Custom agents

Browser Use Cloud SDK

A multi-agent framework for automated video mashup creation.

Open Source TypeScript SDK for building real-time multimodal voice & vision AI agents

AI that shares your terminal session. Open-source AI terminal where the AI types commands directly into your shell, not just suggests them. SSH, Docker, BYO LLM.

Give an agent a job, not your keys. Open-source control plane for AI agent work: each agent gets its own identity, a bounded job, and a signed record of what it did.

Enterprise-grade FastGPT workflow JSON generator - Works with Claude Code, OpenClaw, Costrict.ai, Trae and any skill-based AI platform

Full-featured MCP server and CLI for LINE WORKS (NAVER WORKS) — 26 tools covering messages, calendar, drive, mail, tasks, and boards. Automate with AI agents or scripts.

Open-source security scanner for AI Agent skills, plugins & MCP servers. 39 detection rules. pip install prism-scanner

context engineering for agentic coding

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

Agentic sandbox enumeration: find security issues, and seed escape automation.

ProjectBEA is an always-on AI persona engine: she talks, plays Minecraft with real people, and remembers you between sessions. One mind across Discord, Telegram, Twitch and Minecraft — not a bot per platform.

A practical guide to AI engineering — LLMs, RAG, agents, evals, and production ops. Built for engineers who ship AI systems.

AI-powered personal finance skill — 75 tools across 7 extensions for banking (Plaid), trading (Alpaca), portfolio monitoring (IBKR), tax optimization, market intelligence, and social sentiment. Built for the Agent Skills Protocol, works with 40+ AI agents.

Automate a WeChat group's daily work-report roll-call — start, chase non-submitters, and LLM-summarize for the manager. wxauto + FastAPI + hot-reloadable rules.

Agent_Console（智能体控制台）是一个本地运行的 Agent + RAG 工作台。它把文档入库、混合检索、查询改写、工具调用、运行回调和人工审核放在同一个控制台里，适合做企业知识库问答、课程资料检索、客服辅助和可追踪的智能体实验

Portable — a drop in replacement /remote-control on Claude, + batteries

The AI agent memory layer you can audit — local-first memory governance for AI agents: citations, trust policies, trace receipts, rollback. SQLite, sidecar-first, OpenClaw plugin.

MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyzers, auditable risk scores, and JSON, SARIF, and HTML output. For authors and platform teams; CI-ready, no cloud API.

[Open Source] Novel Writing & AI Programming Assistant. 【公开源码】的小说写作与 AI 编程助手。Aggregates top large models from home and abroad聚合国内外顶尖大模型 (DeepSeek/Gemini/Claude/Kimi/ChatGPT, etc.)

A powerful Retrieval Augmented Generation system that turns your Markdown documentation into an interactive knowledge base using vector search and LLMs.

Project Doxa is an advanced, autonomous agent-based simulation engine where AI agents act as citizens of evolving civilizations.

互動式 IT 故障排除 Runbook，整合 Claude AI。涵蓋 CCTV、NAS、AD、Exchange、Outlook 等企業常見場景。純靜態 HTML，GitHub Pages 一鍵部署。AI-powered IT troubleshooting runbook for Active Directory, Exchange, Outlook, NAS, CCTV and manufacturing environments. Designed for real-world IT operations and support teams.

Autonomous agent for Minecraft, combining LLMs and Baritone pathfinding

Rustant is a high-performance, privacy-first autonomous personal agent built entirely in Rust, designed to execute complex tasks through LLM-powered reasoning while maintaining strict safety guarantees.

These are multi-ai-agents samples for Cloud Native

Official Implementation of "O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL"

Offline agent skill bundling specification.website (128 topics) for Claude Code and other SKILL.md-compatible agents. Spec content CC BY 4.0 by Joost de Valk.

Your AI-Powered Test Agent for Comprehensive Test Cases Generation and Effective Test Automation leveraging RAG architecture & GenAI

Portable, always-fresh docs for agents and humans. A Surface hub is a conformant OKF concept; Surface adds the freshness OKF leaves out - it fails the build when the code a doc describes changes. Deterministic, no LLM.

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-weighted RRF. Apache-2.0.

Code for the API, workload execution, and agents underlying the LLMail-Inject Adpative Prompt Injection Challenge

A curated collection of Agent Skills — reusable units of intelligence that teach AI General Agents how to perform specific tasks autonomously.

