|
|
||
|---|---|---|
| assets | ||
| cookbook | ||
| docs | ||
| pocketflow | ||
| tests | ||
| .gitignore | ||
| LICENSE | ||
| README.md | ||
| setup.py | ||
README.md
Pocket Flow - LLM Framework in 100 Lines
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). -
If the 100 lines are too terse, check out a friendlier intro.
-
Documentation: https://the-pocket.github.io/PocketFlow/
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 built for LLM Agents to build LLM apps—especially if you’re using Cursor AI:
- 🫠 LangChain-like frameworks overwhelm Cursor AI with complex abstractions and deprecated functions.
- 😐 Without No Framework, Cursor AI writes functional code but lacks modularity and maintainability.
- 🥰 With Pocket Flow: (1) Minimal and expressive—easy for Cursor AI. (2) Nodes and Flows keep the codes modular and maintainable. (3) Shared store separates data from compute logic.
With just 100 lines, Pocket Flow ensures Cursor AI follows solid coding practices without sacrificing flexibility.
To set up:
-
Cursor Rules: Copy .cursorrules into your project’s root.
-
ChatGPT & Claude: Create a project (ChatGPT andClaude) and upload the docs folder to project knowledge.
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, it’s 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