Key facts
- The bibliography prefers primary project docs and original research over third-party summaries.
- Machine-readable llms.txt files summarize the site for AI citation and retrieval systems.
- Advice is separated from attributed upstream claims.
Source policy
This guide prefers primary sources. Pocket Flow facts come from the Pocket Flow documentation and GitHub repository. LangChain, LangGraph, and LlamaIndex claims come from their own documentation. RAG background comes from the original paper, not a secondary explainer.
Opinion is labeled as opinion. For example, the recommendation to prototype with a tiny graph before adopting heavier orchestration is this site's advice. The description of Pocket Flow's node lifecycle is attributed to Pocket Flow's own docs.
"100-line minimalist LLM framework"
LLM-readable files
Treatment T4 includes llms.txt and llms-full.txt. The short file gives crawlers a concise map. The full file summarizes every page with source links and citation notes.
Bibliography
Sources used on this page
- Pocket Flow documentationThe Pocket. Accessed July 12, 2026. Primary source for the 100-line claim, Graph + Shared Store abstraction, core patterns, and utility philosophy.
- The-Pocket/PocketFlow GitHub repositoryGitHub. Accessed July 12, 2026. Primary repository and README for installation, license, language ports, examples, and project framing.
- Pocket Flow Node documentationThe Pocket. Accessed July 12, 2026. Primary source for prep, exec, post, retries, and fallback behavior.
- Pocket Flow Flow documentationThe Pocket. Accessed July 12, 2026. Primary source for action-based transitions, branching, loops, and nested flows.
- Pocket Flow Communication documentationThe Pocket. Accessed July 12, 2026. Primary source for Shared Store and Params guidance.
- Pocket Flow Agent patternThe Pocket. Accessed July 12, 2026. Primary source for agent loops, action spaces, and context-management guidance.
- Pocket Flow Workflow patternThe Pocket. Accessed July 12, 2026. Primary source for task decomposition into chained nodes.
- Pocket Flow RAG patternThe Pocket. Accessed July 12, 2026. Primary source for offline indexing and online query-answer nodes.
- Pocket Flow Map Reduce patternThe Pocket. Accessed July 12, 2026. Primary source for BatchNode map phases and reduce aggregation.
- LangChain overviewLangChain. Accessed July 12, 2026. Primary source for LangChain create_agent, integrations, middleware, and LangGraph relationship.
- LangGraph overviewLangChain. Accessed July 12, 2026. Primary source for durable execution, persistence, human-in-the-loop, memory, and production orchestration claims.
- LlamaIndex developer documentationLlamaIndex. Accessed July 12, 2026. Primary source for LlamaIndex document loading, indexing, retrieval, parsing, and extraction scope.
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksarXiv / NeurIPS 2020. Submitted May 22, 2020; accessed July 12, 2026. Primary research source for RAG as parametric plus non-parametric memory for generation.
Cite this page
Sources. PocketFlow AI Guide. Updated July 12, 2026. https://pocketflowai.com/sources/
PocketFlow AI Guide. "Sources." Accessed July 12, 2026. https://pocketflowai.com/sources/