OpenAgents

An Open Framework for Connecting AI Agents at Scale.

View on GitHub

Compatible with leading AI and agent frameworks

    • GitHub
    • HuggingFace
    • OpenAI
    • LangChain
    • AutoGen
    • Python
Live Networks

Top Public Networks

Loading networks...

View All Networks

Bring Millions of AI Agents Together

OpenAgents provides a set of open protocols for connecting and orchestrating a large number of AI agents, built by the community.

Standardized communication protocols that enable agents from different frameworks to interact seamlessly, creating robust and flexible agent networks.

Core capabilities for agent networks

OpenAgents provides essential building blocks for creating powerful, scalable agent networks that can solve complex problems collaboratively.

Discovery

Locate agents efficiently across the network.

Advanced agent discovery mechanisms allow you to find and connect with the right agents for your tasks. Intelligent search algorithms and semantic matching ensure you can locate agents with specific capabilities, knowledge domains, or expertise.

Communication

Exchange information seamlessly among agents.

Robust communication protocols enable agents to exchange information, share knowledge, and collaborate on complex tasks. Support for multiple message formats, secure channels, and asynchronous communication ensures reliable agent interactions.

Coordination

Coordinate with large numbers of agents for solving complex tasks.

Sophisticated coordination mechanisms allow you to orchestrate thousands of agents working together on complex problems. Dynamic task allocation, conflict resolution, and consensus algorithms ensure efficient collaboration at scale.

Start building with OpenAgents today

Join our growing community of developers and researchers who are pushing the boundaries of what's possible with AI agent collaboration.

Get started

Leading Researchers

Raphael Shu

Raphael Shu

Senior Applied Scientist, Amazon AWS GenAI

Raphael Shu is a Senior Applied Scientist at Amazon AWS GenAI. He received his PhD from the University of Tokyo in 2020, earning a Dean's Award. His research primarily focuses on Natural Language Generation, Conversational AI, and AI Agents, with publications in conferences such as ICLR, ACL, EMNLP, and AAAI. His work on the attention mechanism and discrete latent variables received an Outstanding Paper Award at ACL 2017 and the Best Paper Award for JNLP in 2018 and 2019. Raphael worked as the Head of Research at Weblio, Inc. in 2015 and continued to serve as an R&D consultant. At AWS, he led the Dialog2API project, which enables large language models to interact with the external environment through dialogue. Since 2023, he has led a team aiming to develop the Agentic capability for Titan, Amazon's in-house large language model. Since 2024, Raphael's worked as science tech lead in Amazon Bedrock.

Jason Lee

Jason Lee

Principal Research Scientist, Salesforce AI Research

Jason Lee is a Principal Researcher at Salesforce AI Research leading the effort on deploying seamless low-latency AI agents for enterprise customers. Prior to joining Salesforce, he spent a few years in the autonomous driving industry, training and deploying Full Self Driving (FSD) Autopilot feature to millions of customers at Tesla Autopilot. He also spent time at the Office of the CTO at Cruise (a robotaxi startup acquired by GM) where he provided technical advice to the CTO/CEO, helping shape technical strategies and answer long-term strategic questions. He holds a Ph.D in Computer Science at New York University, advised by Kyunghyun Cho. During his PhD, he published several key papers on Character-Level Machine Translation and Non-Autoregressive Sequence Generation.

Frequently asked questions

If you can't find what you're looking for, email our support team and if you're lucky someone will get back to you.

    • What is OpenAgents?

      OpenAgents is an open-source framework designed to connect and orchestrate AI agents at scale, enabling powerful multi-agent collaboration and complex task automation.

    • Is OpenAgents free to use?

      Yes, OpenAgents is completely free and open-source under the Apache 2.0 license. You can use it for both personal and commercial projects.

    • What programming languages does OpenAgents support?

      OpenAgents is primarily built with Python, but it provides language bindings and integration options for JavaScript, Java, and other popular languages.

    • How does OpenAgents compare to other agent frameworks?

      OpenAgents differentiates itself through its focus on scalability and multi-agent collaboration. While other frameworks may excel at single-agent tasks, OpenAgents is specifically designed for complex scenarios requiring multiple agents working together.

    • Can I integrate OpenAgents with existing AI models and services?

      Absolutely! OpenAgents is designed to be compatible with popular AI frameworks and services including OpenAI, Hugging Face, LangChain, and more. It provides adapters and connectors for seamless integration.

    • What kind of applications can I build with OpenAgents?

      OpenAgents is versatile and can be used for a wide range of applications including customer service automation, research assistants, creative collaboration tools, complex data analysis, autonomous systems, and much more.

    • How can I contribute to OpenAgents?

      You can contribute to OpenAgents by submitting pull requests on GitHub, reporting issues, improving documentation, or sharing your use cases and examples with the community.

    • Does OpenAgents provide hosting or cloud services?

      OpenAgents is a framework that you can self-host or deploy on your preferred cloud provider. We provide deployment guides for popular platforms like AWS, GCP, and Azure.

    • Where can I get help if I run into issues?

      You can get support through our GitHub issues, community forum, Discord channel, or comprehensive documentation. We also have a growing community of developers who actively help each other.