FoundationAgents/AFlow
A framework that uses Monte Carlo tree search to automatically generate and optimize agentic workflows composed of LLM-invoking nodes and operators.
Not currently ranked — collecting fresh signals.
star history
AFlow automates the creation of agentic workflows by searching in a code-represented workflow space using Monte Carlo tree search. It replaces manual workflow design with machine-generated solutions, building workflows from configurable nodes (LLM invocations) and reusable operators such as Generate, Format, Review, Revise, and Programmer. The system iteratively selects, expands, evaluates, and updates workflows based on task performance, demonstrating potential to outperform handcrafted agent workflows on various tasks.
Frequently asked
- What is FoundationAgents/AFlow?
- A framework that uses Monte Carlo tree search to automatically generate and optimize agentic workflows composed of LLM-invoking nodes and operators.
- Is AFlow open source?
- Yes — FoundationAgents/AFlow is open source, released under the MIT license.
- What language is AFlow written in?
- FoundationAgents/AFlow is primarily written in Python.
- How popular is AFlow?
- FoundationAgents/AFlow has 556 stars on GitHub.
- Where can I find AFlow?
- FoundationAgents/AFlow is on GitHub at https://github.com/FoundationAgents/AFlow.