This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Consider using release 0.6.90b448 instead.
Reason given by maintainers: not supported
lilbee
This is an experimental tool and a work in progress. There will be issues with some formats and performance at scale is unknown at this time
A local, offline knowledge base. Add documents and code, ask questions grounded in what's actually there.
- Why lilbee
- Demos
- Install
- Quick start
- Interactive chat
- Agent integration
- Supported formats
- Configuration
- How it works
Why lilbee
Index your documents and code into a local knowledge base, then ask questions grounded in what's actually there. Most tools like this only handle code. lilbee handles PDFs, Word docs, epics — and code too, with AST-aware chunking.
- Documents and code alike — add anything from a vehicle manual to an entire codebase
- Fully offline — runs on your machine with Ollama and LanceDB, no cloud APIs or Docker
- Works with AI agents — MCP server and JSON CLI so agents can search your knowledge base too
Add files (lilbee add), then ask questions or search. Once indexed, search works without Ollama — agents use their own LLM to reason over the retrieved chunks.
Demos
AI agent using lilbee (opencode)
An AI coding agent shells out to lilbee --json search to ground its answers in your documents.
Interactive local offline chat
[!NOTE] Entirely local on a 2021 M1 Pro with 32 GB RAM.
Model switching via tab completion, then a Q&A grounded in an indexed PDF.
Code index and search
Add a codebase and search with natural language. Tree-sitter provides AST-aware chunking.
JSON output
Structured JSON output for agents and scripts.
Install
Prerequisites
- Python 3.11+
- Ollama — the embedding model (
nomic-embed-text) is auto-pulled on first sync. If no chat model is installed, lilbee prompts you to pick and download one. - Optional (for image OCR):
brew install tesseract/apt install tesseract-ocr
First-time download: If you're new to Ollama, expect the first run to take a while — models are large files that need to be downloaded once. For example,
qwen3:8bis ~5 GB and the embedding modelnomic-embed-textis ~274 MB. After the initial download, models are cached locally and load in seconds. You can check what you have installed withollama list.
Install
pip install lilbee # or: uv tool install lilbee
Development (run from source)
git clone https://github.com/tobocop2/lilbee && cd lilbee
uv sync
uv run lilbee
Quick start
# Check version
lilbee --version
# Chat with a local LLM (requires Ollama)
lilbee
# Add documents to your knowledge base
lilbee add ~/Documents/manual.pdf ~/notes/
# Ask questions — answers come from your documents via a local LLM
lilbee ask "What is the recommended oil change interval?"
# Search documents — returns raw chunks, no LLM needed at query time
lilbee search "oil change interval"
# Remove a document from the knowledge base
lilbee remove manual.pdf
# Use a different chat model
lilbee ask "Explain this" --model qwen3
# Check what's indexed
lilbee status
Interactive chat
Running lilbee or lilbee chat enters an interactive REPL with conversation history, streaming responses, and slash commands:
| Command | Description |
|---|---|
/status |
Show indexed documents and config |
/add [path] |
Add a file or directory (tab-completes paths) |
/model [name] |
Switch chat model — no args opens an interactive picker; with a name, switches directly (tab-completes installed models) |
/version |
Show lilbee version |
/reset |
Delete all documents and data (asks for confirmation) |
/help |
Show available commands |
/quit |
Exit chat |
Slash commands and paths tab-complete. A spinner shows while waiting for the first token from the LLM.
Agent integration
lilbee can serve as a local retrieval backend for AI coding agents via MCP or JSON CLI. See docs/agent-integration.md for setup and usage.
Supported formats
| Format | Extensions | Requires |
|---|---|---|
.pdf |
— | |
| Office | .docx, .xlsx, .pptx |
— |
| eBook | .epub |
— |
| Images (OCR) | .png, .jpg, .jpeg, .tiff, .bmp, .webp |
Tesseract |
| Data | .csv, .tsv |
— |
| Text | .md, .txt, .html, .rst |
— |
| Code | .py, .js, .ts, .go, .rs, .java and 150+ more via tree-sitter (AST-aware chunking) |
— |
Configuration
All settings are configurable via environment variables:
| Variable | Default | Description |
|---|---|---|
LILBEE_DATA |
(platform default) | Data directory path |
LILBEE_CHAT_MODEL |
qwen3:8b |
Ollama chat model |
LILBEE_EMBEDDING_MODEL |
nomic-embed-text |
Embedding model |
LILBEE_EMBEDDING_DIM |
768 |
Embedding dimensions |
LILBEE_CHUNK_SIZE |
512 |
Tokens per chunk |
LILBEE_CHUNK_OVERLAP |
100 |
Overlap tokens between chunks |
LILBEE_MAX_EMBED_CHARS |
2000 |
Max characters per chunk for embedding |
LILBEE_TOP_K |
10 |
Number of retrieval results |
LILBEE_SYSTEM_PROMPT |
(built-in) | Custom system prompt for RAG answers |
CLI also accepts --model / -m, --data-dir / -d, and --version / -V flags.
How it works
Documents are hashed and synced automatically — new files get ingested, modified files re-ingested, deleted files removed. Kreuzberg handles extraction and chunking across all document formats (PDF, Office, images via OCR, etc.), while tree-sitter provides AST-aware chunking for code. Chunks are embedded via Ollama and stored in LanceDB. Ollama uses llama.cpp with native Metal support, which is significantly faster than in-process alternatives like ONNX Runtime — CoreML can't accelerate nomic-embed-text's rotary embeddings, making CPU the only ONNX path on macOS (~170ms/chunk vs near-instant with Ollama's GPU inference). Queries embed the question, find the most relevant chunks by vector similarity, and pass them as context to the LLM.
Data location
| Platform | Path |
|---|---|
| macOS | ~/Library/Application Support/lilbee/ |
| Linux | ~/.local/share/lilbee/ |
| Windows | %LOCALAPPDATA%/lilbee/ |
Override with LILBEE_DATA=/path or --data-dir.
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for lilbee 0.3.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| lilbee-0.3.10.tar.gz | 2.9 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| lilbee-0.3.10-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.9 MB
Release files / lilbee-0.3.10.tar.gz
| Download URL | lilbee-0.3.10.tar.gz |
|---|---|
| Size | 2.9 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d899aa911a209ccb75019a3031136ec1655cfd85460821a2a37ccbcc8c3dac24
|
|
BLAKE2b-256 checksum How to use checksums |
e872d246020a1abf2d21f50bac14da21d60d117e08015ff63b16cab51aff6f73
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 10, 2026.
Transparency logRelease files / lilbee-0.3.10-py3-none-any.whl
| Download URL | lilbee-0.3.10-py3-none-any.whl |
|---|---|
| Size | 36.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f1e746944d4853d0e3b1ac1f24a08c3fe6040c9f8e21bab3ec6df717f22754f5
|
|
BLAKE2b-256 checksum How to use checksums |
032dcecadf9350fe933b9426807cb8f65f15df874efa60d861758be5f6097a5b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 10, 2026.
Transparency log
