Code agents

RAG pipeline security testing toolkit - 27 techniques across 6 kill chain phases, mapped to MITRE ATLAS

Multi-role AI orchestration runtime for Windows. Quality-gated pipeline (Brain → Miranda → Pappy → Benson) with MCP support, SQLite persistence, and a self-improving distillation loop. Coding you can trust.

Give your AI agent a wallet, email, phone number, and instant access to paid MCP tools — web search, image/video/music gen, X search, SMS, voice calls, code execution, and more. Works with Gemini CLI, Claude, and any MCP client.

AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating of Medical Knowledge Graphs (MKGs), integrates reasoning, and retrieves current external evidence for medical Question Answering (QA).

OpenAI-compatible multi-account Codex and vibe coding proxy

🚀 cto.new 免费反代 | OpenAI & Anthropic 兼容 API | GPT-5.4 / GLM-5.1 账号池自动轮询 · JWT 刷新 · Dashboard UI · 批量注册 ｜ Free OpenAI/Anthropic-compatible API proxy with account pool auto-rotation, JWT refresh, bulk registration & real-time dashboard. ⚠️ 不支持 agent 工具调用 / No function calling support.

Security AI helper for Caido: pipes your local Claude Code / Gemini / Codex / Copilot CLI through 18 MCP tools for manual web security testing. Local-first, no API keys.

High-Performance Encrypted Database for .NET 10 | Embedded + gRPC Server | Vector Search • GraphRAG • Analytics

A curated list of Telegram Bot resources — libraries, frameworks, tools, Mini Apps, and community bots. Actively maintained.

SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command. TDD, planning, self-review, CI shepherd.

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.

Local CLI for automating Classic Outlook on Windows via COM. Includes a Claude Code/Codex Skill for AI-assisted email management with safety guardrails.

Planner/Generator/Evaluator orchestration harness for Claude Code (and Codex)

The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.

Multi-agent architecture for Opencode — cost-optimized model routing, parallel specialist execution, dev tools, and a self-maintaining project wiki

Expert skills, agents, commands, rules, hooks & output styles for Claude Code — session continuity + modern CLI tooling for real-world dev workflows

Bring Galileo powered eval workflows into Claude Code and Codex.

🎮 34 production-grade Claude Code skills for indie game development — studio agents, workflow skills, engine specialists, genre packs, and CI validation. From concept to launch.

An opinionated, agentic life-OS for Claude Code — a markdown vault with daily/weekly/quarterly review skills baked in. Includes the feedback layer most templates skip.

AI-powered job application bot using Google Gemini + Playwright MCP. Automates job searching, form filling, and applications on Gupy, LinkedIn, Indeed and more. Smart scoring, multi-resume, dry-run mode, Telegram notifications, web dashboard.

Project-based Claude CLI session manager with automatic tmux setup and persistence

GTM Operating System — outbound sales, lead gen, campaigns. Brief it. Build it. Ship it. Measure it.

Portable AI agent skills for private career context, local VitaeGraph records, and evidence-based career work across GitHub, LinkedIn, CV/ATS, portfolios, and X.

Full stack AI web application for languge learning built with Next.js and ChatGPT

The Web Access Gateway for AI Agents — 52 channels, 92 MCP tools, 9 SDKs, self-healing backends, async Rust

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

VS Code-style typewriter animation video skill for AI agents (agentskills.io format)

A free, living knowledge base on vibe coding — building SaaS fast with AI agents, local AI, and agentic workflows.

The open-source debugging agent for developers. We connect your favorite coding agent to prod to fix application bugs automatically. Run us locally and eliminate PR slop.

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama) with FTS5 fallback.

An LLM server for a single RTX 5090, built for agent workloads: tool calls, long conversations, reasoning, and many requests at once. One of the fastest engines on this card, at batch 1 and at dozens of concurrent streams, with the numbers in the repo.

Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with structured results, headless operations, and live runtime control.

Claude Code status light system

53 retro HTML/CSS UI themes for AI-assisted frontend development. Windows 95, CRT, vaporwave, DOS, arcade, mainframe, and more.

Comprehensive multi-agent code review for Claude Code

Connect a personal Zalo account to the Hermes Agent gateway via zca-js (unofficial Zalo API). Cross-platform plugin: macOS, Linux, Windows.

