Code agents

Multi-AI orchestration framework for Claude Code — coordinate Claude, Codex, and Gemini with 7 workflow modes, parallel execution, and session unification

给一人公司和小团队用的本地 AI Agent 控制台 把 Claude Code、Codex、Gemini、Qoder 等 Agent 放进同一个看板、消息和审查流程里。

Ghost in the Shell powered by OpenAI (Terminal version of ChatGPT)

SourceGPT - prompt manager and source code analyzer built on top of ChatGPT as the oracle

A tool to interact with Windows drivers to perform a raw disk read and parse out target files without calling standard Windows file APIs

A python code to interact with the GPT3 API to train the chatbot and use it.

Build super simple end-to-end data & ETL pipelines for your vector databases and Generative AI applications

Locally hosted AI code completion server. Like Github Copilot but 100% free and 100% private.

Official Code for "EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting (ICCV 2023)"

CLI built for AI agents to help navigate codebases better. An alternative to grep/find/glob

Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM (Gemini/OpenAI/Claude/Ollama), FastAPI + Docker, production-ready in 3 min

Complete visual content system for Claude Code — 16 workflows, 2 AI models, aesthetic routing, and brand customization.

Allows AI agents (e.g., Cursor, Claude Code) to debug within Tauri apps via screenshot capture, window management, DOM access, and simulated user inputs.

A Rust based terminal workspace for multiple AI coding CLIs in parallel (windows supported)

Like “oh-my-opencode”, but for Cursor IDE. Multi-agent orchestration, natively, using nothing but a few config files.

🚀 Grounded AI development for Dynamics 365 Finance & Operations. Indexes 580K+ X++ symbols (standard, ISV, custom) and exposes 26 MCP tools that prove every method, field, label and form pattern against your real metadata before the AI writes code. Works with GitHub Copilot, Claude Code, Cursor & Visual Studio.

MCP server for OpenAI's Deep Research APIs, Gemini Deep Research Agent, Allen AI's DR-Tulu, and Hugging Face's Open Deep Research

Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.

Let your AI Agent review your iOS/Android apps for appstore policy & security bugs with ipaShip's web app, cli, mcp or claude-skill with safety hooks layer any any llm agent you use - loopin fixes in dev stage only no more waits till submissions.

ZoneMinder client for iOS, Android, Windows, macOS, Linux and web. Live camera view, event review, montage, timeline, push notifications. Rewrite of zmNinja.

A set of Claude Code and GitHub Copilot plugins providing the AI Literacy framework's complete development workflow — harness engineering, agent orchestration, literate programming, CUPID code review, and the three enforcement loops

OpenAI/Anthropic-compatible AI router that keeps apps online with provider failover, key rotation, caching, analytics, and local-model fallback.

🚀 One-command requirement development flow for Claude Code - Complete workflow system with sub-agents, quality gates, and intelligent automation

🎙 Local zero-cost audio→markdown/docx pipeline. Whisper + AI cleanup. Replaces Otter.ai/飞书妙计. Agent-ready (Claude Code/Codex/Copilot/Cursor). macOS/Windows/Linux.

A Claude Code plugin that fills your job applications from your profile, drafts the cover letter, and leaves Submit to you. Locally.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE, native video/document understanding, long-horizon tool agents, quantization-aware training. Scales: Tiny (25M) to Large (1.3B).

CCswitch的全面升级，专门优化codex体验。支持官方订阅和第三方模型混用，自动路由，支持v2subagent使用第三方模型

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

Local-first service attribution, stale development server detection, AI runtime health monitoring, and open-weight model capacity planning.

AI-agent skill producing reusable Markdown from PDFs. It turns flowcharts, diagrams, and charts into text beside each caption instead of empty links. It checks an earlier conversion against the PDF and fixes misread or missing parts. Long PDFs run in small saved batches with an independent review pass, each paragraph tagged with its page.

Build AI Agents like playing LEGOs. Everything is a Plugin.

Automatically turn successful DeepSeek Harness sessions into reusable, reviewable Agent Skills.

Rank LLMs, RAG systems, and prompts using automated head-to-head evaluation

Academic Personal AI Infrastructure

Your own Coding Agent 🤖

An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP). This server is built with the FastMCP framework, which enables LLMs to explore and query SQLite databases with built-in safety features and query validation.

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

🤖 Autonomous AI-powered ethical hacking agent powered by Llama 3.1 70B on NVIDIA NIM

HACS custom integration for using Whisper speech-to-text (OpenAI, GroqCloud or Mistral) API in the Assist pipeline, reducing the workload on the Home Assistant server.

Deconstructing Claude Code — interactive source code analysis, guided wc/helpe walkthroughs, and deep architectural exploration of Anthropic's AI coding agent.

multi-depth architecture views for code understanding and generation in extremely fast speed

Scala code intelligence for coding agents. Zero Build Server. Zero Compilation. Just answers.

WinDbg Copilot - Agentic Debugging extension

Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama while using Claude as the main LLM.

🛡️ Portable credential management for AI agents — Age encryption, session leases, killswitch

Enterprise RAG ecosystem managing 32000+ semantic chunks. Features hybrid parsing (LlamaParse/PyMuPDF) and 256-dim MRL embeddings for 512MB RAM environments

Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components (personas, protocols, formats, templates) that snap together into reliable, repeatable prompts for bug investigation, design docs, code review, security audits, and more. Works with any LLM.

Agent Skills Hub is a global library of AI agent skills that work across OpenClaw, Claude Code, Gemini, Cursor, Antigravity, and more.

Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64).

Production-style LangGraph reference implementation for reliable multi-agent workflows with typed state, review loops, human approval, checkpoint-ready execution, and structured artifact delivery.

The Orchestration Layer for AI Coding Agents

The AI Agent designed for work with security in mind.

