Browse all 20,362 AI agents

An autonomous LLM research agent that executes the full academic paper pipeline — from literature search to compiled PDF

Local-first agent plan annotator

Open source implementation of Anthropic's Programmatic Tool Calling

An open source implementation of code execution with MCP (Programatic Tool Calling)

An open-source, multi-agent AI framework for Playwright test automation — featuring a 2D pixel-art office, live SSE telemetry, and Gemini / Ollama LLM routing.

The open standard for agentic software verification: query business rules, assess release risk, and execute autonomous testing workflows.

Self-hosted alternative to OpenAI's Responses API compatible with Agents SDK and works with all model providers (Claude/R1/Qwen/Ollama etc)

Open-source reverse engineering lab: 197-article knowledge base + MCP tools + CTF/APK/PE automation toolchain. Agent-native.

OpenReviewer is an automated multi-agent system for deep, evidence-driven research paper review, validation, and integrity auditing across methodology, experiments, citations, and cross-section consis

Open-Sable is a local-first autonomous agent framework with AGI-inspired cognitive subsystems (goals, memory, metacognition, tool use). It can run continuously on your machine, integrate with chat int

Open Skills is a modular, Anthropic-style skills framework that lets agents dynamically discover, select, and execute user-defined capabilities. It runs as a standalone FastAPI service or embedded Pyt

An OpenStreetMap MCP server implementation that enhances LLM capabilities with location-based services and geospatial data.

LLM-agnostic tabletop RPG Game Master framework. Runs on OpenCode, LM Studio, or any LLM service. D&D 5e included as reference system — add any TTRPG via a system module.

A computer you can curl ⚡

A Rust execution runtime framework that governs what AI agents can do: ed25519-signed capability writs, effect-ceiling enforcement, policy checks before any tool runs, and an append-only, content-addr

Personal AI butler powered by Claude — task management, Claude Code sessions, memory system, and web UI. Self-hosted, local-first, open source.

OpenAaaS: science agent network — bring AI to your data, not your data to AI. AaaS, Agent as a Service, MCP protocol, local execution, Docker sandbox, zero-config Rust nodes.

Open-source tax skills for AI — 371 skills across 134 countries. Upload to any LLM or connect via MCP. Quality-tiered Q1–Q5.

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

Self-hosted bridge that lets you interact with AI coding agents (Claude Code, Codex, etc.) from messaging platforms (Telegram, Discord, etc.) via the Agent Client Protocol (ACP).

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

Connect agents across runtimes, frameworks, and teams.

A Framework for Evaluating AI Agent Safety in Realistic Environments

An interactive educational platform for learning and understanding AI agents as concepts. To benefit every Educational Institution, every Educator, every Learner. Concept are the critical unit of know

AI agent framework for plan-first development workflows with approval-based execution. Multi-language support (TypeScript, Python, Go, Rust) with automatic testing, code review, and validation built f

Python Library for using Arcade tools with the OpenAI Agents SDK

Complete educational guide with 100+ working code examples for building production-ready AI agents using the OpenAI Agents SDK. Learn to build and deploy scalable multi-agent systems in under 2 hour

A lightweight, powerful framework for multi-agent workflows in Go

Starter Repo with UI Components & Hooks for OpenAI Agents JS

OpenAI Agents And Tools as MCP Server

A lightweight, powerful framework for multi-agent workflows

How to Build Agentic AI Apps with OpenAI Agents SDK | Multi-Agent Systems, Guardrails & Tools

OpenAI Agents Tracing | Open-Source Tracing Dashboard including Costs & Usages

🧳 A state-of-the-art multi-agent travel planning system powered by OpenAI Agents SDK and LangGraph orchestration. Leverages Stagehand/Playwright for browser automation, Supabase for data persistence,

Production-ready OpenAI Agents SDK (TypeScript) template — agents, handoffs, tools, guardrails, sessions, tracing, CLI.

This workflow shows how you can get your OpenAI assistant to call an n8n workflow as a tool. Since you can put almost any functionality in an n8n workflow, this means you can give your assistant acces

This is an end-to-end workflow for creating a simple OpenAI Assistant. The whole process is done with n8n nodes and do not require any programming experience.

Primer workflow for OpenAI models: ChatGPT, DALLE-2, Whisper

Enrich your company lists with OpenAI GPT-3 ↓

Edit an existing image with OpenAI ImageGen1 via API Request

Complete AI Graphic Design Suite with OpenAI, Replicate & Google Drive

This n8n template demonstrates how to use OpenAI's Responses API with existing LLM and AI Agent nodes.

This repository demonstrates a simple OpenAI Swarm-based system for multi-agent orchestration with Retrieval-Augmented Generation (RAG). It handles tasks like summarization, sentiment analysis, keywor

Swarm.js is a Node.js implementation of OpenAI’s experimental Swarm framework. This SDK allows developers to orchestrate multi-agent systems using OpenAI’s API in a lightweight and ergonomic way, whil

This workflow uses OpenAI to generate tweets to be stored in Airtable for review.

Transform college admissions from an overwhelming manual process into an intelligent, efficient, and equitable system that analyzes essays, scores applicants holistically, and identifies top candidate

An open-source AI assistant framework with skills and agent architecture

An alerting layer for agentic frameworks

Access the OpenAlex academic research catalog - 270M+ publications through MCP. STDIO & Streamable HTTP.

MCP server for the OpenAlex API — search 240M+ scholarly works, analyze citations, track research trends, and map collaboration networks

OpenAPI to MCP Server Code Generator

Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over OpenAI endpoints.

Modern JAV metadata manager — multi-source scraping, Jellyfin integration, and AI-ready API. Built with FastAPI + DaisyUI.

通用个性化内容推荐 Agent —— 跑在你自己电脑上，用心理画像而不是点击记录跨平台理解你，主动帮你发现从没接触过的好内容。项目最初是想做一个开源、私有、思路完全不同的 B 站推荐算法平替（项目名由此而来：Open + Bili + Claw），现已演进为支持小红书、通用 Web 的通用跨平台 Agent

An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, s

OpenBrep — 面向 ArchiCAD 高阶用户和 GDL 开发者的 AI 工作台。编译验证、知识驱动、资产可追溯

Give AI your browser. Check email, track orders, download receipts -- all authenticated, no API keys. Open source MCP server + CLI.

modular, service-oriented CAD

runs anywhere. uses anything

Open Source Agentic Coding Harness