github.com/The-Pocket/PocketFlow @v0.0.0

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—(Multi-)Agents, Workflow, RAG, and more.

• Agentic Coding: 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 | | CrewAI | Agent, Chain | Many

^{_{(e.g., FileReadTool, SerperDevTool)}} | Many

^{_{(e.g., OpenAI, Anthropic, Pinecone, etc.)}} | 18K | +173MB | | 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 |

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.

✨ Below are basic tutorials:

Name	Difficulty	Description
Chat	☆☆☆

Dummy | A basic chat bot with conversation history | | RAG | ☆☆☆

Dummy | A simple Retrieval-augmented Generation process | | Workflow | ☆☆☆

Dummy | A writing workflow that outlines, writes content, and applies styling | | Map-Reduce | ☆☆☆

Dummy | A resume qualification processor using map-reduce pattern for batch evaluation | | Agent | ☆☆☆

Dummy | A research agent that can search the web and answer questions | | Streaming | ☆☆☆

Dummy | A real-time LLM streaming demo with user interrupt capability | | Multi-Agent | ★☆☆

Beginner | A Taboo word game for asynchronous communication between two agents | | Supervisor | ★☆☆

Beginner | Research agent is getting unreliable... Let's build a supervision process| | Parallel | ★☆☆

Beginner | A parallel execution demo that shows 3x speedup | | Thinking | ★☆☆

Beginner | Solve complex reasoning problems through Chain-of-Thought | | Memory | ★☆☆

Beginner | A chat bot with short-term and long-term memory |

👀 Want to see other tutorials for dummies? Create an issue!

How to Use Pocket Flow?

🚀 Through Agentic Coding—the fastest LLM App development paradigm-where humans design and agents code!

✨ Below are examples of more complex LLM Apps:

App Name	Difficulty	Topics	Human Design	Agent Code
Build Cursor with Cursor

^{_{We'll reach the singularity soon ...}} | ★★★

Advanced | Agent | Design Doc | Flow Code | Ask AI Paul Graham

^{_{Ask AI Paul Graham, in case you don't get in}} | ★★☆

Medium | RAG

Map Reduce

TTS | Design Doc | Flow Code | Youtube Summarizer

^{_{Explain YouTube Videos to you like you're 5}} | ★☆☆

Beginner | Map Reduce | Design Doc | Flow Code | Cold Opener Generator

^{_{Instant icebreakers that turn cold leads hot}} | ★☆☆

Beginner | Map Reduce

Web Search | Design Doc | Flow Code

• Want to learn Agentic Coding?
• To setup, read this post!

• Check out my YouTube! Read this Guide!

• Want to build your own LLM App? Start with this template!