Skip to content
AI Radar by Wagner Solution
CS
Menu
worth noting Local AI

GitHub Copilot CLI now discovers and adds local models from Ollama

clearly official source

Starting with version 1.0.94-0, GitHub Copilot CLI discovers supported local models from Ollama through the /model command. Once confirmed, the model can be used without restarting. Selecting a local model alone does not enable offline mode or disable telemetry.

Starting with version 1.0.94-0, GitHub has enabled GitHub Copilot CLI to discover supported models from a running local Ollama service using the /model command. Results appear alongside configured and cloud models. Before adding a model, the user checks the provider and endpoint and confirms whether to use the model immediately in the current session or simply add it. No CLI restart is needed.

Both Ollama and the model must already be installed; the new workflow does not install the environment or download models. The model must support tool calling and streaming. Any errors connecting to the provider appear directly in the model selector, along with an explanation.

According to GitHub, selecting a local model does not enable offline mode or disable GitHub telemetry. Offline mode is explicitly enabled in the CLI using COPILOT_OFFLINE=true. However, even this mode does not prevent a remote provider from receiving prompts and code context over the network.

What changed

Why it matters

Developers who already have local models set up can select and add them directly in the CLI and continue their ongoing session. When working with sensitive code, it is essential to understand that neither a local model nor offline mode alone guarantees that all communication stays on the device.

Two audiences, two different impacts

What this means

01

For individuals

While working in GitHub Copilot CLI, you can switch to a supported local model from a running Ollama service without restarting or leaving the current session.

What to do If you have Ollama and a supported model installed, run /model in version 1.0.94-0 or later and check the provider and endpoint before confirming that you want to add the model.
More practical updates →
02

For a business

When deploying it in a company, you need to distinguish between model location, GitHub telemetry and the provider’s network communication. Choosing a local model alone does not address the rules for sharing company code.

Risks and compliance
What to decide Before using it with company code, check the provider, endpoint and settings against the CLI documentation on providers and offline mode.
More business impacts →
GitHub Copilot CLI Ollama streaming tool calling

Check the original

Event sources

clearly official source · 1 publisher, 0 independent. We count feeds from the same owner only once.

1
GitHub Copilot Changelog primary source · first detected Discover local models in GitHub Copilot CLI