Skip to the page

Data / Repositories / Retrieval augmented generation / Python

Python Retrieval augmented generation repositories on GitHub: 4 ranked by stars

4 public Python repositories tagged Retrieval augmented generation are on GitHub, with 38,703 stars between them; 3 had a push in the last 30 days. The most starred: StarTrail-org/LEANN (13,027), The-Pocket/PocketFlow (11,230), LearningCircuit/local-deep-research (9,190).

SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.

Every repository, most starred first

RepositoryWhat it isStarsForksLicenseLast pushRead
StarTrail-org/LEANN[MLsys2026 Best Paper]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.13,0271,184MITOct 14Oct 14
The-Pocket/PocketFlowPocket Flow: 100-line LLM framework. Let Agents build Agents!11,2301,214MITJul 26Oct 11
LearningCircuit/local-deep-research~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents.…9,190845MITOct 14Oct 14
vitali87/code-graph-ragThe ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs5,256699MITOct 14Oct 14

Other languages

Related topics

Every Retrieval augmented generation repository

Read from GitHub by SpecStream between October 11, 2026 and October 14, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.