agents — press a hotkey, speak your prompt, and it lands in Claude Code, Codex, or Cursor. Fully local voice dictation (Parakeet + Gemma), nothing leaves your machine. Windows, macOS & Linux.

High-assurance, artifact-agnostic prompt for authorized security labs, exploit-chain research, PoC validation, and evidence-led reporting.

Agentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, orchestrating the full QA lifecycle: shift-left planning, in-sprint testing, TMS documentation with ROI scoring, KATA automation, and regression with GO/NO-GO. Works across Claude Code, Opencode, etc.

FastAPI reference app for Statewave memory integration. Wraps every chat turn with get_context before the LLM call and record_episode after; seeded demo users show compiled facts and token-budgeted context. Self-hosted, Postgres + pgvector.

Use Claude Code without the terminal. Pick a folder in a window, type in plain English, and Anthropic's AI agent does real work on your own files: spreadsheets, documents, whole folders. Built for people who do not write code. Windows and macOS, free and open source.

Markdown 长文渲染成小红书 3:4 图片组的 Agent Skill，全文不删减，内置 5 种风格（Cursor / Claude Code / Codex 通用）

Run Geoffrey Huntley's Ralph Wiggum loop inside Pi, no shell scripting needed. Native commands control the loop, and the bundled agent skill writes the whole plan from a simple goal. Better than Codex goals and Claude workflows!

Scaffolding skill + always-on conventions (CLAUDE.md/AGENTS.md) for Quarkus + LangChain4j agentic AI apps: AI services, multi-agent workflows, and RAG. Installable in Claude Code, Codex, Copilot, Cursor, and any Agent Skills-compatible agent.

See your AI agents work. Real-time 3D visualization of Claude Code activity, multi-agent orchestration, and REST API integration for external systems.

A self-running research agent that monitors the web on your schedule, verifies findings with LLM analysis, and delivers intelligence reports by email and in-app.

Markdown 长文渲染成小红书 3:4 图片组的 Agent Skill，全文不删减，内置 5 种风格（Cursor / Claude Code / Codex 通用）

An autonomous coding agent that owns its whole loop — engine, workbench, and memory. Apache-2.0.

Claude Code agents and skills for automated Playwright E2E test generation, debugging, and planning using the Page Object Model pattern

Local AI code review for coding agents. Rules enforced inside Claude Code, Codex, and Cursor. Free, open-source, fully local.

Open-source, self-hosted AI gateway for multi-tenant orgs: OpenAI-compatible LLM routing, RAG & vector stores, MCP hub, GPU fleet (MIG slicing), sandboxed coding agents, AI red-teaming & guardrails, and cost optimization — all in one console.

An autonomous AI Research Agent Telegram bot powered by NVIDIA NIM (Mistral Large 3), DuckDuckGo search, and BeautifulSoup for real-time web scraping and comprehensive report generation.

transformers safetensors qwen3_5 image-text-to-text veriloop veriloop-coder

Autonomous coding platform (runtime over harness)

Toolkit for AI whitehats, internal red teams, llm bug bounty hunters and mlops - Adversarial testing for AI, LLMs, and Agents.

Comprehensive toolkit for AI-assisted development: Claude Code permissions (400+ tools), Git workflows, and automation hooks

Train AI coding agents with RL (GRPO) on Prime Intellect — works with Pi Agent

Claude Code Agent Skills

The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first, MCP-native, open source.

让规则真正被执行、让结论真正可复算的工程治理元 Skill：三级跑道／L3 封闭清单+清单外高危域执行层枚举／必问协议／GATE 12 字段可复跑证据+验证层级 ev=／判据版本化 j2.5+金样本回归 23/23／373 条 30 类症状索引细则；含流程包（9 类工作流）与角色包（8 角色）；五平台注入适配+副本内容哈希验收。

Official repository for MiniAppBench. Contains the complete pipeline and codebase for LLM-powered interactive HTML generation and agentic evaluation (MiniAppEval).

Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds compact context packs for Claude Code, Codex, Cursor, MCP, and more.

