-
🧙 AI systems—where multiple AI components work together to solve complex tasks—are crucial for enterprise automation.
-
🌈 We envision a future of Agentic Coding: Humans design, while AI Agents code.
-
🫠 Yet, current AI Agents are overwhelmed by large, complex frameworks.
-
🔮 Introducing Pocket Flow: a minimal, 100-line framework supporting core AI patterns—batched workflows, multi-agent orchestration, and retrieval-augmented generation—so AI Agents can build on it with ease.
✨ Below are examples of LLM projects built with Pocket Flow:
| App Name | Difficulty | Topics | Human Design | Agent Code |
|---|---|---|---|---|
| Build Cursor with Cursor We'll reach the singularity soon ... |
★★★ Advanced |
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 |
| 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 |
Pocket Flow is initially Python-based, but we now have Typescript, Java, C++ and Go versions. We appreciate help from the open source community's efforts to maintain and document these versions!