01 / Interface
Stay in the interface you already use.
Codex stays your workspace. Native GPT, managed providers and your own local models appear in the same model picker — switch models, not apps.
Model Dock For Codex
Work in one place.
Get things done everywhere.
Keep working in Codex. ModelDock brings the models you choose—native GPT, managed providers, and local engines—together with the tools a task may need, without manually moving prompts, files, or results between apps.
LOCAL BRIDGE Responses streaming, tool loops and long-session work remain part of the same task.
The ModelDock stack
Interface, dock, machine —
one system.
ModelDock is the routing layer in the middle — and the idea that where you work, what you route to, and what runs it belong together.
02 / Dock
One dock routes every task.
A local bridge sends each request to the right model and gives it the tools the task needs: vision, search, memory, speech, image generation. Streaming, tool loops and long sessions stay intact, and every route, token and latency stays visible.
03 / Machine
Know the machine underneath.
Local AI runs on real hardware. ModelDock detects Ollama, llama.cpp, vLLM and Strata, and measures your machine against open benchmarks — prefill, decode, power, cost per million tokens — so you can tune, compare or buy with evidence.
See the rankings →