Code agents

[ACL 2026] Code, benchmark and environment for "OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows"

📝 md2wechat MCP Server | 让 Claude Code & AI Agent 一键排版发布到微信公众号

Agentic coding framework powered by AGENTS.md: systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.

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.

AI featured threat modeling and security review action

Crawl any website with Tavily, embed the content, and deploy the RAG on MongoDB Atlas vector search.

A vibe coded Sora JSON Prompt Crafter for curious humans and prompt engineers

Writing companion for AI content generation.

A remote, phone-first console for your tmux — agent-agnostic, no database. Spawn and watch coding agents in parallel worktrees, or anything else you run.

深度优化多Agent自主执行编码 Harness 框架，支持从自然语言任务出发，完成任务规划、代码生成、自动验证与迭代修复闭环，并成功接入 Terminal-Bench 2.0 评测体系，任务完成率约 40%，榜单排名约 70。

Browse & Inspect CLI agents : Claude Code, Codex, Gemini CLI code & conversation history

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.

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.

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.

Install agent skills and MCPs with one API

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

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

A fast, portable CLI tool for synchronizing AI agent configurations across multiple AI coding assistants using symbolic links.

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

CLI for Beeper Desktop API - unified messaging from your terminal. Give your AI agents the power to chat across all your messaging platforms.

Save coding agents' conversations in Git Notes, automatically

Coordination protocol for agent-first teams. No UI. No sprints. No Jira. Just state sync.

🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 44 commands · 19 skills · 8 agents · 43 rules · 30 hooks · auto-learning pipeline. | 一个插件，完整开发团队。

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

arifOS — Constitutional MCP kernel for governed AI execution. AAA trinity: AGI (Mind) · ASI (Heart) · APEX (Judge). Built for the sovereign agentic era.

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

AI Agent which can do any kind of Browser Automation Task & Web Scraping, just using a single prompt!

Go SDK for Anthropic Claude Code CLI – unofficial Claude Code Go agent SDK

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

FxChartAI AI-Agent Trading EA is an open-source MQL5 Expert Advisor for MetaTrader 5 that trades using signals from FxChartAI. It employs trend confirmation, candle tail/trendline analysis, and dynamic order management. Free for personal & commercial use. Contributions welcome.

Bring your own AI environment to Obsidian. For note/doc creation, refinement, search, organization, management, you name it!

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

AI Testing Agent: Open Source AI Agent for Software Testing

Embedded single file SQL database written in Golang

Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.

Local-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.

Real-time .NET proxy and dashboard for inspecting AI coding agent API calls (currently supports Claude Code)

SecTor - Not-So-Secret Agents: Deploying AI to Optimize Security Operations

Automatically monitors YouTube channels for new videos, extracts transcripts, auto-detects the content type (stocks, crypto, podcast, tech review, education, news, etc.), generates tailored summaries using your choice of LLM (Gemini, OpenAI, or Claude), and emails them to you.

Unofficial Ruby SDK for Claude Agent

Governed infrastructure for internal tools and AI agents

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

A JetBrains IDE plugin that integrates OpenCode — the open-source AI coding agent — directly into your development workflow.

Official code for TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents

ᓚᘏᗢ Bengal — High-performance static site generator for Python 3.14+ with parallel builds, autodoc, and content validation

Academic research agent skills for Claude Code and other Agent Skills-compatible tools. Hypothesis generation, experiment design, paper drafting, peer review simulation, and more.

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

Official codebase for the paper "Auditing Agent Harness Safety"

This project includes code for using the AsyncWebRL and WebGym frameworks to train web agent models.

Claude Code skill for handling long-context tasks through recursive decomposition

A curated list of Agent Skills, resources, and tools for AI coding agents like Claude Code, Codex, Gemini CLI, GitHub Copilot, and more.

Agent Decision Records (AgDR) - A standard for documenting technical decisions made by AI coding agents. Extends ADR for the age of AI-assisted development.

UX/UI evaluation, AI governance, and AI security skills for AI coding assistants. Audit interfaces with Nielsen heuristics, WCAG, Don Norman principles. Assess AI risk with NIST AI RMF, ISO 42001, OWASP LLM Top 10, and OWASP AI Testing Guide.

Scrape JavaScript-heavy sites and extract structured data via reusable CSS schemas. Portable agent skill wrapping the Crawl4AI CLI and Python SDK.

Self-improving behavioral files for AI coding agents. Analyzes session transcripts for correction patterns and makes surgical edits to prevent recurrence.

