This repository lists some of the top AI agent projects available on GitHub. It includes a variety of frameworks, tools, and applications for building and managing AI agents.
- AI Agent Frameworks
- AI Tools and Applications
- AI for Specific Domains
- Game AI Agents
- Multi-Agent Systems
- AI Development Tools
- Workflow & No-Code Agents
- Observability & Evaluation
- Agent Safety & Guardrails
- Miscellaneous
| Project Name | Description | Link |
|---|---|---|
| 🤖 MetaGPT | 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming | MetaGPT |
| 🛠️ langflow | Langflow is a low-code app builder for RAG and multi-agent AI applications. It's Python-based and agnostic to any model, API, or database. | langflow |
| 🧑🤝🧑 crewAI | Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. | crewAI |
| ⚡ SuperAGI | <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably. | SuperAGI |
| 🛠️ devika | Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI. | devika |
| 🔧 haystack | AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots. | haystack |
| 📝 phidata | Build multi-modal Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI. | phidata |
| 📚 agentic | AI agent stdlib that works with any LLM and TypeScript AI SDK. | agentic |
| 🐫 camel | 🐫 CAMEL: Finding the Scaling Law of Agents. The first and the best multi-agent framework. https://www.camel-ai.org | camel |
| 🧠 PraisonAI | PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration. | PraisonAI |
| 🧩 griptape | Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory. | griptape |
| 🧬 atomic-agents | Building AI agents, atomically | atomic-agents |
| 🖥️ Cradle | The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements. | Cradle |
| 🔁 LangGraph | Stateful, graph-based agent orchestration framework from LangChain. Supports human-in-the-loop workflows, long-term memory, and streaming. Used in production at Klarna, Uber, J.P. Morgan, and LinkedIn. (24.8k+ stars) | LangGraph |
| 🤖 OpenAI Agents SDK | Lightweight Python framework for building multi-agent workflows with handoffs, guardrails, and built-in tracing. Provider-agnostic and compatible with 100+ LLMs. (19k+ stars) | openai-agents-python |
| 🔷 Google ADK | Google's Agent Development Kit — modular framework with native A2A (Agent-to-Agent) protocol support, hierarchical agent trees, and multimodal Gemini integration. (17.8k+ stars) | adk-python |
| 🐬 Agno | Full-stack open-source Python framework for multi-agent systems with memory, RAG pipelines, multi-modal I/O, and vector DB support. (29k+ stars) | agno |
| ✅ PydanticAI | Type-safe, Pydantic-native agent framework for building production-grade generative AI applications. Supports OpenAI, Anthropic, Gemini, Ollama, and Groq. | pydantic-ai |
| 🪄 Semantic Kernel | Microsoft's enterprise-ready SDK for AI agent orchestration across Python, .NET, and Java. Integrates with Azure AI, OpenAI, Google, and Hugging Face. | semantic-kernel |
| 💾 Letta | Stateful LLM agent framework (formerly MemGPT) with persistent long-term memory across sessions. Supports OpenAI, Anthropic, DeepSeek, Groq, and AWS Bedrock. (15.9k+ stars) | letta |
| Project Name | Description | Link |
|---|---|---|
| 🖥️ anything-llm | The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more. | anything-llm |
| 💬 LibreChat | Enhanced ChatGPT Clone: Features Agents, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active project. | LibreChat |
| 🤖 BotSharp | AI Multi-Agent Framework in .NET | BotSharp |
| 💻 aichat | All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more. | aichat |
| 🦸♀️ superduper | Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data. | superduper |
| 🧑🤝🧑 GPTeam | GPTeam: An open-source multi-agent simulation | GPTeam |
| 🛠️ agent-service-toolkit | Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit | agent-service-toolkit |
| Use Case | Industry / Domain | Description | Link |
|---|---|---|---|
| 24/7 AI Chatbot | Customer Service | Handles customer queries 24/7/365 | Link |
| AI health assistant | Healthcare | Diagnoses and monitors diseases | Link |
| Real estate agent | Real Estate | Analyzes market trends to determine real estate prices | Link |
| Industrial automation agent | Manufacturing | Monitors production lines and ensures quality | Link |
| Predictive maintenance agent | Manufacturing / Industrial | Connects to SCADA/IoT sensors to forecast equipment failures and auto-schedule maintenance, reducing downtime | Link |
| Virtual tutor | Education | Provides personalized education | Link |
| Automated trading bot | Finance | Automates stock trading with real-time analysis. | Link |
| Financial compliance agent | Banking / RegTech | Monitors transactions, flags AML/fraud risks, and auto-generates regulatory reports using multi-agent workflows | Link |
