Custom agents

Open-source sandboxes for AI agents and code execution.

Vibe Mathematics —— 多代理数学问题求解与形式化验证框架

Native macOS menu bar app that tracks local AI coding agent token usage like daily steps.

MedMCP: An Open Agentic Ecosystem for Medical Imaging Workflows

PinTrip 是一个 AI 旅行攻略生成平台。用户可以用自然语言描述目的地、旅行天数、交通方式和兴趣偏好，系统通过多 Agent 协作完成需求解析、景点与天气研究，并生成包含每日行程、预算和实景图片的结构化攻略。

Xiaohongshu & RedNote skill for AI agents — search, read notes, publish, and run approval-gated automation with Python Playwright and clean JSON output.

A disposable copy of your production stack for every pull request: masked Postgres, contained third-party APIs, and agents that use your app like people.

十三希诺 Agent 工作流 · 中文源库：把工程纪律做成可机检门禁的元工作流 Skill 家族——三级跑道／判级／GATE 12 字段可复跑证据／405 条细则库／五包交付（核心+流程+角色+产品工程+单文件蒸馏），五平台注入适配。docs/ 为开发工作区，实验数据已归档。English edition → shisan-xinuo-product-en

Create and improve AI agents that get better over time with automatic optimization and continuous learning

Growth Skills is an open-source collection of AI-executable Agent Skills for growth diagnosis, content production, acquisition, activation, retention, monetization, and growth systems. By KrillinAI.

Production-ready AI-powered pentesting & cybersecurity assistant with Agent, Chat & Planning modes, native desktop GUI, 10 AI providers, and built-in intelligence modules.

The fast AI agent

Visualize AI context & traces.

MCP server for Kdenlive — wraps kdenlive-api for Claude Code and other LLM agents

GenAI on Google Cloud: Enterprise Generative AI Systems and Agents

oo is OOMOL's CLI toolkit. Everything can be done in the CLI.

Design-system and vocabulary drift, enforced. Tailwind themes become law, rogue values get receipts, words live in a database agents inherit — one org ontology across every repo.

Self-improvement loop for Hermes Agent: reads its own trajectory, proposes and applies the smallest skill/memory edit (create/patch), journaled with rollback. /refine command, refine_run tool, on_session_end hook.

🎮 Production-ready AI rules for Unity 6.2+. Single Source of Truth for Cursor (.cursor) and Google Antigravity (.agent) with auto-sync workflow.

Multi-Agent Handoff Inspector: analyze multi-agent handoff records, score context completeness, surface coordination bottlenecks, and render a review dossier.

Stellar-aware execution runtime for AgentLily autonomous finance agents — TypeScript task runner, typed tools, and Stellar payment preparation for Lily Protocol

A durable, file-based framework for long-running LLM-assisted work, with persistent context, project continuity, and coordinated specialized agents across local and remote machines.

Official implementation of LSMART, an open-source simulator to evaluate any lifelong Multi-Agent Path Finding algorithms with real-world kinodynamics and execution uncertainties.

Local, live code review for the AI age - read what the agent wrote and send feedback straight back

An AI agent you build, not just prompt. Local-first Android agent with on-device inference (LiteRT-LM), pipelines you assemble yourself, MCP tool calling, and your confirmation before any risky action.

🏗️ AGRO — Agent Governance Runtime Orchestrator. A portable home for autonomous coding agents.

基于多模态RAG的视频学习Agent

A curated list of ready-to-use Grok bot templates across productivity, sales, marketing, ops, success, and personal workflows.

Transform SaaS REST APIs into AI Agent. Get a semantically-enhanced, governed MCP Servers + Agent Playground for natural-language interaction.

A Python app that shows how an agent calls tools, saves results, and recalls them after a restart.

面向 B站视频学习的本地优先助手：边看边问、随手记笔记，用视频 Wiki 沉淀与复用知识；保留观看账单与兴趣再平衡。

[RSS 2026] ''From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation'' Official Repository

🏗️ A collection of resources for harness engineering — shaping the environment around AI agents for reliability in production.

A plugin-first Go runtime for building extensible AI agent products.