Self-adapting, Tool-enabled, Extensible, Multi-agent System

AEGIS: Automated Error Generation and Attribution for Multi-Agent Systems

The official implementation of our work SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration in AAAI 2025

Agent skill to migrate a Webflow site to React.

A curated list of the OpenClaw family — the open-source AI agent ecosystem. From the 150K-star original to IoT chips, Rust frameworks, and security tooling.

FylloCode 是一个开源桌面应用，把 Claude Code、Codex 等本地 Coding Agent 接进项目工作流。派任务、审方案、追溯每一次改动，积累下来的规范和结论，换一个 Agent 也能继承。

Open-source multi-agent AI video ad engine — 7 agents, 15+ video models, visual canvas. Turn a prompt into a cinematic ad

Identity-first cognitive agent OS with memory, multi-channel ingress, Operating Room orchestration, and desktop surfaces.

Open & nano reimplementation of Sakana Fugu. A repo-native, multi-agent coding loop powered by 9+ LLMs (isolated via Claude Code) and an independent Codex reviewer. Lightweight, bounded, and self-improving (Self-Harness)—no coordinator training required.

Local-first desktop workspace for AI agents: browser, terminal, memory, plugins, runtimes, and durable loops.

Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)

AI 原生多租户 SaaS 开发框架 — FastAPI + Vue 3 + PostgreSQL，内置 AI Agent、RAG、插件系统、RBAC、异步任务等核心能力，助力快速构建行业 SaaS 应用。

Self-hosted, browser-based AI dungeon RPG, fully local on an AMD Strix Halo APU: narrator + per-character agents on one local LLM (Gemma 4 26B MoE via llama.cpp/Vulkan), local images (FLUX.2 klein/ComfyUI), expressive voice (Maya1 TTS). FastAPI brain, SQLite, vanilla JS, docker-compose with guided setup (CLI wizard or double-click HTML).

RondoFlow is a local-first, open-source platform for visually orchestrating Claude Code AI agents. Use a drag-and-drop canvas to create agents, attach skills, define security policies, and run multi-agent workflows.

Hosted persistent memory for AI agents over MCP. Tell it a recalled memory helped or misled, and it re-ranks what comes back next. Shared rooms for multi-agent work. One key or OAuth across Claude Code, Cursor, VS Code and ChatGPT. MIT, in the official MCP Registry.

A set of AI agent skills for research and development tasks.

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.

A complete AI-powered real estate agency — 12 specialized agent paired with 12 production skills that generate CMAs, offer strategies, marketing plans, underwriting models, and compliance audits. Built on the agency-agents framework.

纯本地 AI 编程桌面工具 · 由 DeepSeek 驱动 · 一个 API Key 即用

对话式 PRD 生成技能，中文优化，通用 Agent Skill（Claude Code / Codex / Hermes / OpenClaw 等） · A conversational PRD-writing Agent Skill

Ask your video library anything — an AI agent that watches, reasons in a tool-use loop, and answers with playable clips and charts.

Gear Framework: design portable multi-agent systems with feature-model based specifications and generate code for multiple execution frameworks.

Observable diagnostics, failure attribution, metrics, and no-key replay for multi-agent runtimes.

Autonomous red teaming and evidence-backed security evaluation for live AI agents.

2025 LLM Hackathon for Applications in Materials and Chemistry

TELL: Test-time Experiential Lifelong Learning – a single LLM agent that learns from experience at test time, achieving 43.9% on ARC-AGI-3 with no training.

Agent skill for AI coding assistants — review and build production-grade Claude agents following SDK best practices

WordPress plugin development skills for AI coding agents — Claude Code, Gemini CLI, Cursor, Windsurf, Cline, Codex, Copilot, opencode, and more

A stack of tools and agent specialists built to help those who use LLMs as healthcare advisors.

基于 LLM 的保险保全智能助手 Demo，集成了 RAG 检索增强生成、Tool/Function Calling、多轮对话记忆管理、意图识别与路由 等核心技术，实现智能问答、自动化客服、业务 Agent 等典型 AI 应用场景。本项目以保险保全真实业务场景为案例，涵盖退保、手机号变更等核心保全业务，展示了 AI 技术在传统金融保险领域的落地实践。

macOS 菜单栏工具，聚合显示多个 AI 编程/Agent工具（Claude Code / Codex / Cursor / Qoder / 悟空/ Workbuddy 等）的 token 用量，全本地直读零配置

Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the data layer, we rent the harness.