Deep-dive notes and source code analysis of Claude Code and AI agent harnesses. Exploring memory mechanics and internal architectures.

Agent Smith has taken over your terminal: he recursively breaks down tasks and mercilessly executes them with Claude Code CLI/Opencode/openclaw until your project is "assimilated." Red pill or blue pill? On GitHub, only cloning his code matters.

Repo-native AI orchestration engine — connects issue trackers (GitHub, GitLab, Linear, webhooks) to coding agents (Claude, Codex, Copilot, Pi) with isolated workspaces and a live TUI.

One command to keep secrets out of AI (LLMs). Works with Claude Code, Cursor, Copilot, Windsurf, and any AI coding tool.

MCP-based code knowledge graph and budgeted context subgraph retrieval for AI coding agents.

LLM-powered MCP server for building financial deep-research agents, integrating web search, Crawl4AI scraping, and entity extraction into composable analysis flows.

RPG Maker MV Ultimate — AI copilot (MCP): generate maps, edit the database & events, and understand your project (validate references, explain why an event never fires, critique maps).

Self-hosted A-share multi-agent research desk: 15-agent debate, optional Tushare Level-2 order queue, K-line workstation with AI insight, and a signal translation layer so models read conclusions — not raw dumps. AGPL-3.0.

OWASP GenAI Data Security Initiative — taxonomies, crosswalks, datasets, and tooling for securing data in generative AI systems

Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

gguf llama-cpp ollama moe qwen code

AI-powered pre-submission audit for Apple App Store & Google Play Store. 140+ rules across 21 categories to catch rejection risks before you submit. Works with Cursor, Claude.ai, Gemini, Copilot, Windsurf & any AI coding assistant.

DeepSeek Harness 长期记忆插件：四通道检索融合 + 记忆演化闭环，记忆构建与检索方法来自 ICLR 2026 论文 MemGAS。Long-term memory plugin for DeepSeek Harness (dsh).

Code and Data for Paper "EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments".

Build, share, and talk to autonomous Voice Agents powered by Vapi & ElevenLabs. (Built as a part of Vibe Coding Hackathon)

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an agent edit code and train under governance: frozen task, scorer, and evidence.

Build production-ready AI agents with the Strands Agents SDK and AWS services. This repository demonstrates how you can create multi-modal systems with persistent memory in minimal code. Progress from your first agent to production-ready systems through hands-on chapters.

Unified multi-agent orchestration layer for Claude Code with parallel execution, session persistence, and natural language routing.

The official code base for paper AAAI2026 <MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models>

Real-time agent visualization in pixel office for Claude CLI and Claude macOS app with basic Codex support /// Real time визуализация ИИ агентов в виде пиксельного офиса для Claude CLI и Claude macOS app с базовой поддержкой Codex.

Animated macOS desktop pet and AI coding agent monitor for Claude Code, Codex, Cursor, and Pi, with local and remote SSH session tracking.

Agent team plugins for Claude Code - pre-configured teams of specialized agents that collaborate on complex tasks

AI agent skill pack for RPG Maker MV/MZ — teaches Claude Code, Codex, and Cursor to safely read and write RPG Maker project files

Marketing & growth skills for AI agents (Claude Code, OpenClaw, etc.)

AI-powered trading skills for Claude/Gemini agents. Backtesting, edge research, market analysis, strategy design, and more.

Agent skills from Xcode 27, packaged as a Claude Code plugin

Mirror of MengTo/Skills — agent skills for Codex, Claude, and Cursor (MIT, © Meng To). Upstream: github.com/MengTo/Skills

Claude Code + Higgsfield as an automated video production studio: 19 skills, prompting playbook, agent operating manual, and real shipped production prompts

本地优先的 AI 求职工作台：采集与管理 BOSS 直聘岗位，基于真实经历匹配 JD、定制简历并准备面试，支持 MCP 接入 Claude Code、Codex 等 Agent。

AI side-panel assistant for Chrome. Reads the active page and acts on it with your approval — click, type, switch tabs, fill forms. Multi-LLM, reusable Skills, recordable workflows, MCP bridge to Claude Code / Codex / Trae, optional Node/Playwright runner.