| Content personalization agent | Entertainment | Recommends personalized media content | Link |
| Job recommendation agent | Human Resources | Suggests best-fit candidates for job openings. | Link |
| Self-driving delivery agent | Transportation | Optimizes routes and autonomously delivers packages. | Link |
| Smart farming assistant | Agriculture | Provides insights on crop health and yield predictions. | Link |
| Legal document review assistant | Legal | Automates document review and highlights key clauses. | Link |
| Supply Chain optimization agent | Supply Chain | Plans efficient delivery routes and manages inventory. | Link |
| Event forecasting agent | Politics | Predicts global events | Link |
| Shopping agent | E-commerce | Helps customers find products they'll love. | Link |
| AI travel assistant | Hospitality | Plans travel itineraries based on preferences. | Link |
| AI game companion agent | Gaming | Enhances player experience with real-time assistance. | Link |
| Real-time threat detection agent | Cybersecurity | Identifies potential threats and mitigates attacks. | Link |
| Recommender agent | Retail | Suggests best product recommendation | Link |
| AI drug discovery agent | Pharma / Life Sciences | Multi-agent toolkit for querying biomodels, knowledge graphs, and scientific literature to accelerate pharmaceutical R&D. Includes Talk2BioModels, Talk2Scholars, and Talk2Cells agents. | AIAgents4Pharma |
| Mental health support agent | Mental Health | LLM-powered multi-agent app providing 24/7 emotional support and guidance, built with AutoGen and Flask. Designed to reduce stigma and barriers to mental healthcare. | mh_agent |
| Carbon intensity & grid forecasting agent | Energy / Sustainability | Predicts grid carbon intensity and renewable energy percentage using LSTM models and real-time electricity data. Supports energy arbitrage and sustainability reporting. | Eco-AI.ly |
| Scientific discovery agent | Research / Academia | Curated collection of LLM agents for biomedical research — covering medical image analysis, multi-omics, genomics, and scientific literature synthesis. | Awesome-LLM-Agents-Scientific-Discovery |
| Project Name | Description | Link |
|---|---|---|
| 🎮 SerpentAI | Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own! | SerpentAI |
| 🕹️ street-fighter-ai | This is an AI agent for Street Fighter II Champion Edition. | street-fighter-ai |
| 🐍 snake-ai | An AI agent that beats the classic game "Snake". | snake-ai |
| 🏟️ chatarena | ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs. | chatarena |
| Project Name | Description | Link |
|---|---|---|
| 🤖 MetaGPT | The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming | MetaGPT |
| 🧑🤝🧑 crewAI | Framework for orchestrating role-playing, autonomous AI agents | crewAI |
| 🐫 camel | CAMEL: Finding the Scaling Law of Agents. The first and the best multi-agent framework. | camel |
| 🧠 PraisonAI | Combines PraisonAI Agents, AutoGen, and CrewAI into a low-code multi-agent LLM system | PraisonAI |
| 🔁 LangGraph | Stateful graph-based multi-agent orchestration with human-in-the-loop and streaming | LangGraph |
| 🔷 Google ADK | Agent Development Kit with native A2A protocol for cross-framework agent communication | adk-python |
| 🐬 Agno | Full-stack Python framework for collaborative multi-agent teams with shared memory and RAG | agno |
| 🧬 atomic-agents | Building AI agents, atomically | atomic-agents |
| 🖥️ Cradle | General Computer Control framework with strong reasoning and skill curation | Cradle |
| Project Name | Description | Link |
|---|---|---|
| 🛠️ devika | Agentic AI Software Engineer that understands high-level instructions, breaks them into steps, researches, and writes code | devika |
| 🔧 haystack | AI orchestration framework for production-ready LLM applications with RAG, semantic search, and conversational agents | haystack |
| 📝 phidata | Build multi-modal Agents with memory, knowledge, tools and reasoning | phidata |
| 🧠 PraisonAI | Low-code solution for building and managing multi-agent LLM systems | PraisonAI |
| 🧩 griptape | Modular Python framework for AI agents and workflows with chain-of-thought reasoning | griptape |
| 🧬 atomic-agents | Building AI agents, atomically | atomic-agents |
| 🖥️ Cradle | General Computer Control with strong reasoning, self-improvement, and skill curation | Cradle |
| 🤖 OpenAI Agents SDK | Lightweight multi-agent framework with handoffs, guardrails, tracing, and MCP support | openai-agents-python |
| ✅ PydanticAI | Type-safe agent framework for production-grade generative AI apps | pydantic-ai |
Tools for building agentic pipelines visually or with minimal code — ideal for teams that don't write Python from scratch.