现代化的AI驱动知识管理与智能体工作流平台，集成了大语言模型(LLM)、Skills、向量数据库、智能体(Agents)、工具集成，MCP，A2A协议等功能。该平台旨在帮助个人和团队高效地组织、存储、检索和利用知识资产，同时通过可定制的工作流自动化复杂任务。

An advanced multi-agent framework for automating complex bioinformatics workflows.

Multi-language CLI for Rafter — the security toolkit built for AI coding agents and the developers who use them.

Vulpine: multi-agent vulnerability-development pipeline for Claude Code and OpenCode

Multi-agent AI chat platform - Create AI personas and watch them converse in real-time with Ollama integration

AI-powered visual novel writing studio with multi-agent collaboration, node-based plotting, branches, and human-in-the-loop editing. Built with Tauri + ReactFlow. 开源长篇小说创作工具

Long-task-oriented video analysis skill for Claude Code (/vea) — resumable staged execution, automatic parallel scoring, OpenClaw orchestration, audiovisual analysis with agent handoff

Agent skills for the React Native Community

Agentic Framework for Synthesizing CodeQL Queries

A coding agent with a new context-engineering framework — bounded, deterministic, reconstructed context (the Slice), built for long-horizon work.

Community-driven catalog of ready-to-use agents for the Security Copilot portal.

一个从零实现 AI Agent 的开源学习项目——每一步都有源码，每一章都能运行，渐进式理解智能体。Build an AI Agent from Scratch — Learn AI Agents step by step with runnable source code.

Claude Code skill: radar for fundamental posts on autonomous AI agents across AI-lab engineering blogs

Static analysis and attack-surface scanner for AI agents — SAST for prompts, tools, MCP servers, and agent workflows. Detects capabilities, prompt risks, tool permissions, and governance gaps before deployment.

Security-posture-first list of sandboxes for running AI coding agents' code, ranked by isolation, egress control and secrets handling

AI求职桌面助手：找岗位（BOSS直聘、猎聘、智联招聘和前程无忧）、改简历、准备面试。

A LLM-powered agent for NetHack

A compact heads-up display for your coding agent. Instruments while it works, the answer when it stops. Claude Code, Codex, OpenCode.

For the Udacity Master of Science in Artificial Intelligence and MBA in AI Product Management! Contains my solutions for various Nanodegree Programs (Robotics, Artificial Intelligence, Machine Learning, Deep Reinforcement Learning, Computer Vision, Sensor Fusion, Flying Cars, Business Intelligence, Agentic AI, GenAI).

A Swift framework for Final Cut Pro FCPXML processing built with AI agents

The most complete Dify MCP server + CLI — 193 tools for building, testing, and shipping Dify workflows, with Dify 1.18 support.

LitReview Skill is an installable agent skill for end-to-end literature review generation. It helps agents conduct literature reviews with a well-designed and widely used review framework so the search process is broad, iterative, and less likely to miss relevant articles.

Use your X Premium or SuperGrok subscription in pi.

A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.

The autonomous AI multi-agent swarm for end-to-end game development. From idea to playable game in one click.

An open-source template that turns your repo into an autonomous development team. Uses GitHub Actions and Claude to orchestrate AI agents under the scrum framework to manage and build directly from Issues.

AI-native IDE built with Electron, Monaco, and React — integrated terminal, Solana wallet, Claude agent, and one-click deploy

Whisper a design prompt to Claude Design and bring the result back to your coding agent — oracle, but for claude.ai/design.

200+ AI, Gen AI, LLM, agentic AI, Forward Deployed Engineer (FDE), AI systems architect, applied AI, LLMOps and AI platform engineering interview questions across 10 topics. Each has a short answer, in-depth detail, a worked example and interview tips.

Decision provenance and data-flow tracking for coding agents: computes what changed in your code and data, records why it changed, and surfaces both before a silent failure ships.

SPAR: multi-agent scholarly retrieval with query decomposition, query evolution, and citation-aware exploration.

An End-to-End Multimodal ECG Interpretation Agent. This agent solves the challenges of non-direct analyzability of ECG images and insufficient association of professional diagnostic knowledge. By adopting multimodal AI and knowledge-enhanced retrieval techniques, it generates accurate and implementable intelligent ECG diagnosis reports.

Connect AI assistants to TwinCAT automation Build, deploy, and monitor TwinCAT PLCs directly from VS Code with GitHub Copilot

AI-powered code review for Emacs using ACP agents. Review git changes with Claude, Cursor, Gemini, or other AI agents and navigate results interactively

DSH - Dseam