Open-source local AI Agent desktop app for authorized security assessment — Electron + Mastra-powered runtime, visual pentest workflow, Kali sandbox, multi-provider LLM routing. 本地 AI 安全评估智能体桌面应用

🤖 Hermes Agent + 9Router + OmniRouter on a free Hugging Face Space — one-click deploy with a beautiful web wizard (Telegram bot, web dashboard, OpenAI-compatible API, hourly backups)

Self-hostable, multi-tenant AI agent service with sandboxed code execution（可自托管的多租户 AI Agent 服务，支持沙盒隔离执行）

React debugging in Chrome DevTools: a 5-view panel (Dashboard/Profiler/State/Effects/Settings) with render+memory profiling, issue detectors, a Redux inspector, AI analysis, and an MCP server for coding agents.

Scrub Data: A Framework for Reproducible Data Curation with AI Coding Agents

Codebase-level adversarial review by a panel of frontier models. A Claude Code skill that runs every file through DeepSeek + Gemini + Kimi + MiniMax in sequence, then has Claude verify the findings against the actual source.

An explainable AI system that combines Graph Intelligence, Vector Search, and Retrieval-Augmented Generation (RAG) to deliver grounded answers and transparent reasoning paths. Includes a FastAPI backend, Streamlit UI, FAISS vector index, and an in-memory knowledge graph for hybrid retrieval and recommendations.

A fork of obsidian-terminal with AI-focused enhancements for seamless integration with Claude Code, Codex, and other AI coding tools.

Codai is an AI programming tool that boosts coding efficiency and empowers non-programmers. Its future plans include introducing a local database, enabling customization, and building a versatile AI terminal. It aims to popularize AI programming and lead the AI Programming+ era.

Use NavamAI to supercharge your productivity and workflow with personal, fast, and quality AI. Turn your Terminal into a configurable, interactive, and unobtrusive personal AI app. Power of 15 LLMs and 7 providers at your finger tips. Pair with workflows in Markdown, VS Code, Obsidian, and GitHub. Get productive fast with three simple commands.

WPF application to operate OpenAI API

🤖 A Telegram bot that integrates with OpenAI's official ChatGPT APIs to provide answers.

IDE for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine - now on Windows

Agentic-RAG Framework: A high-performance knowledge retrieval system featuring Hybrid Search (FAISS + BM25), RRF Re-ranking, and MySQL/Redis persistent storage.

Smart assistant for threat monitoring, attack prevention, and web protection.

An open-source AI coding agent for the terminal. It remembers you and your projects, so you don't have to explain yourself twice.

飞书 + cc-connect + Claude Code：把 AI 编程助手装进聊天框。免梯子、手机控电脑、24h在线、成本极低。

Context-efficient command runner for coding agents.

The creation pipeline for Claude Code products — research, create, validate, publish. 13 types, 20 quality patterns, zero coding required.

Code and data for COLING2024 paper "Characteristic AI Agents via Large Language Models".

n8n mcp rules provdes pre-configured prompts that show AI coding agents how to use Synta MCP for n8n workflow automation, which enables AI models to build, validate, & debug n8n workflows with deep knowledge of the platform's complete node library, allowing smart workflow-creation real-time error checking & expert troubleshooting assistance

Techniques and tools for optimizing how AI coding assistants understand your codebase, with a focus on cost reduction and efficiency.

Lightweight server for developing conversational agents using Microsoft AutoGen 0.4

A powerful, self-extending MCP server for dynamic AI tool orchestration. Features sandboxed JS execution, capability-based security, automated rate limiting, marketplace integration, and a built-in monitoring dashboard. Built for the Model Context Protocol (MCP).

Workflow transpilation and execution framework - import LangChain, Airflow, GitHub Actions, Kubernetes, Docker Compose

Access control for AI agents. MCP proxy + Policy Decision Point. CEL policies, RBAC, full audit trail. Any container, any sandbox.