PocketFlow — Agent Frameworks

What is PocketFlow?

PocketFlow is a reaction to frameworks you cannot see the bottom of. The whole thing is roughly a hundred lines with no dependencies: a node does one piece of work in three phases — gather what it needs, do the work, decide what happens next — and the string a node returns picks which edge to follow. Nodes share one plain dictionary. That is the framework. There is no model client, no retry policy for a provider's particular errors, no tracing; you write those, and the cookbook of worked examples stands in for a reference manual. It suits people who would rather own a small amount of code than configure a large amount of someone else's.

What can you do with PocketFlow?

Read the whole framework in one sitting — About a hundred lines with no dependencies, which means you can answer a question about its behaviour by looking rather than by searching an issue tracker.
Three phases per node — Gathering the inputs, doing the work and deciding what happens next are separate methods, so the part that calls a model stays free of the surrounding bookkeeping.
Route by returning a name — A node returns a string and that string picks the next edge, so branching and looping are written where the decision is actually made.
Retry and fall back per node — Each node can be given a number of attempts and a fallback result, so one flaky step does not take the whole flow down.
Batch and async variants of the same shapes — The same node and flow ideas come in versions for running over many items and for waiting on slow calls concurrently.

Before you choose PocketFlow

Nothing wraps the model. The API call, the handling of a provider's rate limits and error shapes, and any record of what a run did are all code you write and maintain.
The documentation is a cookbook of worked examples rather than a reference: for anything the examples do not cover, the hundred lines of source are the specification.

Frequently asked questions

Is PocketFlow free for commercial use?

PocketFlow is released under the MIT licence — OSI-approved open source, which permits commercial use.

How can PocketFlow be deployed?

PocketFlow is available as Runs locally / Self-hosted.

Documentation

Reproduced from the The-Pocket/PocketFlow README, published under MIT. Read the original ↗

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!

Get started with Pocket Flow:

To install, pip install pocketflowor just copy the source code (only 100 lines).
To learn more, check out the video tutorial and documentation
🎉 Join our Discord to connect with other developers building with Pocket Flow!
🎉 Pocket Flow now has Typescript, Java, C++, Go, Rust and PHP versions!

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.

Name	Difficulty	Description
Chat	☆☆☆ Dummy	A basic chat bot with conversation history
Structured Output	☆☆☆ Dummy	Extracting structured data from resumes by prompting
Workflow	☆☆☆ Dummy	A writing workflow that outlines, writes content, and applies styling
Agent	☆☆☆ Dummy	A research agent that can search the web and answer questions
RAG	☆☆☆ Dummy	A simple Retrieval-augmented Generation process
Batch	☆☆☆ Dummy	A batch processor that translates markdown into multiple languages
Streaming	☆☆☆ Dummy	A real-time LLM streaming demo with user interrupt capability
Chat Guardrail	☆☆☆ Dummy	A travel advisor chatbot that only processes travel-related queries
Majority Vote	☆☆☆ Dummy	Improve reasoning accuracy by aggregating multiple solution attempts
Map-Reduce	☆☆☆ Dummy	Batch resume qualification using map-reduce pattern
CLI HITL	☆☆☆ Dummy	A command-line joke generator with human-in-the-loop feedback
Multi-Agent	★☆☆ Beginner	A Taboo word game for async communication between 2 agents
Supervisor	★☆☆ Beginner	Research agent is getting unreliable… Let’s build a supervision process
Parallel	★☆☆ Beginner	A parallel execution demo that shows 3x speedup
Parallel Flow	★☆☆ Beginner	A parallel image processing showing 8x speedup
Thinking	★☆☆ Beginner	Solve complex reasoning problems through Chain-of-Thought
Memory	★☆☆ Beginner	A chat bot with short-term and long-term memory
Text2SQL	★☆☆ Beginner	Convert natural language to SQL queries with an auto-debug loop
Code Generator	★☆☆ Beginner	Generate test cases, implement solutions, and iteratively improve code
MCP	★☆☆ Beginner	Agent using Model Context Protocol for numerical operations
Agent Skills	★☆☆ Beginner	Route requests to reusable markdown skills and apply them in an agent flow
A2A	★☆☆ Beginner	Agent wrapped with A2A protocol for inter-agent communication
Streamlit FSM	★☆☆ Beginner	Streamlit app with finite state machine for HITL image generation
FastAPI WebSocket	★☆☆ Beginner	Real-time chat interface with streaming LLM responses via WebSocket
FastAPI Background	★☆☆ Beginner	FastAPI app with background jobs and real-time progress via SSE
Voice Chat	★☆☆ Beginner	An interactive voice chat application with VAD, STT, LLM, and TTS.
Judge	★☆☆ Beginner	LLM-as-Judge evaluator-optimizer loop for iterative content refinement
Debate	★☆☆ Beginner	Adversarial reasoning with two advocates and an impartial judge
Agentic RAG	★☆☆ Beginner	Agent-driven RAG that decides which documents to read
Self-Healing Mermaid	★☆☆ Beginner	Generate Mermaid diagrams with automatic error recovery
Heartbeat	★☆☆ Beginner	ClawBot-like always-on periodic monitoring with nested flows
Lead Generation	★★☆ Intermediate	Sales pipeline: scrape, enrich, score, and personalize emails
Newsletter	★★☆ Intermediate	AI newsletter curation: search, filter, summarize, and format
Invoice Processing	★★☆ Intermediate	Extract and validate invoice data from PDFs using vision
NotebookLM	★★☆ Intermediate	Turn documents into a podcast with two AI hosts
Deep Research	★★☆ Intermediate	Recursive map-reduce research with iterative refinement
Coding Agent	★★★ Advanced	Production coding agent with 6 tools, memory, and patch-as-subflow

👀 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
Website Chatbot Turn your website into a 24/7 customer support genius	★★☆ Medium	Agent RAG	Design Doc	Flow Code
Danganronpa Simulator Forget the Turing test. Danganronpa, the ultimate AI experiment!	★★★ Advanced	Workflow Agent	Design Doc	Flow Code
Codebase Knowledge Builder Life’s too short to stare at others’ code in confusion	★★☆ Medium	Workflow	Design Doc	Flow 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?
- Check out my YouTube for video tutorial on how some apps above are made!
- Want to build your own LLM App? Read this post! Start with this template!