Code agents

Pega DX MCP Server - Enabling conversational interaction with Pega Infinity™ applications. This MCP Server transforms Pega Infinity™ interactions into intuitive, conversational experiences through the Model Context Protocol.

An autonomous AI agent that reads your whole project, runs commands, and writes & verifies code on its own — going deeper than autocomplete. Bring any model, hosted or local.

Self-evolving skill engine for Claude Code — skills that create, score, repair, and harden themselves through recursive improvement loops

Checkpoint everything git misses in AI agent workspaces. Save, fork, push to any OCI registry.

MiniMax shipped Kimi's office skill codebase with find-and-replace. 13 byte-identical files, hardcoded 'kimi' in source, DLL compiled from kimiagent/.kimi/skills/.

Remote control for Claude Code, Codex, Pi and Opencode.

LLM-adaptive embeddings (Zero-shot / LoRA) with Generative Topic Modeling & Agent-based workflow for social science text mining

Bash script to update Claude Code's project references after moving a folder to a new path

Control Antigravity AI from Discord — send natural language tasks, schedule or run instantly, and get results back in real time.

Skills, sub-agents, and playbooks for Claude Code, Cursor, and any Agent Skills-compatible AI coding assistant.

A Tool to give your LLM access to your Kernel.

An opensource icon generation tool based on OpenAI gpt-image-1.

Red Team + Blue Team agents for Claude Code. Automated security auditing with ~100 lines of Markdown each.

Multi-resource rate limiting for LLM APIs. Reserve tokens before you call, refund what you don't use, stay under the limit across workers.

🧠 A powerful, fully featured MCP Server for interacting with AI agents powered by @Openapi®

A flexible platform that provides Docker & Kubernetes backends, a lightweight CLI (mcpt), and client utilities for seamless MCP integration. Spin up servers from templates, route requests through a single endpoint with load balancing, and support both deployed (HTTP) and local (stdio) transports — all with sensible defaults and YAML-based configs.

Stealthy Prompt Injection and Poisoning in RAG Systems via Vector Database Embeddings

💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go

Benchmarking platform for evaluating AI agents on CTF-style tasks and tool-use workflows.

太医院 — Agentic Longevity OS with 10 AI physicians. N-of-1 trials, cross-module pattern detection, PubMed-grounded insights, Bayesian causal inference. Works with Claude Code & OpenClaw.

AI skills for Claude Code. Product marketing, strategy & GTM frameworks by a product leader and full-stack builder in the age of AI.

Protect .env secrets from AI coding agents. CLI (Rust) + VS Code extension. AES-256-GCM vault, OS keychain, Touch ID, smart sandbox values. Agents see fakes — you see the real ones.

Low-Cost Cross-Domain Web Structured Information Extraction using specialized LoRA adapters.

Local-first web UI for exploring your X/Twitter bookmarks

Coordinate multiple computers running Claude Code through git-based messaging. Includes Fleet Commander — an interactive browser game to learn the system.

Your AI development team — 27+ agents and 21 skills that build, review, debug, and ship production code. Works with Claude Code, Cursor, VS Code, Windsurf, Codex, and OpenCode. 7 framework packs: Vue, React, Next.js, SvelteKit, Angular, Astro, Nuxt.

Agent Droid Bridge gives AI agents programmatic control over Android devices and emulators via ADB, exposed as an MCP server.

Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

Claude Code skills for brand development, image generation, and frontend design — built around the convergence problem. LLMs generate the average. These workflows escape it.

Claude Code in a Docker image built on aicodebox, with an HTTP API, an OpenAI-compatible endpoint, an MCP server, a Telegram bot and a cron scheduler, in minimal or full-toolchain variants.

Always-on local AI assistant and AI coding agent runtime in Go. OpenClaw, Claude Code, Codex, and OpenCode alternative with Terminal TUI, Telegram, MCP tools, SQLite memory, approvals, scheduled tasks, and subagents.

WhatsApp MCP Server — Connect AI agents to WhatsApp via Model Context Protocol. 61 tools, 10 resources, 12 real-time events. Supports Baileys (WhatsApp Web) and Cloud API. Built with TypeScript, BullMQ, and Docker.

Unofficial Node.js client for gemini.google.com.

