科技回声

Hey HN! Been working on this library for architecting stateful LLM agent trees that execute in parallel. Think of it like a AI scheduler for BabyAGIs or AutoGPTs, like:-----Parent (Plan and Adjust): Chief Revenue Officer / VP SalesChildren (Do and Check): 3 Sales Development Representatives; 2 Account Managers; 1 Market Researcher.You can give the CRO a task and it will break it down, distribute it appropriately to its children, and the children will work in parallel on the task.-----Curious to hear your feedback first HN, we're launching on Twitter tomorrow!

The VP of Sales is interesting. I would imagine that agents wouldn't look like the traditional human roles, but would stack fractally under each other, like functions in code do.

This is brilliant and incredibly useful. Also easy to customize.

The VP of Sales is interesting. I would imagine that agents wouldn't look like the traditional human roles, but would stack fractally under each other, like functions in code do.

This is brilliant and incredibly useful. Also easy to customize.

Show HN: Agent Actors – Plan-Do-Check-Adjust with Parallelized LLM Agent Trees

2 条评论

Show HN: Agent Actors – Plan-Do-Check-Adjust with Parallelized LLM Agent Trees

2 条评论