Autogen enables building next-gen LLM apps via multi-agent conversations to accomplish tasks. Customizable & conversable agents flexibly combine LLMs, human input & tools. Open source framework simplifies orchestration, automation & optimization of complex LLM workflows.
Autogen is an open-source framework that enables developers to build next-generation large language model (LLM) applications using multiple agents that can converse with each other to solve complex tasks.
🤖 Highly customizable and conversable agents that can flexibly combine LLMs, human inputs, and external tools
🔁 Supports advanced conversation flows and topologies between multiple collaborating agents
🎚️ Simplifies orchestration, automation and optimization of workflows powered by LLMs
❇️ Agents can operate in various modes like fully automated, hybrid, or tools-only without needing code changes
📱 Ready-made building blocks make developing sophisticated assistants smooth
Whether you want to build a mathematical assistant, a coding sidekick, a conversational question-answering system, or any other multi-agent LLM-powered app, Autogen provides flexible constructs to make it possible with minimal effort.
It delivers an extensive suite of capabilities essential for creating robust, production-ready systems that can solve tasks through agent collaboration. Check out the documentation and examples to see it in action.
🚀 Productivity - Orchestrate multiple LLMs and tools to tackle complex workflows 10x faster than solo models.
🎯 Specialization - Assign roles matched to each asset's strengths for higher quality output.
🔁 Reusability - Codified workflows, data, and prompts simplify building new use cases.
⚙️ Configurability - Easily customize environment rules, SOPs, and interactions to suit any need.
👥 Accessibility - Intuitive abstractions open up complex multi-agent systems to more developers.
In summary, AutoGen provides the perfect blend of power and simplicity for engineers to leverage multiple LLMs and tools for advanced yet reliable applications. Innovation unlocks for developers across skill levels with modular building blocks and guardrails.
- 👷🏽♀️ Builders: Chi Wang, Qingyun Wu, Julia Kiseleva, Negar Arabzadeh
- 💾 Used in 1.3k repositories
- 👩🏽💻 Contributors: 172
- 💫 GitHub Stars: 19.4k
- 🍴 Forks: 2.2k
- 👁️ Watch: 206
- 🪪 License: Apache-2.0
- 🔗 Links: Below 👇🏽
- GitHub Repository: https://github.com/microsoft/autogen
- Official Website: https://microsoft.github.io/autogen/
- Twitter account: https://twitter.com/pyautogen
- Research: https://microsoft.github.io/autogen/docs/Research/
- Profile in The AI Engineer: https://github.com/theaiengineer/awesome-opensource-ai-engineering/blob/main/libraries/autogen.md
🧙🏽 Follow The AI Engineer for daily insights tailored to AI engineers and subscribe to our newsletter. We are the AI community for hackers!