PocketFlow
Minimalist 100-line LLM framework enabling Agent creation and workflow orchestration.
GraphCanon updated 2d · GitHub synced 2d · 25 views this month
Decision brief
PocketFlow is a minimalist 100-line Python framework designed for efficient AI agent development and deployment, offering support for multi-agent systems, workflows, and RAG with very low dependency requirements.
Good fit when
- - When you need a lightweight solution (<100 lines) that minimizes dependencies and avoids vendor lock-in for developing LLM-based agents.
- - If you are working on projects where simplicity and quick prototyping are key, such as in academic research or proof-of-concept development.
Avoid when
- - Avoid if your project requires complex feature integration that typically demands a larger codebase with more extensive dependencies.
- - Not suitable for large-scale enterprise applications requiring robust, vendor-supported solutions with comprehensive documentation and support frameworks.
- Hosting:
- unknown - No specific cloud or hosting requirements mentioned. Its lightweight nature makes it versatile across various deployment environments from local development to cloud-based systems.
- Pricing:
- freemium - Free and open-source, with no direct costs for the core framework but might require additional investment in complementary services or support for larger projects.
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (21d since push)
- As of 2d
- Provenance
- Not a fork · Organization account
- As of 2d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install PocketFlowHow it fits your stack(9)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
PocketFlow is a lightweight, agentic AI coding platform designed for efficient agent development and deployment. It supports multi-agent systems, workflows, and RAG (Retrieval-Augmented Generation) with minimal dependencies.
Capability facts
- Languages
- python
Source: github.language · Aug 17, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 17, 2026)
| LangChain | Agent, Chain | Many <br><sup><sub>(e.g., QA, Summarization)</sSource link
Source: README excerpt (regex_v1, Aug 17, 2026)
- To install, ```pip install pocketflow```or just copy the [source code](https://github.com/The-Pocket/PockeSource link
Source: README excerpt (regex_v1, Aug 17, 2026)
uang.substack.com/p/agentic-coding-the-most-fun-way-to)**: Let AI Agents (e.g., Cursor AI) build Agents—10x productivity boost!Source link
Tags
README
English | 中文 | Español | 日本語 | Deutsch | Русский | Português | Français | 한국어
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 |
| S |
For agents
This page has a .md twin and JSON over the API.