What is LEANN built with?
LEANN is a Python repo built with FastAPI. It uses AI through einops, evaluate, llama-index-embeddings-huggingface, Ollama, sglang, and 12 more, makes its content with llama-index-readers-file, nbconvert, pypdf2, pypdfium2, pdfplumber, and 1 more, deploys with boto3 and psutil, and uses pyzmq. It has 55,453 written lines, with 65 test files.
Read on November 9, 2026, at commit 07796bd. Read it as markdown
The card says what it's built with. Its whole map opens it up: every part of the code and how it connects to the rest.
Frontend
Interface 1
Backend
The base 1
Data 1
- pyzmq4 files
AI 16
llama-index17 files
- torch10 files
sentence-transformers2 files
mcp1 file
mlx1 file
evaluate
- Ollama
sglang
torchvision
- datasets3 files
- transformers3 files
- flashlib2 files
Services 1
Other repos with a similar stack
Ordered by how much of its stack they share with LEANN, then by stars.
- run-llamallama_index52.9k
LlamaIndex is the document processing platform for AI
19 of 48 in commonCompare → - bojieliai-agent-book57.9k
《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
14 of 48 in commonCompare →
Frequently asked questions
What language is LEANN written in?
What framework does LEANN use?
Does LEANN use AI?
What services does LEANN use?
Does LEANN have tests?
Which repos have a stack like LEANN's?
See inside your code, today.
Paste your repo and see it drawn, part by part: a medium one in under a minute.
Free, no account.
Is it your repo? Add its badge, keep it up to date or take it down →