MCP server for Kali Linux penetration testing - 121 tools for AI-assisted security testing - Giving Agents access to full pentesting tools

Code-quality feedback for LLM coding agents

SketchUp meets AI Agents

Team-API 专为团队、组织、企业打造的多租户大模型 API 网关。具备完整权限管理与审计能力，助力团队更好地使用AI大模型。支持Claude/OpenAI/Gemini等主力模。QQ交流群：1095286563

《Skill 蓝皮书 2026》· 基于 61,776 条 Skill 数据的原生研究 · AgentSkillsHub 出品 · 54% 0 star · 基尼系数 0.983

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

🌿 StoryForge (草苔) — AI导演式小说创作系统。Tauri+Rust驱动的桌面写作软件，集成知识图谱、伏笔追踪、StyleDNA风格引擎、协同编辑、7阶段全自动创作工作流。让AI成为你的创作搭档，越写越懂你。

Advanced code editor using local AI

Structured planning and persistent context for AI coding agents. Plan multi-phase work once and any agent (Claude Code, Codex, OpenCode) executes it across sessions without losing the thread.

Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.

🦞 AI 量化交易系统 — 37 因子选股 · 8 层风控 · 同花顺数据大屏 · 全自动盯盘

Make your AI agent think before it codes.

恶意中转，目标是支持对opencode，claudecode，openclaw等常见的agent的攻击。

An Agent Skill for the DL experiment lifecycle: RUN (a GPU you own or rent) → VERIFY the number is real → DELIVER reproducible, single-source figures and tables.

Agent skill for ImageGen-driven editable PowerPoint deck generation and strict slide-image-to-PPTX conversion

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then audits drift, cycles and fragility in code you already have. Zero import cycles, zero critical anti-patterns - measured against itself.

✨ A programmable content review harness for AI agents. The slop filter your agents are missing.

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidence graphs for risk, forensics, and audit.

Email gateway that opens a Claude Code session per inbound AgentMail message (cmux or Ghostty)

Your codex login → a full ChatGPT Plus/Pro account (every model, deep research, image gen, code exec) inside Claude Code, Codex & any MCP client. One-line install.

A web UI for viewing and controlling the local pi coding agent in your browser.

Agent-first Model Context Protocol (MCP) server to debug, profile, and optimize running Flutter apps. Connects AI assistants to Dart VM Service over WebSockets for direct access to widget trees, memory snapshots, network traffic, stateful CPU profiling, and layout diffing.

Go-based Unraid plugin monitor and control your Unraid system via REST API, WebSocket, MCP, Prometheus, and MQTT. Supports Docker/VM control, real-time metrics, Home Assistant integration, and AI agent tooling.

A curated gallery of 107 high-quality GPT-Image-2 prompts — portraits, posters, character sheets, UI mockups. Click any image to try on APIMart.

A Codex/Claude Code skill for document-driven, multi-agent Vibe Coding workflows.

Agentic AI Humanizer Skill for Codex, Claude and OpenClaw: Bypass AI Detectors

💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.

Agent token and task monitoring, thousands of pet avatars, cross-platform support, and compatibility with popular AI agents. 一眼查看 Token 与任务状态，海量 Petdex 形象可选，支持 Windows/macOS/Linux、ESP/Wio Terminal，兼容 Cursor、Codex、Claude、Windsurf 等主流 Agent。

Kraivor is an AI-powered system that analyzes real-world codebases and simulates how they behave under production stress, failures, and scaling conditions.

188+ local tools for Claude, ChatGPT, Cursor & Grok — Mail, iMessage, Teams, Slack, WhatsApp, OneDrive, Google Drive, Zoom, Outlook, Office. Native macOS, 100% local, no API keys.

🇰🇷 400+ Korean AI Coding Agent Skills — Claude Code, Gemini CLI, Codex, Cursor 스킬을 기능별로 모은 큐레이션

Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.

Computer-use, but for the iPhone — AI agents (and your browser) see and drive a real phone over macOS iPhone Mirroring. Low-latency WebRTC video, near-native touch, HTTP API + MCP. Rust, self-hosted.

Zotero MCP server: search, citations, add by DOI, safe writes, semantic search and PDF page images for Claude, ChatGPT and any MCP client. TypeScript, local-first.

Auto-updated leaderboard of trending claude-skills and AI agent repos, refreshed every 15 minutes

The Proxmox MCP you can hand the keys. All four products: PVE, PBS, PMG, PDM.

transformers safetensors gemma4_unified image-text-to-text gemma4 coding

transformers safetensors iquestpltcoder text-generation code code-generation

transformers safetensors qwen3_next text-generation qwen3 nvfp4

Semantic diff review for coding agents

Frappe Agent Skills gives AI coding assistants structured Frappe knowledge for DocTypes, APIs, Desk customization, frontend apps, reports, testing, and production patterns.

┣nteractive tmux pane tree with live agent badges and Vim-style navigation.

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