面向 LangGraph 与 Deep Agents 的企业级异步Agent Runtime，提供开箱即用的工程化能力，帮助开发者高效构建、集成与运行 AI Agent 应用。 支持多租户、多模态交互与多 Agent 协同，提供 AG-UI/SSE 流式交互、断线续接及覆盖模型调用、工具执行与 Agent 协作的全链路追踪。集成计划审核、人工介入（HITL）、自动化任务调度与 OpenSandbox 沙箱执行能力，满足复杂 Agent 应用的交互、执行与管控需求。

李大魔的 AI Skills 合集：把AI写的中文改成人话 · 让Agent换会话不丢上下文

An Elixir library and standalone agentic engine for building AI workflows

REWE Pickup CLI for AI agents — grocery ordering from the terminal

用 Claude Agent SDK 将订阅额度与完整 harness 接入自建聊天前端：与 claude -p 的差别、query() 参数、权限回调、固定前缀、提示缓存、登录态、Mac 与 VPS 部署

Three trap-laden fix-it tasks with hidden graders for testing an AI coding agent's judgment. Sandbox setup, prompts, answer key, and results for Qwen3.8-Flash, Qwen3.6-35B and Claude Opus 5.

Per-task rubric-blind skills for the Parthenon self-evolving legal-agent framework (Harvey LAB).

CoDesign gives AI agents like Claude Code, Codex and PI a real design engine for genuine, editable designs, not flat images. Bring in what you have: InDesign, Photoshop, PowerPoint and PDF files stay editable. Exports print PDFs (CMYK, bleed) and videos. Every design opens in a built-in editor for manual fixes. Runs on your machine, no account.

Enterprise multi-agent self-evolving workflow orchestration platform MVP

端到端 QA 验收编排器 · Agent Skill：上下文 → 风险 → 用例 → 脚本 → 执行 → 审查 → 报告，全程自动衔接，只在用例确认时停下等你审核。支持 Claude Code / Codex / Cursor

Dure — every coding agent, one workspace across desktop and mobile.

Monitoring that arrives with the "why", not just "down" — uptime checks, application logs and AI incident explanations in one compose file, wired into your app by the coding agent you already use. Works with npx upcontrol.

Practical MuleSoft recipes — 100+ DataWeave patterns, AI agent integration, CI/CD pipelines, migration guides, and more.

Know which tmux coding agent is waiting on you — and jump to it. Works with the Claude Code, Codex, and Gemini CLI sessions you already run. No wrapper, no new terminal.

全栈开发、AI Agent、软件工程与计算机基础的学习实践，记录技术探索、项目开发与工程实验。

Coding agents move fast. Logic Loop helps you keep up. A desktop app for running parallel terminal agent sessions across projects — switch without losing context. An open-source project by Super Logic AI.

Toolkit del webinar Agenti AI per i contenuti (Agents Week di Learnn): prompt, skill, procedure e cartella di esempio per Claude Code, Cowork, Codex e ChatGPT

Free subdomains under makes.fyi / agentdomains.co, claimed from the CLI. A/AAAA/CNAME/TXT/NS records, auto-HTTPS proxy and forwarding for the sites and APIs AI agents build.

A Chromium fork built for AI agents: built-in MCP server, per-agent logged-in identities, sessions as tab groups

An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any harness: Claude Code, Codex, Hermes, any ACP agent, or you. Windows, macOS, Linux.

可自托管的持久化个人 Agent：进程重启后恢复任务，支持子 Agent、定时计划、长期记忆、网页界面与微信通道

Give your agent a DJ booth: one local system for music discovery, acquisition, analysis, stems, playlists, Rekordbox-compatible USBs, and CDJs.

Guide pédagogique non officiel en français sur REA (Reverse Engineer Anything) : analyser des applications et des binaires avec un agent de code via MCP et CLI, Hopper ou Ghidra, preuves à l'appui. Inclut le cadre légal de la rétro-ingénierie. Projet amont : morluto/rea.

The animated diagram editor AI agents can draw on. Animated technical diagrams (architecture, sequence, BPMN, cloud icons) built by you and your agent together on the same live canvas, via WebMCP. Open-source, local-first.

鼓谱整理：粘贴 B站链接，把滚动鼓谱视频整理成可打印的 A4 PDF。免费、无需注册。Turn Bilibili drum score videos into printable A4 PDFs at drum.kenqia.top.

开源 · 本地优先的 AI 智能体：编程与实干兼备。 自带模型密钥，内置 MCP、技能、插件、工作流、知识库以及数据库。

Agentic AI 系统设计笔记

TRACE: Trust Runtime Attestation and Compliance Evidence. Open attestation standard for agentic AI governance.

