phowell
/
pocketflow
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
364 Commits 1 Branch 0 Tags 48 MiB
Python 71.6%
Jupyter Notebook 20.4%
HTML 7.6%
CSS 0.4%
Go to file
zachary62 0a3b108283 update agent 2025-03-13 20:19:10 -04:00
assets update agent 2025-03-13 18:36:16 -04:00
cookbook para 2025-03-11 16:16:05 -04:00
docs update agent 2025-03-13 20:19:10 -04:00
pocketflow m 2025-02-02 22:30:18 +00:00
tests rename as mini llm flow is poor 2025-01-09 03:01:25 +00:00
.cursorrules update cursor rule 2025-03-11 19:27:43 -04:00
.gitignore add examples 2024-12-27 05:29:24 +00:00
LICENSE Create LICENSE 2024-12-26 00:44:17 -05:00
README.md Update README.md 2025-03-13 11:07:58 -04:00
setup.py track the current retry 2025-01-25 05:39:44 +00:00

README.md

License: MIT Docs

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!