Natural language AI assistant for Autodesk Revit using MCP (Model Context Protocol)

AI learning engine — turn YouTube videos, documents, and text into study notes and a searchable knowledge wiki. 4 output styles, multilingual (ko/en/ja), RAG, spaced review, team workspaces. Flask + Next.js.

Enterprise-grade AI Agent system for code generation, analysis, and orchestration

Multi-agent GUI for AI coding assistants — Claude Code, Gemini CLI, OpenCode & more. npx agentgui

Self-hosted API gateway for Claude Code on Amazon Bedrock — unlock extended thinking, web search & tool use with team budgets, OIDC SSO, and an admin portal

An end-to-end RAG chatbot using FastAPI, LangChain, ChromaDB & Streamlit with Multi-LLM support to answer questions from uploaded PDFs.

A step-by-step guide to building a Codex-style agent runtime,like codex

The open standard for AI agent personas. One file. Persistent identity.

Flutter clean architecture skill for AI agents. Riverpod 3.x codegen, Freezed 3.x sealed classes, and GoRouter patterns.

🚀 Manus AI Go SDK - Complete Golang library for seamless integration with Manus AI API. Build AI-powered applications with task automation, file management, and real-time webhook notifications. Type-safe, idiomatic Go code with comprehensive error handling, full test coverage, and detailed documentation. Perfect for Go developers.

HeyGen avatar video generation skill for Claude Code. Batch, templates, translation, photo avatars, TTS. Stdlib-only Python.

A bilingual Dan Koe skill that helps creators sharpen point of view, design media-to-business loops, and draw better AI boundaries.

Autonomous AI pentesting agent that understands natural language. Self-healing, self-evolving, multi-LLM powered.

14-category autonomous product-building OS for 32+ AI coding tools. One-line prompts → deployed products.

AI-agent workspace for quantitative trading — backtest, validate, and paper trade strategies with multi-agent collaboration

A full-featued Calibre MCP server with granular permissions for read/write/import/etc. Locally tested and freshly released, consider this an alpha. Back your library up before you give an agent write permissions.

飞书（Lark）或微信（WeChat）聊天控制 DeepSeek Harness / Claude Code / Cursor / Codex / CCC Agent

Cross-platform AI agent desktop app and multi-agent workspace for Claude Code, Codex CLI, and Gemini CLI. Rust + React + Tauri.

Find and call JustOneAPI endpoints from MCP-compatible AI assistants using natural language.

Production-grade, 10,000+ line PRDs that let AI agents one-shot entire applications. Built on CRHQ.ai.

Search the web in Pi through your Codex subscription.

The first browser MCP built for security testing. Give your AI agent a real Firefox browser and let it find vulnerabilities.

Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact output, lossless XHTML<->Markdown round-trip, Claude Code + Codex + GitHub Copilot integration.

Claude Profile Manager — run multiple Claude Code accounts side-by-side with isolated credentials and zero overhead

See AI thinking in real time — 3D orb that visualizes Claude Code reasoning. Free, open-source MCP server

A tool that scans a codebase, pick the important files, and export them as JSON to your clipboard or a file.

bb-huge 🤗 , Personal bug bounty findings hub and bug bounty orchestration for multiple agents

Cross-IDE, multi-stack agent skill for OpenUI (the Open Standard for Generative UI). Adds OpenUI to existing projects across 12 backend stacks, any LLM provider, and 11 agent platforms. Scaffold, integrate, validate.

One step to enable best-practices for AI agents — drop into any project and enjoy the magic.

Encrypted vault, ZK settlement archiving, x402 payment receipts, Agent Passport binding, and Solana anchoring for OpenClaw and agent runtimes. Drop-in stack — compression, privacy, payments, identity.

Windows + Docker + Python 基于 Milvus + MySQL + Redis + 大模型的私有化 RAG 问答系统

little-canary is a prompt-injection detector that reads attacks by their effect on a sacrificial canary model before they reach production. Puts a small canary model in front of your app, watches whether untrusted input compromises it, and returns block, flag, or pass as an inbound preflight check before your primary model acts.

Connect AI agents to AuditHub’s blockchain security tools. Launch scans, review findings, monitor tasks. Open source, Apache 2.0.

Local-first runtime for managing an AI-company with agents, orchestration, git workflows, and CLI-driven execution.

Readplace - Read the Web not the Slop. Save articles, read them later. No 3rd party tracking/analytics. Built by the creator of js-cookie for the purpose of sharing their AI integrated learning system used in the last 10 years.

