PyPI page
Home page
Author:
None
Summary:
The whole local AI stack in one executable: run and manage local AI models across every GPU you have, and search your files, code, and the web pages you crawl, with answers that cite the source. Per-project libraries, semantic and hybrid search, vision OCR, an auto-built wiki, CLI, TUI, MCP server, REST API, and Python library. No model server, no database server, no containers. Works with your own Ollama or LM Studio models too.
Latest version:
0.6.90b420.dev727
Required dependencies:
cachetools
|
diskcache
|
filelock
|
gguf
|
httpx
|
huggingface-hub
|
jinja2
|
kreuzberg
|
lancedb
|
lilbee-engine
|
litestar
|
mcp
|
numpy
|
nvidia-cublas-cu12
|
nvidia-cuda-nvrtc-cu12
|
nvidia-cuda-runtime-cu12
|
pillow
|
psutil
|
pydantic-settings
|
textual
|
tiktoken
|
tomli-w
|
tree-sitter-language-pack
|
typer
|
typing-extensions
|
uvicorn
Optional dependencies:
crawl4ai
|
graspologic-native
|
litellm
|
spacy
Downloads last day:
53
Downloads last week:
1,411
Downloads last month:
5,049