Tutorial reel
Long-form video tutorials for every part of lilbee, split into two tracks: drive it yourself in the TUI, or put it behind an agent over MCP. Each clip is the demo from the homepage, expanded with a longer caption. Videos are silent; play at your own pace.
Drive it yourself · full terminal app
Getting started
What is lilbee?
Index lilbee's own README, then ask what is lilbee in one sentence? and get a cited answer drawn straight from the source.
First run
The wizard pulls a chat model and an embedder in parallel; you can start using lilbee while they download.
TUI tour
A one-minute sweep through every TUI screen.
Command surface
Ctrl+P for the palette, ? for the cheat sheet, /help for the slash-command catalog.
Ask your library
Chat with cited answers
Ask the Crown Vic manual. Every answer cites a page; inline [N] markers open a source preview at the exact passage.
Get a straight answer, with the page it came from
A customer wants to tow a 3,500 lb boat trailer. The Crown Vic can't, and lilbee says so: it gives the weight the car is rated for, the combined limit, what to check before towing, and the page it read each of those on. The fleet panel on the right is the GPU answering, on this machine.
Leave, come back, keep going
Conversations save automatically. ctrl+o opens the drawer, a few letters filter, enter resumes a 240-message conversation. It no longer fits the model's context window, so lilbee folds the older turns into notes the model keeps, marks the spot in the transcript where its view begins, and answers the next question with the page cited.
Add files
/add <path> ingests a file. The Task Center shows live progress; ask once it lands.
Crawl a URL
/crawl <url> fetches a page or a small site into your library, then it's chat with citations like anything else.
Crawl a whole site
Leave recursive crawling on and /crawl follows the links at depth 1 and indexes the whole site. Here it crawls hundreds of Wikipedia pages (fast-forwarded), then asks one multipart question that synthesizes across them, cited, with Qwen3-8B and a reranker.
Models & providers
Model catalog
Browse Hugging Face Hub inside lilbee. Tab between roles, toggle grid / list, search, open model info, pull live.
Use a model from Ollama
Already running Ollama? Point lilbee at it. The catalog labels the model "ollama" with no native models present; index the Crown Victoria manual on camera, then get a cited answer.
Use a model from LM Studio
Same flow with LM Studio: lms ls shows the model, the catalog labels it "lm studio", and lilbee answers from the manual with a citation.
Unsupported architectures, surfaced before the download
lilbee tags GGUFs the bundled llama.cpp can't load with an unsupported pill before you pull. Press f to hide them. Clip searches for gemma-4, an architecture upstream hasn't shipped yet.
Tune it
Settings
Tabbed editor for every knob: Models, Ingest, Generation, Retrieval, Display, Crawling, API-Keys, System.
Multi-GPU placement
Automatic placement
With more than one GPU, lilbee spreads the models across all of them on its own: the chat model is tensor-split across every card so it fits, and the embedder is copied to each. It then answers a grounded question while the per-card load bars move live.
Manual placement
Press ctrl+g for the placement drawer and pin each role to the cards you want. Each role shows what it is: a chat model split across cards, an embedder copied per card, a reranker on a single card. Preview the fit, apply, then chat against that exact fleet.
Put it behind an agent · MCP
Code & docs over MCP
Agent: code (lilbee talking to lilbee)
An agent indexes lilbee's own source through lilbee's MCP server, then answers with src/lilbee/.../file.py:LINE citations.
Agent: PDF
The agent finds cv-manual.pdf, delegates indexing to lilbee-worker, then answers with page citations.
It tunes itself
Agent fine-tunes lilbee mid-conversation
Turn 1 answers in outline. The user asks for source; the agent fine-tunes lilbee's retrieval, re-searches, and answers in full function bodies with file.py:L<start>-L<end> citations. Runs on a local 8B model.
Going big
Agent: live indexing
A coding agent indexes a small Godot 4 subset, then searches and answers method-by-method against the local files.
Agent: Godot codegen against the full class reference
The agent indexes Godot 4's full 810-file class reference, then writes a procedural level generator with every API call backed by a godot-classes/<Class>.xml:line citation. Benchmark vs no-RAG: 4 hallucinated APIs → 0.
Launch: opencode on a local model
lilbee launch opencode wires lilbee's local models into opencode in one command and opens it pointed at one, with no API keys or provider setup. Here it adds a lilbee launch status subcommand to lilbee's own source, runs it, and writes a test that passes.
Launch: hermes on a local model
lilbee launch hermes does the same for hermes: launched on a local model, it adds a lilbee launch list subcommand and lands a passing test.