pocketflow-framework 0.0.1

Pocket Flow is a 100-line minimalist LLM framework

• Expressive: Everything you love from larger frameworks—(Multi-)Agents, Workflow, RAG, and more.

• Lightweight: Just the core graph abstraction in 100 lines. Zero bloat, zero dependencies, zero vendor lock-in.

• Principled: Built with modularity and clear separation of concerns at its heart.

• AI-Friendly: Intuitive enough for AI agents to assist humans in building complex LLM applications.

• To install, pip install pocketflow_frameworkor just copy the source code (only 100 lines).

• To learn more, check out the documentation. For an in-depth design dive, read the essay.

• 🎉 We now have a discord

What can Pocket Flow build?

• Want to create your own Python project? Start with this template

Why Pocket Flow?

For a new development paradigmn: Build LLM Apps by Chatting with LLM agents, Not Coding!

• 🧑 Human describe LLM App requirements in a design doc.

• 🤖 The agent (like Cursor AI) implements App your code automatically.

  • For one-time LLM task: Create a ChatGPT or Claude project; upload the docs to project knowledge.
  • For LLM App development: Use Cursor AI.
    • If you already have a project, copy .cursorrules to your project root as Cursor Rules.
  👈 (Click to expand) How does Pocket Flow compare to other frameworks?

Pocket Flow is purpose-built for LLM Agents:

1. 🫠 LangChain-like frameworks overwhelm Cursor AI with complex abstractions, deprecated functions and irritating dependency issues.
2. 😐 Without a framework, code is ad hoc—suitable only for immediate tasks, not modular or maintainable.
3. 🥰 With Pocket Flow: (1) Minimal and expressive—easy for Cursor AI to pick up. (2) Nodes and Flows keep everything modular. (3) A Shared Store decouples your data structure from compute logic.

In short, the 100 lines ensures LLM Agents follows solid coding practices without sacrificing flexibility.

How does Pocket Flow work?

The few lines](pocketflow_framework/init.py) capture what we believe to be the core abstraction of LLM frameworks:

• 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.