Go to file
Zachary Huang 173da2cec0
Update README.md
2025-02-24 16:56:11 -05:00
assets emphasize agent build agent 2025-02-24 09:26:03 -05:00
cookbook update readme 2025-02-23 23:56:23 -05:00
docs update the guide 2025-02-21 19:30:14 -05:00
pocketflow m 2025-02-02 22:30:18 +00:00
tests rename as mini llm flow is poor 2025-01-09 03:01:25 +00:00
.gitignore add examples 2024-12-27 05:29:24 +00:00
LICENSE Create LICENSE 2024-12-26 00:44:17 -05:00
README.md Update README.md 2025-02-24 16:56:11 -05:00
setup.py track the current retry 2025-01-25 05:39:44 +00:00

README.md

Pocket Flow - LLM Framework in 100 Lines

License: MIT Docs


A 100-line minimalist LLM framework for (Multi-)Agents, Workflow, RAG, etc.

Why Pocket Flow?

Pocket Flow lets you build LLM apps just by chatting with agents like Cursor AI—no need for low-level coding.

Pocket Flow is designed for LLM Agents. If youre using Cursor AI...

  1. 🫠 With frameworks like LangChain: Cursor AI often relies on deprecated packages or “hallucinates” functions.
  2. 😐 with No Framework: Cursor AI writes functional but not maintainable for real projects.
  3. 🥰 with Pocket Flow: (1) Minimal and expressive—easy for Cursor AI. (2) Nodes and flows keep the codes modular and maintainable. (3) The shared store separates data from compute logic.

With just 100 lines, Pocket Flow ensures Cursor AI follows good coding practices without sacrificing flexibility.


To set up:

What Is Pocket Flow?

The 100 lines capture what we believe to be the core abstraction of LLM projects:

  • Computation: A graph that breaks down tasks into nodes, with branching, looping, and nesting.
  • Communication: A shared store that all nodes can read and write to.


From there, its easy to implement popular design patterns like (Multi-)Agents, Workflow, RAG, etc.



  • To learn more about how it works, check out the documentation
  • For an in-depth dive into the design, check out the essay