Governed API and agent runtime for desktop, VS Code, and CLI. Secure API testing, mocking, automation, secret protection, and controlled AI tool access.

A menu-bar macOS agent loop: every N minutes it asks Claude/Codex what's overloading your Mac and suggests one-click, risk-checked fixes.

Invarium is pytest for AI agents. Test behavior, not exact text.

Multi-provider Android AI chat SDK with Jetpack Compose UI, headless Kotlin API, Room history, and support for OpenAI, Gemini, Claude, and Grok.

AI-DLC (AI-Driven Development Life Cycle) claude code plugin

GraphRAG over any codebase — a Neo4j knowledge graph of code entities plus a 3072-dim vector index, bridged so one natural-language query walks structure and ranks by meaning. Python · Neo4j · OpenAI embeddings · Streamlit · Docker. Hybrid semantic + structural code search.

Self-evolving skills for your coding agent — auto-create and auto-improve skills as you work, no trigger needed.

基於 Google ADK 與 MCP Toolbox 的保險科技推薦 Agent 原型。核心 Agent 能理解保險需求、主動追問，並透過受控 SQL 工具查詢醫療、意外、家庭與收入保障產品。後端採 FastAPI 提供 SSE 串流與 WebSocket 即時互動，前端以 Next.js 呈現對話介面。知識庫結合 PostgreSQL 與 pgvector 實現 FAQ 語意搜尋與 RAG 查詢，並支援多模態 Live Agent 語音互動。安全層涵蓋 JWT 驗證、PII 脫敏與 SHA-256 雜湊鏈防篡改稽核日誌。品質保證採 ADK evalsets 評估驅動開發，部署支援 Docker Compose、Cloud Run 與 Terraform 多環境配置。

Local code search for AI agents: six fast, purpose-built tools that return ranked answers, not raw grep. Because maybe grep isn't all you need... 🍬

Lightcode is a coding agent written in Go.

Visualize Claude Code as a top-down office — agents as employees, sessions as orchestrators, all in real time.

"Done" means nothing — a menhera-style completion gate for Claude Code that blocks empty completion claims until tests actually ran green and no TODOs are left behind.

Lightweight project/mobile workbench for same tmux-backed AI coding sessions; not remote desktop or a second AI chat.

AI-powered penetration testing with Claude Code agents. RedTeam Barranquilla - Automating security assessments using PTES methodology.

Autonomous IT service desk built entirely on Microsoft 365 — Copilot Studio, Power Automate, and SharePoint. Ticket → triage → approve → execute, no per-seat SaaS fees. Microsoft Agent Academy Hackathon winner.

Record a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.

Talk to your Mac — a native macOS voice assistant that sees your screen, drives your Mac, and answers back. Powered by the OpenAI Realtime API. Open source.

Make Claude Scriptable Again

MCP server that gives LLM agents read-only shell access over SSH. Powers Fawdy (fawdy.com)

基于langchain1.1版本和高德mcp server的多智能体agent旅游助手

Self-hosted, MIT-licensed AI-agent orchestration platform. Agents with personas, skills & tools that chat, run ~90 tools, delegate to sub-agents, and stream results across ~46 LLM providers. RAG, semantic memory, marketplace.

A powerful offline chat application that provides AI mentors specialized in various tech domains. Learn programming with intelligent, emotionally-aware AI mentors that understand your needs and guide you through your development journey.

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.

OpenAI Codex 中文使用手册：CLI、AGENTS.md、权限安全、MCP、Skills、Subagents、工作流与排障。

一个集微信小程序 + FastAPI 后端 + React 前端的 AI 内容创作全栈平台，支持热点采集、AI 内容生成（文章/视频/数字人）、多平台自动发布。

Discord Rich Presence (RPC) for Claude Code — live model, project, tokens, and lifetime stats in your Discord profile. Driven by Claude Code hooks.

Coding-agent harness for continuous contribution — discovers, implements & validates your next high-fit change as a review-ready draft PR you decide on.

Discord Rich Presence for Codex CLI, Codex VS Code Extension, and Codex App.

Unofficial Linux port of MiniMax Agent — AI-powered code assistant for Linux (.deb for Debian/Ubuntu/Mint & .pkg.tar.zst for Arch/Cachy OS/Manjaro)

Codex Portable · OpenAI Codex CLI 便携版 · U盘即走 · 零安装 · MIT