Custom agents

Turn feature requests into review-ready pull requests: issue, implementation, tests, a review-and-fix loop, and docs. Runs locally or on GitHub Actions, and is built for complex brownfield repos. Each week its retrospective reads what you actually merged and proposes improvements to your skill extensions.

Sandbox for Agents

Single-file, zero-dependency task board: owner-vs-agent plates, a dependency map, tap-to-complete.

Orchestrate sandboxed agents that run in the cloud while you work

A coding-agent skill for generating designed HTML textbooks and print-ready PDFs

⚡ Open source, agentic alternative to Intercom & Zendesk

All-in-One Desktop Agent Skills Utility. Welcome to the Skill Zoo, where all your skills live!

Agent Skill for polished LaTeX-to-Word conversion with live Zotero citations

Official ClickHouse Agentic Data Stack - self-host with ClickHouse, LibreChat, Langfuse, and ClickHouse MCP.

Agent-Pixels is a paperclip plugin implementation of 'Pixel-Agents' the VSCode extension by Pablo De Lucca (7k Stars). The plugin features new "Security Cameras" in Paperclip by Dotta (60k Stars)

Linked-Intent Development - a SDD methodology for agentic coding

Agent skills for Xiaomi MiMo series.

Agent skill to extract color palettes from images — screenshots, Figma exports, design mockups. Installable via npx skills add pascalorg/image-analysis

LegalWork, a local computer-use agent for law firms, by Eigenwelt Labs. Review, redline, and draft documents on your own machine with the model you choose.

ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

[ICLR 2026] Official Implementation of "FeatureBench: Benchmarking Agentic Coding for Complex Feature Development"

CLI & MCP for GitHits - The Code Context Layer for AI Coding Agents

Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.

Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.

A local-first AI companion for books and films, with memory, ratings, reflections, and personalized recommendations.

闲鱼全流程自动化运营系统：从商机挖掘、商品发布，到 AI 客服、固定内容/卡密自动发货、评价与售后跟进一站式完成；支持多账号、多租户、异常恢复和 Docker 自部署。

Open Job Context Protocol -- an open standard for agent-consumable job feeds built on MCP

Agent that read, write and edit documents.

Local-first, transparent threat hunting for the logs you already have: Zeek, Pi-hole, syslog, CloudTrail. Named technique behind every finding. No SIEM, no agent, no black box.

Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Local hands for your AI, keys in your pocket — a desktop agent where every capability is authorized, executed locally, and backed by Evidence.

Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-credential demo.

Janus: Towards Evolving Agentic Laboratory

the first open-source platform for simulation testing, monitoring and self-improving voice agents

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, and evals.

帮助 AI Agent 生成可直接导入 Dify 的工作流 DSL YAML | Help AI agents generate import-ready Dify Workflow DSL YAML

A personal VM cloud in one Go binary: persistent Linux VMs on macOS, Linux and Windows, AI coding agents working inside them, any port published to HTTPS through Cloudflare Tunnel. Driven from a Mac OS 9 desktop in the browser, over SSH, or by an agent.

基于 FastAPI 多 Agent 协同的拟真 AI模拟面试平台，支持多面试官切换、实时语音交互与 9 阶段面试流程，内置 5 层安全防护。

Kun Like 桌宠 —— DeepSeek Harness 桌面宠物插件：右下角小坤宠随 Agent 工作状态切换 9 种动作，任务完成播放「你干嘛~哎哟」

DSH 自动化插件：让 Coding 任务按计划在全新 Agent Session 中运行，并由用户或 Agent 创建和管理定时任务。 / Run coding tasks in fresh Agent sessions and manage schedules from DSH Web or an Agent.

AI-powered exam question generator. Upload study materials, get exam questions in seconds. Open source, local-first, cross-platform.

Jailbreaker is a local evaluation tool for testing chatbot and agent-style systems against jailbreak, prompt-injection, and related failure modes.

A clear-writing agent skill grounded in the Google Developer Documentation Style Guide.

Fnos 原生 Hermes Agent

虚拟歌手洛天依（Luo Tianyi）智能对话Agent。

MCP server that drives real Chrome with your real logged-in sessions — genuine fingerprint (passes bot.sannysoft), human-like input, bot-wall aware. 43 tools, single static Rust binary.

DeepSeek Harness Agent Workflow

AI Agent for Exploratory Browser Testing

Lego-RL: Harness-Native Reinforcement Learning for Coding Agents

An open-source local print agent that enables silent printing from web applications.一个开源本地打印代理，让 Web 应用实现稳定的静默打印。

基本可用 Universal context-compression proxy for AI coding agents

The review app for code your agent writes. Native Rust/GPUI desktop app with real Git workflows.

Python SDK for DefuzeX agent behavior testing.

Brand Design Skill 是一个 image-first 的 Codex 品牌设计 Skill。它通过对话式流程引导 Agent 完成苏格拉底式需求澄清、Logo 图像探索、最终图像 Logo 资产、行业化 VI 应用场景，以及高质量 HTML 品牌手册。|

Thea brings coding agents to the physical world.

A tiny skill that surfaces relevant terms of art as you work with agents, growing your domain vocabulary over time

Local-first system of record for documents (PDFs, images, text files, etc.) for you and your agents

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI

Local, fail-closed policy enforcement and human approval for MCP tool calls.

The open-source trading harness for agents

🎬 Open-source animated architecture diagrams as code. Diagram-native DSL, 17 layout engines, Web Animations API, and MCP server for AI agents.

