awesome-ai-agents

A curated list of frameworks, tools, and resources for building and deploying AI agents. From multi-agent systems to autonomous coding assistants, this repository covers the latest advancements in AI agent technology. Perfect for developers, researchers, and AI enthusiasts exploring the future of autonomous systems.
https://github.com/nipunaranasinghe/awesome-ai-agents

Last synced: 2 days ago
JSON representation

🌟 Core Frameworks
- Google ADK (Agent Development Kit) - python) |Code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents |
- CrewAI - based agent orchestration, task delegation |
- Agency Swarm - swarm) |Reliable multi-agent orchestration using OpenAI Assistants API |
- ChatDev
- MetaGPT - based agents |
- AgentVerse - agent simulation environments for research |
- SuperAGI - source AGI framework, multi-modal agents |
- AGiXT - XT/AGiXT) |Adaptive automation platform with persistent memory |
- Upsonic - oriented |
- AutoGen - agent conversations, GPT-4 integration, customizable workflows |
- Neurolink - provider AI agent framework, unifies 12+ LLM providers, workflow orchestration |
- LangChain - ai/langchain) |Tool integration, memory management, agent chaining |
- OpenAI Assistants API (SDK) - python) |Build AI assistants with tools and persistent threads via SDK |
- LangGraph - ai/langgraph) |Stateful, multi-actor applications with LLMs |
- AgentOps - AI/agentops) |Monitoring, cost tracking, and benchmarking SDK for agents |
- LLMStack - code multi-agent framework with data workflows |
🚀 Specialized Agents
- 🗣️ Programming Language Agents
  - LangChain4j
  - TypeChat - safe LLM outputs using TypeScript types |
  - LangChain.rb
  - OpenAI Agents (Python) - agents-python) |Lightweight, provider-agnostic agent framework |
  - Swarms-rs - Swarm-Corporation/swarms-rs) |Swarm-based agent orchestration in Rust |
  - AnythingLLM - Labs/anything-llm) |All-in-one AI agent builder with RAG and UI |
  - LangChain.js - ai/langchainjs) |JS version of LangChain |
  - Semantic Kernel - kernel) |Integrate LLMs into .NET apps |
  - Haystack - ai/haystack) |Search and question answering agents |
  - LlamaIndex.js - llama/LlamaIndexTS) |JS version of LlamaIndex |
  - LangChainGo
- 🎨 Creative Agents
  - ShortGPT - form video generation agent |
  - AI-town - infra/ai-town) |Virtual world simulation with AI agents |
- 💻 Coding Agents
  - GPT Pilot - io/gpt-pilot) |Assists in writing and debugging code |
  - Aider - gauthier/aider) |AI pair programming in terminal |
  - Devika
  - SWE-agent - nlp/SWE-agent) |AI agent for software engineering tasks |
  - OpenDevin - source coding automation platform |
  - Plandex - ai/plandex) |AI coding engine for complex projects |
  - OpenHands - Hands-AI/OpenHands) |Open-source AI software development agents (formerly OpenDevin) |
  - TaskWeaver - first agent framework for analytical tasks |
- 🔬 Research Agents
  - DeerFlow - flow) |Framework for deep research with web search and Python execution |
  - GPT Researcher - researcher) |Autonomous agent for comprehensive research |
  - Storm - oval/storm) |Multi-agent system for collaborative reasoning |
- 🌐 Web Agents
  - NanoBrowser - based AI browsing agent |
⚙️ Agent Operations
- 🚀 Deployment
  - Daytona - generated code |
  - E2B - dev/E2B) |Secure sandboxed environments for agents |
  - OctoAI
  - Modal - labs/modal-client) |Serverless runtime for AI workloads |
- 🧠 Memory
  - MemGPT - based agents. |
  - Letta (formerly MemGPT) - ai/letta) |Dynamic, adaptive agent memory system |
  - ChromaDB - core/chroma) |Vector DB for memory/context |
  - Weaviate
- 📊 Evaluation
  - AgentBench - environment testing for agents |
  - LangTrace - Labs/langtrace) |Monitoring and trace visualization |
  - Agent Evaluation - evaluation) |Benchmarking agent capabilities |
  - Simple Evals - evals) |OpenAI's lightweight LLM evaluation library |
📚 Research & Benchmarks
- 📄 Papers
  - arXiv
  - arXiv - agent systems |
  - arXiv
  - arXiv
  - arXiv - based agents |
  - arXiv
- 📊 Benchmarks
  - SOTOPIA-π - lab/sotopia-pi) |Social intelligence benchmark for multi-agent systems |
  - ToolBench
🌐 Community Resources
- 👥 Communities
  - GitHub
  - Join
  - Discord
- 📰 Newsletters
  - Subscribe
  - Subscribe
  - Subscribe
  - Subscribe
  - Subscribe
Community Resources
- Communities
  - Join
  - Join
  - Join
- Newsletters
  - Subscribe
🚀 Contributors
- 📰 Newsletters
  - ![Contributors - ai-agents/graphs/contributors)
  - stargazers
  - ![Contributors - ai-agents/graphs/contributors)
Contributing
- 📰 Newsletters
  - repository

Programming Languages

Python 29 TypeScript 9 Go 3 JavaScript 2 Ruby 1 Shell 1 Java 1 C# 1 Rust 1 Jupyter Notebook 1

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

awesome-ai-agents

🌟 Core Frameworks

🚀 Specialized Agents

🗣️ Programming Language Agents

🎨 Creative Agents

💻 Coding Agents

🔬 Research Agents

🌐 Web Agents

⚙️ Agent Operations

🚀 Deployment

🧠 Memory

📊 Evaluation

📚 Research & Benchmarks

📄 Papers

📊 Benchmarks

🌐 Community Resources

👥 Communities

📰 Newsletters

Community Resources

Communities

Newsletters

🚀 Contributors

📰 Newsletters

Contributing

📰 Newsletters