6.8 KiB
Pocket Flow is a 100-line minimalist LLM framework
-
Lightweight: Just 100 lines. Zero bloat, zero dependencies, zero vendor lock-in.
-
Expressive: Everything you love from large frameworks—(Multi-)Agents, Workflow, RAG, and more.
-
AI-Friendly: Let AI Agents (e.g., Cursor AI) build Agents—10x productivity boost!
-
To install,
pip install pocketflowor 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!
Why Pocket Flow?
Current LLM frameworks are bloated. You only need 100 lines for LLM Framework!
| Abstraction | App-Specific Wrappers | Vendor-Specific Wrappers | Lines | Size | |
|---|---|---|---|---|---|
| LangChain | Agent, Chain | Many (e.g., QA, Summarization) |
Many (e.g., OpenAI, Pinecone, etc.) |
405K | +166MB |
| LlamaIndex | Agent, Graph | Native for RAG (Summarization, KG Indexing) |
Many [Optional] (e.g., OpenAI, Pinecone, etc.) |
77K (core-only) |
+189MB (core-only) |
| CrewAI | Agent, Chain | Many (e.g., FileReadTool, SerperDevTool) |
Many (e.g., OpenAI, Anthropic, Pinecone, etc.) |
18K | +173MB |
| Haystack | Agent, Graph | Many (e.g., QA, Summarization) |
Many (e.g., OpenAI, Anthropic, Pinecone, etc.) |
31K | +195MB |
| SmolAgent | Agent | Some (e.g., CodeAgent, VisitWebTool) |
Some (e.g., DuckDuckGo, Hugging Face, etc.) |
8K | +198MB |
| LangGraph | Agent, Graph | Some (e.g., Semantic Search) |
Some (e.g., PostgresStore, SqliteSaver, etc.) |
37K | +51MB |
| AutoGen | Agent | Some (e.g., Tool Agent, Chat Agent) |
Many [Optional] (e.g., OpenAI, Pinecone, etc.) |
7K (core-only) |
+26MB (core-only) |
| PocketFlow | Graph | None | None | 100 | +56KB |
Pocket Flow also makes an excellent educational resource by revealing exactly how an LLM framework works under the hood—without the heavy abstractions of larger libraries.
How does Pocket Flow work?
The 100 lines capture the core abstraction of LLM frameworks: Graph!
From there, it’s easy to implement popular design patterns like (Multi-)Agents, Workflow, RAG, etc.
How to Use Pocket Flow?
🚀 It's highly recommended to build Agents with Agents—the fastest development paradigm!
-
😎 Humans craft the high-level requirements and system design.
-
🤖 AI agents (e.g., Cursor AI) handle the low-level implementation.
Check out the video to see the process in action!
What can Pocket Flow build?
✨ Below are examples of LLM Apps:
| Formal App Name | Informal One-Liner | Difficulty | Learning Objectives |
|---|---|---|---|
| Ask AI Paul Graham | Ask AI Paul Graham, in case you don't get in | ★★☆ Medium |
RAG Map Reduce Text-to-Speech |
| Youtube Summarizer | Explain YouTube Videos to you like you're 5 | ★☆☆ Beginner |
Map Reduce |
| Cold Opener Generator | Instant icebreakers that turn cold leads hot | ★☆☆ Beginner |
Map Reduce Web Search |
-
Want to learn how I built these LLM Apps? Check out my YouTube!
-
Want to create your own Python project? Start with this template!