[](https://the-pocket.github.io/PocketFlow/)
Pocket Flow is a [100-line](pocketflow/__init__.py) minimalist LLM framework
- **Lightweight**: Just the core graph abstraction in 100 lines. Zero bloat, zero dependencies, zero vendor lock-in.
- **Expressive**: Everything you love from larger frameworks—([Multi-](https://the-pocket.github.io/PocketFlow/design_pattern/multi_agent.html))[Agents](https://the-pocket.github.io/PocketFlow/design_pattern/agent.html), [Workflow](https://the-pocket.github.io/PocketFlow/design_pattern/workflow.html), [RAG](https://the-pocket.github.io/PocketFlow/design_pattern/rag.html), and more.
- **AI-Friendly**: Intuitive enough for AI agents (e.g., Cursor AI) to build agents!
- **Principled**: Built with modularity and clear separation of concerns at its heart for maintainable codes.
- To install, ```pip install pocketflow```or just copy the [source code](pocketflow/__init__.py) (only 100 lines).
- To learn more, check out the [documentation](https://the-pocket.github.io/PocketFlow/). For an in-depth design dive, read the [essay](https://github.com/The-Pocket/.github/blob/main/profile/pocketflow.md).
- 🎉 We now have a [discord](https://discord.gg/hUHHE9Sa6T)!
## What can Pocket Flow build?
✨ Below are examples of LLM Apps:
| Formal App Name | Informal One-Liner |Difficulty | Learning Objectives |
| :------------- | :------------- | :------------- | :--------------------- |
| [Ask AI Paul Graham](https://github.com/The-Pocket/Tutorial-YC-Partner) | Ask AI Paul Graham, in case you don't get in | ★★☆
*Medium* | [RAG](https://the-pocket.github.io/PocketFlow/design_pattern/rag.html)
[Map Reduce](https://the-pocket.github.io/PocketFlow/design_pattern/mapreduce.html)
[Text-to-Speech](https://the-pocket.github.io/PocketFlow/utility_function/text_to_speech.html) |
| [Youtube Summarizer](https://github.com/The-Pocket/Tutorial-Youtube-Made-Simple) | Explain YouTube Videos to you like you're 5 | ★☆☆
*Beginner* | [Map Reduce](https://the-pocket.github.io/PocketFlow/design_pattern/mapreduce.html) |
| [Cold Opener Generator](https://github.com/The-Pocket/Tutorial-Cold-Email-Personalization) | Instant icebreakers that turn cold leads hot | ★☆☆
*Beginner* | [Map Reduce](https://the-pocket.github.io/PocketFlow/design_pattern/mapreduce.html)
[Web Search](https://the-pocket.github.io/PocketFlow/utility_function/websearch.html) |
- Want to learn how I vibe code these LLM Apps? Check out [my YouTube](https://www.youtube.com/@ZacharyLLM?sub_confirmation=1)!
- Want to create your own Python project? Start with [this template](https://github.com/The-Pocket/PocketFlow-Template-Python)!
## Why Pocket Flow?
🚀 **Agents build Agents** – the fastest paradigm for building LLM systems!
- 😎 **Humans** craft the **high-level requirements and system design**.
- 🤖 **AI agents** (e.g., Cursor AI) handle the **low-level implementation**.
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.
3. 😐 **Without a framework**, code is *ad hoc*—suitable only for immediate tasks, *not modular or maintainable*.
5. **🥰 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 *simplicity* or *flexibility*.
## How does Pocket Flow work?
The [100 lines](pocketflow/__init__.py) capture the core Graph abstraction of LLM frameworks:
From there, it’s easy to implement popular design patterns like ([Multi-](https://the-pocket.github.io/PocketFlow/design_pattern/multi_agent.html))[Agents](https://the-pocket.github.io/PocketFlow/design_pattern/agent.html), [Workflow](https://the-pocket.github.io/PocketFlow/design_pattern/workflow.html), [RAG](https://the-pocket.github.io/PocketFlow/design_pattern/rag.html), etc.
## How to start?
- **For quick questions**: Use the [GPT assistant](https://chatgpt.com/g/g-677464af36588191b9eba4901946557b-pocket-flow-assistant) (note: it uses older models not ideal for coding).
- **For one-time LLM task**: Create a [ChatGPT](https://help.openai.com/en/articles/10169521-using-projects-in-chatgpt) or [Claude](https://www.anthropic.com/news/projects) project; upload the [docs](docs) to project knowledge.
- **For LLM App development**: Use [Cursor AI](https://www.cursor.com/).
- If you want to start a new project, check out the [project template](https://github.com/The-Pocket/PocketFlow-Template-Python).
- If you already have a project, copy [.cursorrules](.cursorrules) to your project root as [Cursor Rules](https://docs.cursor.com/context/rules-for-ai).
