lilbee v0.6.66b
Elastic License 2.0 100% coverage typed

A batteries-included local search engine for your data and code that you can talk to.

Point it at your files, notes, and code; ask questions in plain English. Every answer links back to the file and line. Point it at nothing and it's still a clean local-AI chat with the model catalog wired up; cloud models too if you bring an API key or use a frontier agent over MCP.

one program, one install terminal app command-line tool MCP server web API Python library

It runs on your computer. Your files stay on disk; lilbee uses a cloud model only when you pick one.

install
lilbee first-run setup wizard pulling models

First run: a setup wizard pulls a chat model and an embedder, then drops you straight into chat.

/ scrub. More on the recordings: the full reel →

macOSLinuxWindows
$ pip install --pre lilbee
optional extras
For a pip / uv install, add the name in brackets, e.g. 'lilbee[crawler,litellm]'. The binary, Homebrew, AUR, Nix, and Docker builds bundle all three already. lilbee works without them.
[crawler]index websites too: crawl a docs site or wiki to markdown, then search it offline
[litellm]bridge to popular hosted model providers for chat, vision, or embeddings; you bring the key, the terminal app flags when one's active
[graph]concept-graph search: finds matches plain keyword search misses, with no extra model calls

every release is a pre-release. latest on PyPI →  .  full install guide →

it's early. a ★ on GitHub helps people find it; bug reports and issues are very welcome.

one program

It's the model, the search through your files, and the chat, all in one program. Run it when you want, close it when you're done; nothing left running in the background, no container to keep alive. Want something long-running? Use the command line and manage it yourself.

the usual local-AI setup
  • a model server, always running
  • model files fetched by hand
  • a vector database to stand up
  • code wiring them together
  • a separate app for the interface
  • often a container around it all
a deployment to stand up and keep alive.
lilbee
  • the model runtime (llama.cpp) and the vector index (LanceDB) run inside lilbee, not as separate services to stand up
  • use it as a full-screen terminal app, a command-line tool, a Model Context Protocol server, a web API, or a Python library
  • a built-in model catalog: browse and pull straight from Hugging Face Hub, no hunting for model files yourself
  • a scoped library per project, so each domain stays its own clean encyclopedia
  • runs on a laptop or headless over a remote shell; move it between machines
one install command, sane defaults. point it at a folder, ask.
what it does

feed it your files

Point it at a folder: your man pages, a pile of PDFs, your notes, a codebase. Then talk to them. Every answer tells you the file and line. Each project gets its own library, so nothing bleeds across.

pair it with your agent

Pair it with your favorite agent over MCP. It reads the real code and docs before it answers, cites the file and line, and says "I don't know" instead of guessing.

websites, offline

Crawl a docs site or a wiki, turn it into markdown, and keep it. Search and chat with it offline, even after it goes down.

scans & OCR

Old scans and photos go through OCR or a local vision model and come out as searchable markdown, layout intact.

a note on answers

Answers are only as good as the model you pick and the settings behind it. lilbee ships sane defaults, but exposes 50+ settings you can tune: search, the answers, how your files get read.

go deeper
built on

lilbee stands on established open-source projects and wires them into one program.

lilbee  .  Elastic License 2.0