Code agents

Careti: Your New AI Patner : Adding Cursor's Flexibility to Cline's Transparency

Generate captions for videos using the power of OpenAI's Whisper API

Pair Claude Desktop on Anthropic with Claude Code routed through Ollama. Visual walkthrough + copy-paste prompt that cuts your Claude Code bill ~90%.

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

Universal security guardrails and workflow policies for AI coding agents.

Agent skills for AI coding assistants (Antigravity)

Keep AI coding agent configs in sync. One manifest, distributed to every platform.

A full-stack EdTech system for generating, auditing, and managing outcome-aligned assessment questions using Bloom’s Taxonomy, featuring a FastAPI backend, PostgreSQL persistence, and a React-based dashboard.

GPS-aligned AI prompts and Agent Skills for genealogical research (CC-BY-NC-SA-4.0)

The native AI Agent framework for Bun. Build local-first, bare-metal agents with embedded vector search and instant API deployment. 🚀

Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do.

A lightweight subagent extension for the pi coding agent

[Experimental] A coding agent for RStudio

Lumigo's Python Distributed Tracing and Performance Agent for AWS lambda

CLI to Get Whoop wearable data via Rest API, perfect for Agents to be taught as a SKILL

Agent-first GPT Image 2 CLI and installable skill for OPENAI_API_KEY or Codex auth.json.

Code of the NeurIPS 2021 paper: Language and Visual Entity Relationship Graph for Agent Navigation

PGR is an experimental, stateless MCP code-search server for studying how ranking, latency, and output shaping affect agentic search.

Notifications for agent CLIs using brrr.now 📳

OpenAI-compatible proxy for assistant-ui.com free LLM endpoint. Supports streaming, tool calling, vision, and 5 models.

This repository hosts a collection of custom web applications powered by OpenAI's GPT models (incl. o1, o3-mini, GPT-4.5, GPT-4o, and GPT-4o mini), Whisper model, and TTS model. These apps include an interactive chatbot ("Talk to GPT") for text or voice communication, and a coding assistant ("CodeMaxGPT") that supports various coding tasks.

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

A secure, stable Rust alternative to openclaw/moltbot/clawdbot

AI coding agent with more freedom.

NectarGPT is a cutting-edge open-source Chrome extension powered by GPT-X. Automate tasks like coding, writing product descriptions, creating social media posts effortlessly and more. Experience AI-driven productivity and enhanced user experience.

Collection of leaked ChatGPT system prompts, documenting base tools, conditional features, and specialized assistants. Provides insights into the internal structure and behavior of different ChatGPT components and their activation conditions.

Automate PR reviews with LLMs like OpenAI GPT and Google Gemini. Supports multilingual reviews, file exclusions, and custom model selection. Simple setup, smarter code reviews!

Configuration manager for AI coding tools - Claude Code, Gemini CLI, Codex CLI, Antigravity. Manage MCPs, rules, permissions, memory, and workstreams.

Security Scan orchestrator for AI Agents 🎯

A native /slop-review window for Claude Code, Codex CLI, and pi — review the slop before you ship it. Monaco-powered inline comments, agent reads them back. Forked from badlogic/pi-diff-review.

One prompt. Full delivery.

A Git-native knowledge layer for your team — and a set of tool suite that keeps it alive.

Wingman is the fastest and easiest way to run Llama models on your PC or Mac.

songGPT is an experimental open-source project that explores the potential of Language Models, specifically ChatGPT, in generating original and customizable musical compositions. Using Python, the output is automatically converted to MIDI and audio files, enabling users to create unique and diverse music pieces.

Code repository for the NAACL 2025 paper "LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models"

Centralized AI agent skills for Obsidian plugin and theme development.

Skills and plugins to accelerate security workflows with the Orca Cloud Platform

AutoCodeAgent - An innovative AI agent powered by IntelliChain, Deep Search, and multi-RAG techniques

A radically simple, reliable, and high performance template to enable you to quickly get set up building multi-agent applications

A computer for your agent - sandboxed code execution for AI agents

Write detections, investigate alerts, and query logs from your favorite AI agents

Unofficial tools and server implementation for Binance's Model Context Protocol (MCP). Designed to support developers building crypto trading AI Agents.

🐉 Hail Hydra — Multi-headed speculative execution framework for Claude Code. 10 AI agents, 3x faster, ~70% cheaper. Inspired by speculative decoding.

Local AI-powered code review agents for Claude Code

自建 ChatGPT api 反向代理服务，腾讯云函数

OSCAL tools for AI agents

A collection of Agent Skills designed to help AI coding agents build and maintain Swift applications targeting WebAssembly.

An autonomous claude code development team orchestrated by a hook-driven deterministic code workflow. An example repo to inspire your own workflow

Durable Cloudflare computers for agents: run repos, steer live workspaces, verify results, and return receipts.

Every Claude Code resource worth knowing - tools, tutorials, skills, SDKs, and community links. updated weekly so you never miss what matters.

A Thai token optimization tool for AI coding agents that keeps commands, code, and technical details accurate.

AI Testing Agent: Open Source AI Agent for Software Testing

AI coding agent workflow engine for structured task lifecycles.

👨🏻‍💻 Meet Lumina – my personal AI assistant powered by hybrid RAG with Pinecone vector search and Neo4j graph traversal, Google AI, LangChain, and an MCP server with 30+ tools. Features real-time streaming, conversation branching, and a multi-agent agentic AI pipeline for intelligent, grounded responses with inline citations.