| Project Name | Description | Link |
|---|---|---|
| 🌊 Dify | Open-source LLM app development platform with visual workflow builder, RAG pipeline, agent capabilities, and model management. 60k+ stars. | Dify |
| 🌀 Flowise | Drag-and-drop UI to build LLM agent flows. Supports LangChain, LlamaIndex, and dozens of integrations including OpenAI, Bedrock, and Azure. | Flowise |
| 🤖 n8n | Workflow automation platform with AI agent nodes, MCP support, and 400+ integrations. Self-hostable and source-available. | n8n |
| 🛠️ langflow | Low-code visual builder for RAG and multi-agent AI applications. Python-based and model-agnostic. | langflow |
| ⚙️ botpress | Open-source hub to build and deploy GPT/LLM agents with enterprise-grade scalability and integrations. | botpress |
Tools for monitoring, debugging, tracing, and evaluating agent behavior in production.
| Project Name | Description | Link |
|---|---|---|
| 🔭 LangSmith | Agent engineering platform from LangChain for tracing, evaluating, and monitoring LLM/agent runs end-to-end. Pairs with LangGraph. | LangSmith SDK |
| 🛡️ AgentOps | Observability and analytics platform for AI agents — records sessions, tracks costs, detects errors, and supports replay debugging. | AgentOps |
| 🌅 Arize Phoenix | Open-source AI observability and evaluation framework for LLM applications, RAG pipelines, and agents. Supports OpenTelemetry tracing. | Phoenix |
| 📊 PromptFlow | Microsoft's suite for building, evaluating, and deploying LLM-based AI flows with integrated quality measurement. | PromptFlow |
Frameworks and tools focused on evaluating risk, enforcing safety constraints, and mitigating harmful agent outputs.
| Project Name | Description | Link |
|---|---|---|
| 🛡️ EmoAgent | Multi-agent framework that evaluates and mitigates mental health risks in AI-human interactions. Includes EmoEval (benchmarking) and EmoGuard (real-time safeguard) modules. | EmoAgent |
| 🔒 NeMo Guardrails | NVIDIA's open-source toolkit for adding programmable safety guardrails to LLM-based conversational AI — controls topics, tone, and factual accuracy. | NeMo-Guardrails |
| 🧪 Agent-Wiz | CLI tool for threat modeling and visualizing AI agents built using LangGraph, AutoGen, CrewAI, and more. Identifies attack surfaces in multi-agent architectures. | Agent-Wiz |
| Project Name | Description | Link |
|---|---|---|
| 🛡️ SWE-agent | SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024] | SWE-agent |
| ⚙️ botpress | The open-source hub to build & deploy GPT/LLM Agents ⚡️ | botpress |
| 🌠 awesome-llm-apps | Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models. | awesome-llm-apps |
| 🛠️ DB-GPT | AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents | DB-GPT |
| ☁️ E2B | Secure open source cloud runtime for AI apps & AI agents | E2B |
| 🔍 gpt-researcher | LLM based autonomous agent that conducts local and web research on any topic and generates a comprehensive report with citations. | gpt-researcher |
| 🧙♂️ auto-dev | 🧙AutoDev: The AI-powered coding wizard with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant 🐞! Customizable prompts 🎨 and a magic Auto Dev/Testing/Document/Agent feature 🧪 included! 🚀 | auto-dev |
| 🧩 griptape | Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory. | griptape |
| 🌐 Neurite | Fractal Graph-of-Thought. Rhizomatic Mind-Mapping for Ai-Agents, Web-Links, Notes, and Code. | Neurite |
| 🤖 DemoGPT | 🤖 Everything you need to create an LLM Agent—tools, prompts, frameworks, and models—all in one place. | DemoGPT |