Desktop IDE for working with multiple AI coding agents. Supports Claude, Codex, OpenCode, Cursor and Grok.

transformers safetensors mixtral text-generation merge moe

transformers pytorch codegen text-generation arxiv:2203.13474 license:bsd-3-clause

Agent skill that audits and cleans agent-facing markdown docs — archives completed-work history, fixes stale facts and contradictions, keeps only live verified facts.

Aggregated Kubernetes apiserver and e2b-compatible data plane for warm-pooled agent sandboxes on microVMs. Sandboxes are served from per-node inventory with no per-sandbox etcd object and claimed from node-local sandboxd warm pools; the e2b SDK reaches them through an edge proxy.

The visual layer of your agent harness. Renders React components and Three.js scenes from source, with structure and evidence behind every frame — so agents can see, verify, and fix what they built.

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

Expose VS Code language intelligence to AI agents via MCP, with automatic routing across multiple windows

An automated AI-powered trading system designed to analyze market data, generate trading signals, and execute trades using configurable strategies.

A runbook for initializing resumable, verifiable, and auditable project harnesses for AI coding agents.

Zero-touch pipeline that turns newly weaponized CVEs from the CISA Known Exploited Vulnerabilities (KEV) catalog into production-ready Sigma detection rules, automatically, every week.

Open-source AI coding agent CLI with multi-provider support, local models, MCP, and specialized AI agents.

OhMyPi (OMP) Agent Framework Spec-Driven Development infrastructure for Oh My Pi. Skills transform artifacts through a deterministic engineering workflow.

CareerDesk: Your Personal Career Assistant

Perhaps the only agent skill you need: if memory loss is the root, let every AI agent rebirth follow the First-Time Principle. That's all.

Persistent institutional shared memory as observable middleware for collaborative AI agents

Fullstack platform for sharing AI Agent skills, built with TanStack Start, Tailwind, and TypeScript. Features Clerk auth, Firebase real-time data, PostHog analytics; + codebase reviewed by CodeRabbit.

Documentation memory for AI coding agents—route project knowledge, reduce repeated context loading, and validate living Markdown docs.

在原版 ChatGPT / Codex 同时使用 DeepSeek V4.1 Flash 与 GPT。Local loopback router, native Responses API, full tool loops, no fork.

基于23位著名游资心法的A股超短线交易系统 Skill。核心：情绪周期、龙头战法、概率思维。适用于Hermes Agent、OpenClaw、Claude Code等AI Agent平台。

DeepSeek Harness (DSH) 插件精选目录 — 14 类 280+ 个社区插件，覆盖 MCP / Skill / TUI / 多 Agent / 上下文记忆 / UI 皮肤，点链接直达仓库。Curated directory of dsh plugins for DeepSeek Harness.

"🐳 Dsh-Quant: The Everything-Plugin Ai native Quant OS "

TypeScript SDK for Odoo; CLI; Skill modules and MCP server for AI agents. CI-tested against v17 and v18.

Autonomous marketing team for Claude Code — 9 AI agents, 20 skills, 4 MCP servers, one /grow command

28 OSINT Agent Skills that turn Cursor, Claude & AI coding agents into a full open-source intelligence platform — reconnaissance, attribution, GEOINT, breach checks & due diligence. Ethical, sourced, passive-first.

"The First Principles of AI Programming" Open Source Book. Starting from the underlying physical constraints of large models, it deduces the operational mechanisms of agents and the engineering practices of AI programming systems.

Organize your AI sessions, and carry what they know into the next one.

🎯 CenterOS — The Lightweight AI Operating System! A simple, cloneable framework that turns your AI into a personalized system for automating your business, life, and everything else.

Local-first terminal AI copilot - git-aware answers, shell command suggestions, and diff reviews through a local Ollama model. Go core + VS Code extension + Python plugin SDK.

Code Graph mcp solutions for AI agents with ontology and sentence. Supports extra large codebases

Cloud dead-drop C2 framework — RSA-4096 + AES-256-GCM, 5 cloud providers, Rust-only agents, P2P mesh, persistence engine, credential harvesting

Local-first terminal AI copilot - git-aware answers, shell command suggestions, and diff reviews through a local Ollama model. Go core + VS Code extension + Python plugin SDK.

Curated collection of agent skills for AI coding assistants.

AI product management skills and plugin for Claude Code, Cowork, Codex & other AI agents: evidence-tagged PRDs, specs, requirements, RICE prioritization, backlog and roadmap scoring, product strategy, GTM launch plans, release verification, benchmark packs, UX/UI design prompts for web + mobile apps. Every claim sourced or labelled unsourced.