ComPDF Skills are AI-agent-ready PDF processing skills for Claude Code, Cursor, Copilot, OpenCode, and 39+ coding agents to convert, edit, split, insert, compare, compress PDFs, and more.

Local-first macOS menu bar app for Codex usage limits and reset credits.

Stop re-explaining yourself

Your local-first command center for working with AI agents like a real team.

transformers gguf llama llama-2 text-generation code

Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.

Turn a goal into a supervised run.

15-minute AI-agent positioning session for startups: forced choices, a sub-30-word statement, co-founder compile, and a 90-day proof plan. Claude Code / Cowork / Codex.

Verified AI dependency migrations. Finds which of your lines a version bump actually breaks, fixes them, and proves the result still compiles and passes your tests.

The open registry of affiliate programs. Built for developers and AI agents.

多智能体深度研究系统，融合私有知识图谱(GraphRAG)与联网搜索，含 Harness 编排、持久化 Memory 与受控自进化 Skills，FastAPI + React 全栈。

OpenAI Privacy hackathon - Paris, 🏆 winning project

Adapter-driven control plane for coding-agent work: tasks, goals, run DAGs, gates, verification, and state sync.

Codex CLI and Claude Code CLI on your phones. No computers required.

Claude Code integration for OpenPets: automatic desktop pet status updates with one-command setup.

Beginner-friendly repository for launching your first LLM API with Python, LangChain and FastAPI, using local models or the OpenAI API.

3-tier agentic ChatOps (n8n + GPT-4o + Claude Code) implementing all 21 patterns from "Agentic Design Patterns" — solo operator managing 137 devices

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

🤖 Autonomous development orchestrator for the BMad Method. Runs fully autonomous, parallel, multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint backlog and dependency graph.

5 Claude Code skills for product managers. Drop them in your .claude/skills/ folder and go.

Chat, specs, tasks, and code. An autonomous engineering platform. Full autonomy when you trust it. Full control when you don't.

Data-Agent：从 0 到 1 构建 Text2SQL 智能体实战教程，覆盖 StateGraph 编排、双重 RAG、关系图谱、HITL 人工确认、SQL 自动纠错、Python Docker 沙盒执行与 A2A + SSE 流式交互。

Daofy for Delphi — MCP Server that compiles Delphi projects and queries knowledge base for AI assistants.

hermes-agent源码解析

50+ AI agent skills for Claude, Codex, OpenClaw etc — agentic marketing automation, AI creative agency, and developer productivity tools

maw — CLI for running multiple AI agents across machines via tmux. Wake agents, talk across nodes, watch screens, track cost. Engine-agnostic (Claude Code, Codex, Aider, OpenCode), built on Bun.

Official samples and developer tools for building on SharePoint Embedded, the document storage API on Microsoft 365. Includes React, TypeScript, and ASP.NET Core boilerplates, an MCP server for AI coding agents, Copilot and Power Platform assets, Postman and Bruno collections, and admin scripts.

Open-Source Intelligent Command Layer

Lightweight Codex/Claude loop harness with strict evidence gates.

55 MCP tools to drive the Unity Editor from any MCP-compatible AI agent — scenes, GameObjects, prefabs, assets, tests, and builds. OpenClaw gateway included for remote and chat access.

Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.

Awesome Open Data Agent Platform resources: open data access, semantic layers, multi-agent SQL, memory, governance, and GenBI.

给 AI Coding Agent（Claude Code / Cursor / Codex / Gemini CLI）用的 **技能版 npm** —— 本地优先、模型无关、MCP 原生。

1200+ AI models in your GitHub Copilot Chat — free & forever free. VS Code extension powered by OmniRoute: 340+ providers (90+ free) — Kimi, Claude, GPT, Gemini, GLM, DeepSeek, Qwen — with agent mode, tool calling, vision and quota-aware auto-fallback. MIT.

Turn npm, Python, and Rust release evidence into bounded Codex maintenance tasks.

Open-source starter stack for Agent product developers: desktop client, control plane, workers, multi-agent workflows, admin, mobile, and operations.

A bot that comments on tweets containing a specified keyword. The bot uses the OpenAI API to generate comments and the Twitter API to post them. It is designed to run continuously, with a fixed delay between each comment.

A multi-agent system designed for generating music videos with scrolling subtitles based on lyrics. This project analyzes the lyrics and creates detailed prompts based on the analysis results to generate story-like images, ultimately producing an image-to-image music video, using openai API, gpt-4o and dall-e 3 models.

AURA (Agent-Usable Resource Assertion) is an open protocol designed to make the web machine-readable. It replaces fragile screen scraping with a declarative aura.json manifest, allowing websites to expose their capabilities as a secure, efficient, and standardized API for AI agents.

A nonebot plugin base on OpenAI API (gpt-3.5-turbo)

This is the source code of "Efficient training techniques for multi-agent reinforcement learning in combatant tasks".

[NeurIPS2021] Federated Reinforcement Learning with Theoretical Guarantees. The repo contains code and experiments for our Federated Policy Gradient with Byzantine Resilience framework for improving sample efficiency of RL agents.

Deep Research based on Claude Code's agentic framework 🦉⚡ export const SPINNER_VERBS = [ 'Accomplishing', 'Actioning', 'Actualizing', 'Architecting', 'Baking', 'Beaming', "Beboppin'", 'Befuddling', 'Billowing', 'Blanching', 'Bloviating', 'Boogieing', 'Boondoggling', ...]

Astraeus Σ-9000: A Claude Code–native, zero-shot meta-agent orchestration compiler prompt engineered for one-time repository bootstrapping within deterministic, agentic development environments.

A persistent, daemon-based multi-agent system that leverages opencode to automatically discover, plan, implement, and review code changes across a codebase.