Local semantic copilot and governed agent engineering runtime for AI-assisted software delivery.

Frappe FlowAgent is a native visual workflow automation platform for Frappe and ERPNext that enables users to build AI-powered workflows or AI Agents using a drag-and-drop interface.

Agent Almanac — a curated reference of executable skills, specialist agents, and teams for AI-assisted development, with interactive visualization

Install and run every AI agent on your phone locally

Coco is a proactive co-assistant that connects user workspace with a broader ecosystem of AI agents.

Arcade kart racer in the spirit of Mario Kart, built entirely with Three.js. 100% procedural assets, no build step. Built by five Claude Opus 5.5 sub-agents from one prompt.

Rubric-driven evaluation for AI agents. Executable criteria, code and model judges, and inspectable trace reports.

Agentic data engineering built on Pub/Sub for Tables. Discover, publish, transform and consume data as versioned tables with lineage, with an AI agent doing the assembly and the engineer approving.

A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature video, complexity delta, and deep-linked snippets.

The Arabic AI ecosystem as a map, a list, and a skill your agent can install.

Research orchestration platform where human researchers and AI agents collaborate

TradeOS MCP lets you connect TradeOS trading intelligence to MCP-compatible AI tools, so your assistant can analyze markets, search tickers, compare spreads, use macro context, and manage custom trading agents directly from natural-language prompts.

Micro-VM sandbox for AI agents: isolated, gated and auditable, to prove what your agents did

Halaska UI: a single-file React UI kit for AI products, built on shadcn/ui. 40 AI UX patterns and 90 components for agents, chat and generative UI.

微信 API、微信协议（iPad/Mac）。支持消息收发、群聊管理、朋友圈和通讯录，提供多语言 SDK、WebSocket / Webhook 推送。可申请试用，长期维护。

Agentic AI for Offensive Cybersecurity, published by Packt

AirSIM hardware integration for MU300/U30 Air: OpenWrt LuCI plugin, Linux call agent and PCM bridge. Development preview.

Practice the AI-assisted coding interview format with your own coding agent: ten problems with planted bugs, stubs, timed tests, and an interviewer prompt

A comprehensive collection of skills and agents designed specifically for **Grok** - the AI with a personality that combines physics expertise, real-time data access, meme culture awareness, and coding efficiency. Each skill is optimized for Grok's unique strengths and communication style.

Solana EVM Developer: AI Agents & AI-powered on-chain systems Smart Contracts & DeFi Protocols Cross-Chain Bridges NFT Marketplaces & Dynamic NFT Platforms Token Launchpads & Bonding Curve DEXs P2E Games & GameFi Provably Fair Non-Custodial Casinos & Betting Non-Custodial Staking & Yield Systems Institutional Lending Protocols & RWA infrastructure

AnyKB — 私有 RAG 知识库 + 透明 Agent

对话机器人，包含了看图说话，单轮对话和多轮对话，tensorflow 2.0 pytorch 1.3.1 GPT-2

This is an AI project

oracle framework is the fastest and easiest way to bring your agent to life.

➡️ Moved to Hivekeep: github.com/MarlBurroW/hivekeep — self-hosted autonomous AI agents. Your AI team. At home.

A lightweight Model Context Protocol (MCP) server that enables natural language interaction with your Todoist tasks directly from your IDE. Built with simplicity and maintainability in mind.

Chatbot for Stack Overflow

Python script for ingesting various files into a semantic graph. For text, images, cpp, python, rust, javascript, and PDFs.

PDF RAG server for cursor.

financial market analyst with ai agent

Pioneering blockchain network enabling AI agents to operate autonomously through economic agency. Uomi empowers digital entities to deliver real-world value, transact independently, and evolve through market dynamics, creating a new paradigm of AI-driven decentralized intelligence.

BTC Fear & Greed Index powered by MiroFish/OASIS multi-agent simulation. 500 AI investors simulate panic contagion dynamics.

ns3-gym for multi-agent

[2025-上海人工智能实验室书生实训营十佳、优秀项目]

Library that helps you to get mobile application user agent and web view user agent strings

AI on-call agent that detects deploy failures explains what broke pages the responsible team and rolls back automatically.

Memory that follows you across every AI tool. No cloud storage. No account required. Set it up once, use it everywhere.