面向 Chrome/Firefox 的轻量级浏览器安全工作台：集成抓包、拦截改包、重放/Fuzz、编解码工作台、敏感信息检测、HawkEye MCP 与浏览器级 Agent。（A lightweight Chrome/Firefox browser security workbench for capture, interception, replay/Fuzz, codec toolkit, sensitive-data detection, HawkEye MCP, and browser-level Agent workflows.）

Your brain, then your team's brain, then your agents' brain. Drop in documents and it compounds them into an interlinked markdown wiki you own — readable in Obsidian, synced through your own private GitHub repo. Share it with a cohort. Coding agents resume from it across sessions, models and machines.

Convert source material into executable Agent Skill packages

A bridge to help connect a brand new iCloud account to Facetime audio for voice to voice agent action

轻量级终端 Coding Agent，支持多模型接入与 MCP 标准扩展。

Pytorch Implementation of Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

一套让多个 AI agent 协作干工程活、且没有任何一方能给自己签合格的设计，加上它的实现，以及它真的跑起来时留下的账本。

A course on context engineering with code agents.

Hermes Agent Ultra (built from hermes-agent-rs core by lumioresearch, @oxterrybit). Hermes-agent feature parity at commit level. Rust Performance

A user-space safety net that helps researchers prevent AI agents from overloading shared HPC login nodes.

Rollout inference runtime for Agentic RL and multi-turn code agents

Physical AI skills for coding agents, with field-tested robotics guidance, the robium-ai CLI, and a learning engine.

An advanced, UI-powered AI second brain Agent Skill for OpenClaw, Hermes Agent, WorkBuddy, TRAE, and QClaw. ZhiGui uses long-term memory to help you make better decisions, automatically plan tomorrow, resolve conflicting notes, and deliver each day's plan through your existing agent channels.

Campfire - Collaborative web platform for AI coding agents with Collective Intelligence layers

Agent Skills for Chinese IPO sponsor execution: diligence, filing production, pre-submission QC, regulatory inquiries, and filing refresh.

Evidence-first game operations incident investigation agent with read-only MCP tools and reproducible evaluations.

CraftBot is an architect AI agent. It interprets design briefs, grounds its thinking in domain knowledge through ingesting documents, images and other references, and outputs Python code that procedurally defines a building design.

Agent skills for daily use

A memory governance engine for multi-agent cloud knowledge bases — one knowledge base shared by every agent and every device, with consistency guaranteed. Pure Markdown, nine governance automations, zero dependencies.

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk Hermes/Claude/Codex/opencode. Verified.

The setup I used for my GPT-6 Astra Portal run: controller, SourcePauseTool patch, setup guide, and sanitized session log.

Portable, verifiable work state for coding agents

Type a movie, get a captioned speech + beat-cut fan edit. Local-first, no API keys, works with your AI bot (Claude Code / Codex).

XCode CLI & Simulator MCP. Progressive disclosure of tool responses reduces context and token waste. Lets AI agents build, run and drive iOS apps — without drowning in Xcode's output.

CUA-Lite: An Open Platform for Computer-Use Agents

Agent Skills for managing live LiteLLM proxy deployments — users, teams, keys, orgs, models, MCP servers, agents

Python AI Agent 学习计划（精简大纲 + 学习详情）

Job Yang's AI Agent Skills: writing, video reading, and reusable agent workflows.

News: We add many jev+robot in infrastructure. A curated collection of papers and resources on robot-use agents, tool-based robot control, embodied agent runtimes, and self-evolving robotic systems.

OpenTelemetry plugins for every coding agent, in the Agent Plugins format — a marketplace that runs itself: open an issue, the repository validates, reviews, lists and follows your plugin.

Dex lets your agent build your analytics.

18 portable Agent Skills for voice-native AI, human judgment, microbets, social tact, writing, life systems, and safe deployment.

Who's working, who's waiting on you — grouped by project, each agent in its vendor's logo and colour. Worktrees nest under their repo, rows order by activity, idle sessions fade. Light and dark.

LangGraph 显式状态机实现的 coding agent 平台：人审、统一权限、事务性写入、审计——企业级治理链的单机参考实现（cody-harness 的姊妹项目）

ScienceIDE: Turning World’s Scientific Codebase into Agent Learnable Environments

Windows 多账号 AI 内容生产工作台｜项目/CSV 任务、可恢复调度、执行意图门禁、原会话定位、产物绑定下载、本机受控 Agent 接口（--local-control / CLI / MCP）

Self-hosted AI social media studio: one piece of material in, platform-native posts out. Format router, self-critique, pre-publish risk gate, real OAuth publishing. Web app + CLI + MCP server + agent skill.

Open-source API to check if an email has been exposed in a data breach and monitor breaches across your verified domains. Real-time alerts and breach analytics protect your online identity.

STC 简明技术性中文：给 AI 用的中文写作规范。输出更自然、简短，术语更一致，任务回执更清楚。支持 CLI、独立 Skill 和网页聊天。Simplified Technical Chinese: rules, a dictionary, and tools for clear, concise AI output.

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

Agent Factory is an open-source studio for building, editing and chatting with AI agents. You build them from simple nodes: LLM calls, HTTP requests, JavaScript, memory and sub-agents. It runs locally with one docker-compose command, and ready-made testing agents are available in the shared agents-store repo.