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

GitHub Copilot CLI now discovers local models from Ollama

clearly official source

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

Starting with version 1.0.94-0, GitHub Copilot CLI lets users discover supported models from a running local Ollama service using the /model command. It lists them alongside models already configured and cloud models available through GitHub Copilot. Discovery does not automatically add a model: the user checks the provider and endpoint and confirms adding it, with the option to switch to it immediately as well. The model can be used in the current session without restarting the tool.

Both Ollama and the model must be installed beforehand; this process does not install the environment or download models. The model must support tool calling, meaning the ability to invoke tools, and streaming, meaning incremental delivery of output. Any errors connecting to the provider appear directly in the model selection list with an explanation.

Selecting a local model does not enable offline mode or disable telemetry from GitHub. Offline mode is configured separately using COPILOT_OFFLINE=true. According to GitHub, a remote provider may receive prompts and code context over the network even in this mode.

What changed

Why it matters

Local model availability and restrictions on network communication are two separate decisions. The new feature lets users work with an already installed model during an ongoing session, but selecting it alone does not guarantee operation without network data transmission.

Two audiences, two different impacts

What this means

01

For individuals

A developer with Ollama running can select a supported local model directly in the current GitHub Copilot CLI session and continue without restarting.

What to do When adding a model via /model, check the provider and endpoint before confirming.
More practical updates →
02

For a business

When working with company code, selecting a local model cannot be considered a guarantee of restricted data transmission: selecting a local model does not disable telemetry, and a remote provider may receive prompts and code context even in offline mode.

Risks and compliance
What to decide Before using GitHub Copilot CLI with company code, check the provider, offline mode and telemetry configuration against the tool documentation.
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.

2
GitHub Copilot Changelog primary source · first detected Discover local models in GitHub Copilot CLI GitHub Copilot Changelog primary source GitHub Copilot weekly releases — October 5 An overview of multiple AI topics; AI Radar covers only this event.