ModelDock¶

Why ModelDock?¶

Local LLMs are powerful, but managing them is painful. ModelDock eliminates the friction of discovering, downloading, organizing, and loading models — so you can focus on building.

import modeldock as md
client = md.load("llama3")

# Missing? Downloads automatically.
# Installed? Returns instantly.
client = md.load("llama3")

md.search("coding")
md.recommend(task="vision")
md.info("qwen3")

md.install_category("coding")

md.cache.status()
md.cache.clean()

client = md.load("llama3", backend="ollama")

Architecture at a Glance¶

ModelDock follows Clean Architecture with SOLID principles. Dependencies point inward — the domain and ports layers are pure, concrete runtimes are adapters.

Interface:   modeldock/__init__.py (SDK)  +  modeldock/cli (Typer)
Application: modeldock/core/   (services, LifecycleOrchestrator, ModelManager)
Domain:      modeldock/domain/ (pure entities, no I/O)
Ports:       modeldock/ports/  (typing.Protocol interfaces)
Adapters:    modeldock/adapters/ (runtimes, registry, downloaders, cache, progress)
Common:      modeldock/common/ (config, logging, platform, http, errors)

Quick Example¶

import modeldock as md

# Auto-install if missing, then use
client = md.load("llama3")

# Run a chat
response = client.chat(
    model="llama3",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response)

# Load a model (auto-installs if missing)
modeldock load llama3

# Browse the catalog
modeldock list

# Search by capability
modeldock search coding

# Install specific models
modeldock install llama3 qwen3 deepseek-r1

Supported Runtimes¶

Install¶

pip install modeldock
# with the Ollama backend helper (optional):
pip install modeldock[ollama]

Requires Python 3.9+ and a local Ollama install for the first runtime.