Paseo product adapter for Google's official Antigravity ACP kernel: daemon context, mode/MCP adaptation, Admission queue, and skill discovery.

Grok Bot 0.18.0 runtime code archive — unminified bundles, mechanical per-module split, byte-for-byte reproducible

Build and deploy agentic finance applications on the Alva platform. Access 250+ financial data sources, run cloud-side analytics, backtest trading strategies, and publish interactive playbooks.

Code Trace Tree is a VS Code/JetBrains plugin that traces code in a tree structure with AI support. Build and display code workflows as trace points. Add traces from the editor menu or the Agent Skill; double-click to jump to the source.

Claude-Code-style TUI bundle for DeepSeek Harness. 充分结合 DSH 的核心机制和高级特性与Codex CLI 、Claude Code、Pi agent 等主流交互机制，打造的 DSH-Code. （对齐DSH官方上游最新 RC 版本！持续更新中！支持DSH 特殊模式，插件系统，模型管理，子代理管理，切换模型特殊动画）注：自 DSH-Code 1.0.0起，代码由DSH-Code 自迭代完善，不使用外部 agent /CLI 完成！

Windows workbench for Claude Code, Codex, OpenCode, Antigravity & Grok Build. See which agent needs you, resume sessions, and reconnect from your phone.

Agent Skills for working with Etherscan and on-chain data. These skills let AI agents turn raw Etherscan API responses into structured, verifiable output — every address, amount, and transaction hash comes from a live API call, never invented.

Kit is a coding agent runtime. Claude Code but faster, cheaper and more to the point 🎯

Turn your database into secure, semantically rich MCP tools for agents.

transformers gguf llama llama-2 text-generation code

Reduce hallucinations through first-principles reasoning, verification, self-critique, and explicit uncertainty for AI agents.

AI coding agent skills for shipping, maintaining secure WordPress Sites

Claude Code plugin for people who describe what they want and let Claude build it: brand identity, product planning, plain-language build/ship/debug workflows, and a creator toolkit.

Combine GPT-6 Astra and Claude Fable 5.1. Astra directs, Claude builds, Astra verifies.

A Flutter client for herdr: a status board and live terminal for the coding agents on your own machines. Over SSH, with no bridge binary to install.

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.

把 WorkBuddy / CodeBuddy（腾讯代码助手） 的桌面端登录态，转成你本机 / 局域网可直接使用的 OpenAI / Anthropic 兼容 API，并提供一个 多账号代理共享平台（账号池自动切换、独立 API Key、按 Key 配额、用量记账）。 workbuddy2api 不负责登录、不模拟桌面端、不替你执行工具。它只做三件事： 读取本机登录态并注入完整的鉴权头（含设备风控头 X-Device-Token） 在 OpenAI / Anthropic 协议与腾讯后端协议之间转换 对 Codex CLI 这类长上下文 agent 请求做后端友好的压缩投影

transformers safetensors llama text-generation conversational base_model:deepseek-ai/deepseek-coder-33b-instruct

Teaches AI coding agents to make clear, honest charts, and checks each one before you see it. For Claude Code, Codex, Cursor, and more.

16 reusable skills and 6 agents for Codex, Claude Code, Cursor, OpenCode and Grok Bot: Humanizer, ML debugging, PR review and Skill Watch.

Your app is guilty until proven secure: an agent skill whose /hack-me breaks into your own running app, proves each bug with a real request, patches it, and re-verifies. Claude Code · Codex · Cursor.

Self-hosted AI voice agent

A clean-room terminal coding agent built from Claude Code architecture research.

This repository will guide you to create ChatGPT like chatbot using OpenAI's GPT 3.5 model

An easy-to-use reverse engineered text to image generation Python API wrapper for Lexica.art

Turn domain experts into production AI agents.

CodeAlert - 红色警戒之人工智能崛起！！！欢迎参加第一届AI智能体红警游戏黑客松

Unit tests for plain text - LLM as a copy editor

Model Context Protocol (MCP) Gateway & Registry - Central hub for managing tools, resources, and prompts for MCP-compatible LLMs. Translates REST APIs into MCP, builds virtual MCP servers with security and observability, and bridges multiple transports (stdio, SSE, streamable HTTP).