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

11 agent skills (Anthropic Skills format) — one `npx skills add` installs the full pipeline for building interactive teaching sites end-to-end on Claude Code / Codex / Antigravity / 55+ AI coding agents. ｜ 11 個 agent skills，一條 npx skills add 把「從零打造互動式教學網站」完整 pipeline 裝進 55+ AI coding agent。

A collection of MATLAB coding rules and guidelines optimized for use with AI coding assistants like Cursor, Windsurf, Claude Code, and GitHub Copilot

The Ultimate Claude Code Workflow - Memory Bank, 14 Agents, 18 Commands, 10 Critical Gap Solutions

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

Every Claude Code session loads every agent, skill, and MCP server you configured, used or not. Audit, archive, restore anytime.

Hermes skill for ACP-style multi-agent delegation (Hermes, Codex, Claude Code).

Blackhat 2025 presentation and codebase: AI SOC agent & MCP server for automated security investigation, alert triage, and incident response. Integrates with ELK, IRIS, and other platforms.

RepoMind is an AI-powered documentation generator for modern codebases that helps developers understand any GitHub repository faster. It analyzes project architecture, folder structures, dependencies, APIs, and core logic to generate clean, intelligent documentation with contextual insights. Built with Next.js, Octokit, RAG pipelines, Pinecone.

AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 90 tools, MITM proxy, stealth browser, autonomous AI agent. Built on Tauri + Rust + React.

Curated index of 200+ AI tools, one writeup per tool with hands-on takes. Covers coding, design, research, video, voice, agents, music, local LLMs. Compare alternatives, see real pricing, find the right tool for the job.

Collective intelligence runtime for AI agents. Knowledge graph + persistent memory.

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). AGPL.

Kronos Agent OS (KAOS): self-hosted runtime for durable AI agents with memory, skills, MCP tools, automations, dashboard, and optional swarm coordination.

Self-hosted MCP server connecting Claude to Odoo 15→19 — 197+ tools, multi-tenant, Bulgaria l10n

114 source-backed /goal contracts for coding agents, plus 200 separated seed patterns.

An undetectable AI assistant that lives on your screen. Solves problems, answers questions, analyzes screenshots — invisible to everyone but you.

HotPlex — Unified access layer for AI Coding Agent.

[ACL'26 Main] Official code for "LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning".

A free, self-paced course for learning OpenCode, the open-source AI coding agent

Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust

GitHub action to integrate https://pi.dev/ coding agent with GitHub-compatible CI/CD, issues and PRs

Codes and data for paper: GrepSeek: Training Search Agents for Direct Corpus Interaction

Research-first project scaffolding for Claude Code. Mines GitHub Issues for production failures before writing a single file.

Lightweight Kanban board for Hermes Agent. SQLite-backed, dark/light themes, drag & drop, auto-detects agents from Hermes profiles.

A local resource sentinel for the multi-agent era — monitors RAM, processes & disk used by AI agent CLIs (Claude Code, Codex, MCP servers), flags leaks/zombies/runaway caches, and proposes AI-driven cleanup you approve.

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

🎭 Battle-tested plugins for Hermes Agent — zero core patches. Native vision bypass, multi-agent context injection, and more.

Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, organized into campaigns, waves, squads, and review gates.

Prompting tests for evaluating LLMs, coding agents, and agentic models

Open-source infrastructure for AI agents — each gets an email address, folder, inbox, and API key. Move files through named inboxes instead of shared cloud credentials; signed receipts and MCP built in. Human email verification can unlock 5 GB transfers, durable storage, outbound email, and an HTTPS app subdomain. One Go binary, MIT.

Show local time on every Claude Code message, and let Claude know when each prompt was sent. Zero-config plugin, cross-OS, graceful degradation.

Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 122 canonical MCP tools, hybrid recall, bi-temporal history, AES-256-GCM. Local-first, air-gap ready, MIT.

Open-source Claude agent skill that teaches Claude Code, Claude Desktop & Claude AI to create and edit professional motion graphics videos with Remotion. AI video editing, B-roll, captions, sound design — from one prompt.

Automate Blender 3D modeling with AI via MCP — 93 tools for modeling, sculpting, architecture/MEP, materials, and 3D-print prep. Includes Blender Studio: a visual record/replay session editor with a multi-provider AI assistant (Claude, Gemini, OpenRouter) — drive it from n8n, Claude Code, or standalone.

Loop-native agent workspace — put your AI coding agents on a canvas, wired into loops that run themselves.

[ICML 2026] Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks

Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class teammates. Live multiplayer, semantic + full-text search. Go + PostgreSQL + React/Milkdown.

329 agent skills (Cursor, Claude Code & Codex), 5,380 OpenClaw skills, 201 ML notebooks, 8 textbooks, 82 research papers, 18 industry reports for PMs, Designers & Developers.

A coding agent skill that helps measure and close the understanding gap in any codebase, research corpus, or documentation set.

Private local meeting rooms where Codex, Claude Code, and other agents collaborate live.

主要为 OpenCode Go 套餐打造的桌面客户端与本地代理：把 Claude Code 和 Codex 接到 OpenCode Go 并查看额度，也支持其他 OpenAI/Anthropic 兼容上游（Anthropic ↔ OpenAI Chat Completions / Responses 协议互转）。

这是一个专为 AI Agent（如基于大语言模型的编程助手）设计的 STM32 调试技能包（Skill）。它封装了常用的 STM32 固件编译、烧录、调试、寄存器查看以及变量实时监控功能，旨在让 AI 助手能够无缝、高效地协助开发者进行 STM32 嵌入式开发。

🛰️ Coding Agent Fleet (cafleet) is a coding agent orchestrator for multi-agents collaboration across coding agent providers

Ollama Cloud plugin for Pi coding agent (API Key based)