A 100-line minimalist LLM framework for (Multi-)Agents, Workflow, RAG, etc.
- Install via
pip install pocketflow, or just copy the source code (only 100 lines). - To learn more, check out the documentation. For an in-depth design dive, read the essay.
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.
How does Pocket Flow compare to other frameworks? Pocket Flow is purpose-built for LLM Agents (e.g., Cursor AI):
- 🫠 LangChain-like frameworks overwhelm Cursor AI with complex and outdated abstractions.
- 😐 Without a framework, code is ad hoc—suitable only for immediate tasks, not modular or maintainable.
- 🥰 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 to set up Pocket Flow for LLM agents?
- For quick questions: Use the GPT assistant (note: it uses older models not ideal for coding).
- For one-time LLM task: Create a ChatGPT or Claude project; upload the docs to project knowledge.
- For LLM App development: Use Cursor AI. Copy .cursorrules to your project root as Cursor Rules.
Below are examples LLM Apps and tutorials
| App Name | Difficulty | Learning Objectives |
|---|---|---|
| Youtube ELI5 Summarizer | ★☆☆ Beginner | Map Reduce |
| AI Paul Graham | ★☆☆ Beginner | RAG |
- Do you want to create your own Python project? Start with this template
The 100 lines 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.
From there, it’s easy to implement popular design patterns like (Multi-)Agents, Workflow, RAG, etc.
