Code agents

A curated collection of AI, data engineering, and DevOps projects featuring real-world applications, advanced techniques, and tutorials—ideal for learners and practitioners exploring data science and machine learning.

Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"

Repository-level Repair Agent Based on SWE-Bench—JoyCode Agent

Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud

VC - AI-orchestrated coding agent colony

AgentClaw turns one-sentence ideas into reusable Claw capabilities. Build less boilerplate with declarative workflows, computer browser code file control, MCP, Skills, memory, knowledge bases, tracing, scheduling, and API/MCP publishing.

Open-source control plane for AI coding agents — run, monitor & orchestrate dozens of parallel Claude Code, Codex & Gemini sessions from one web dashboard or your phone. Self-healing, single-file, tmux-native.

Multi-agent demo platform for Titans (arXiv:2501.00663) — neural networks that learn to memorize at test time. 7 AI agents, native desktop UI.

A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时：快速开发、验证和恢复复杂 AI 工作流，并将其稳定交付为服务。

AI-powered companion for Homebox. Snap photos and let AI auto-identify and catalog items into your inventory, then use the AI Chat to organize, search, and update your inventory effortlessly.

A local OpenAI- and Anthropic-compatible proxy that brings your Claude Pro/Max subscription to Cursor, Cline, Aider, and the Agent SDK. Session-affinity routing, multi-account pooling, and live drift detection keep long agent runs stable across tools.

Just say what you need. Flowent gets it done.

Open Source Agentic Business Intelligence with Malloy Semantic Layer :tada:

ChatGPT Bot in CLI with long term memory support using Embeddings.

An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.

The IQ Series is a hands-on learning experience for Microsoft IQ: Microsoft's unified intelligence layer for the enterprise, spanning Foundry IQ, Work IQ, and Fabric IQ. The series includes video episodes, Jupyter notebooks, and Azure deployment templates.

Your Intelligence, Orchestrated. Every builder. Every team. Every agent. For Everyone.

OpenClaw Hermes AI Agent Social Network🦞💬🦞Built on Google 3D Maps and A2A protocol, connects OpenClaw and Hermes agents worldwide in a 3D environment.

OpenAI API Client for PHP. Includes all endpoints and models (DTOs) for all requests and responses.

Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.

Host Agent for AWS CodeDeploy

分门别类的 ChatGPT 中文引导语大全。

基于 Gemini 的可视化多智能体深度推理引擎 | A visual multi-agent deep reasoning engine powered by Gemini, featuring dynamic planning, chain-of-thought visualization, and multi-session management. Built with React 19 + TypeScript + Vite 6.

Mochi is a small, fast, embeddable programming language designed for agents, data, and AI. It combines functional syntax, stream-first semantics, and native support for datasets, graphs, and simulation.

OpenAPI to Agent Skill for context-efficient AI agents

Full-stack Typescript framework that ships web, iOS, Android, server, and database together.

把工作流变成可研究、可评测、可发布的乔木 Agent Skill | Turn workflows into researched, tested, release-ready agent skills.

An Autonomous LLM Agent that runs on Wizcoder-15B

Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.

[ BOF-LAUNCHER ] -> an API for loading, executing and in-memory masking BOFs on Windows and Linux for use in C/Zig/Go/Rust agents/implants. [ Z-BEAC0N ] -> a custom-written stage-1 (aka pre-C2) solution engineered with a small footprint, stealth and modularity in mind. [ DEVELOPED BOFS ] -> cross-platform (12), Linux-only (10), Win-only (2)

Codemogger is a code indexing library and MCP server for AI coding agents

chatgpt、claude、midjourney，grok和gemini官网完整还原，以及Claude Code和Codex完整镜像，包含其官网的全部功能。具有完善的用户体系和流量变现体系。

Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents.

Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patterns, SOLID principles, and testing — for Claude Code, Cursor, Copilot, and any SKILL.md-compatible agent.

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture)

Lightweight VPS monitoring with agent + server + web dashboard. Rust + React monorepo.

All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.

The official implementations of Agent-as-a-Router: Agentic Model Routing for Coding Tasks.

Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.

Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.

🤖 Telegram Bot API PHP SDK 4.x. Create Telegram Bots with PHP Easily! [WIP]

just like spatz... but for svelte5, with shadcn-svelte, svelte-animations, svelte-superforms, stripe payments, subscriptions, content-filtering, and more.

Official code for "Self-Distilled Agentic Reinforcement Learning"

An instruction layer for AI coding agent

An ai-assistant chat app that using your own OpenAI/Claude API key.

基于LangChain和LangGraph实现的AI Agent配置平台

AI-powered legal compliance assistant for alcohol beverage pricing laws — extracts, analyzes, and explains New York state-level regulationsusing RAG + knowledge-graph reasoning.

Samples using AI and Azure SQL DB

Mobilewright is a dev framework for Mobile App Testing and Automation. It allows testing iOS/Android app on real devices, emulators and simulators with a single API.

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

Chinese-localized spec-driven development toolkit for Codex, Claude Code, Cursor, and other AI coding agents.

Open-source AI Agent platform for teams. Your agents don't just chat — they read files, run code, call APIs, and deliver results.

Use Claude and GPT through one local gateway with OpenAI-compatible and Claude-native APIs.

Integrated AI environment in the terminal. Build, test and instruct agents.

一键给Claude Code 提高智商，包含生产级 agents、skills、hooks、commands、rules 和 MCP 配置

Stop babysitting local AI agents. Just notifications, approve, and resume your Codex,Pi,Grok, or Claude code sessions anywhere. 0-Intrusion mobile control bridge via Telegram/微信/飞书. No hooks, no skills, no MCP.

JARVIS: a real-time agentic intelligence-gathering platform powered by autonomous web scraping & OSINT, streamed via Meta Ray-Ban smart glasses

One dashboard for all your local AI coding agents. Switch providers, manage sessions, and orchestrate tasks across Codex, Claude Code, Gemini CLI, CodeBuddy Code, Pi, OpenCode, KiloCode, and OpenClaw. Zero cloud, local-first control plane.

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

Write-time code quality enforcement system for Claude Code. Every file edit triggers automated formatting and linting through fast Rust-based linters and dedicated Claude instances that intelligently fix remaining violations

Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.

Source-available, self-hosted platform for building AI agent flows - visual editor over a Django backend.

transformers safetensors iquestloopcoder text-generation conversational custom_code

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

PlanWeave is a file-backed loop engineering system for long-running coding agents. It turns fuzzy plans into claimable tasks, routes them through implementation and review agents, records every run, and keeps the loop recoverable.

💀 It's headless WordPress!

LLMs Best Tricks

Code for the paper "FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents" arXiv:2502.07393

📄 [Skill] Vision-in-the-loop LaTeX typesetting agent — auto-compile, render, diagnose, and fix paper layouts

🤖👾🐶 下一代 Agentic 桌宠 = LLM + 记忆 + 情感 + RPG + Claude Code Next Gen Agentic Desktop Pet = LLM + Memory + Emotion + RPG + Claude Code

Anti-detect browser automation CLI & Skills for AI agents — Camoufox-powered fingerprint spoofing, no bot-detectable Playwright leaks

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.

🚀 Give Claude AI superpowers for GitHub workflows. Transform "fix stuff" commits into professional messages, generate intelligent changelogs, and get AI code reviews - all with one command.

A Modern GUI Interface for Vector Database Management(Supports MCP integration)

有啥问题抖音私我，我后面攒起来更新

Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search

23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.

The easiest way to run the fastest MLX-based LLMs locally

[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"

QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.

Simple self-hosted web application, which can be used to convert audio to subtitles by OpenAI's Whisper model

Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP

Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync

Make function calling with LLM easier

ReconNess is a platform to allow continuous recon (CR) where you can set up a pipeline of #recon tools (Agents) and trigger it base on schedule or events.

Run Claude Code/Codex within AgentFS, orchestrated by LlamaIndex Workflows

AI-native ClickHouse console for your cluster diagnostics and query generation, optimization and data visualization.

ThunderAI is a Thunderbird Addon that uses the capabilities of ChatGPT, Gemini, Claude or Ollama to enhance email management.

Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, commands, and workflows for Java, TypeScript, Python, PHP, AWS, and AI.

Smart(er) code reading for humans and AI agents. Reduces cost per correct answer by ~40% on average. Install: cargo install tilth -or- npx tilth

A Fork of Rikkahub with an overhauled UI and feature additions

Auto-retry Claude Code on subscription rate limits, API overload (529/5xx) and safeguard false positives — waits for the printed reset, exponential backoff, tmux-based

PandaAGI provides a simple, intuitive API for building general AI agents in just a few lines of code

Polymarket Polymarket AI trading AI trading prediction markets prediction markets paper trading paper trading OpenAI OpenAI Node.js Node.js Express Express Docker Docker CLOB CLOB mean reversion mean reversion dashboard dashboard crypto bot crypto bot SQLite SQLite automated trading automated trading API API research trading research trading

Full-stack Next.js 14 application. Uses React 18 client & server components, TypeScript, Prisma ORM, Railway PostgreSQL database, NextAuth.js OAuth 2.0 authentication, OpenAI API GPT-3.5-Turbo, and Stripe payments.

Demonstrates how to protect your OpenAI API Key using a Cloudflare Worker to serve your ephemeral token and then do client side tool calling

An in-depth book and reference on building agentic systems like Claude Code