GitHub Copilot CLI Adds Local Model Discovery Support
GitHub has released an update for its command-line interface tool, simplifying the way developers discover and integrate local models into their existing workflows.
Radwan AbdulhadiEditor and technology writer
Discovering Local Models in the CLI
GitHub has announced an update to the GitHub Copilot CLI that makes choosing a local model easier without requiring developers to leave their existing workflow. According to the [GitHub Changelog](https://github.blog/changelog/2026-10-07-discover-local-models-in-github-copilot-cli/), starting in CLI version 1.0.94-0, users can utilize the /model command to discover supported models from a running local Ollama instance.
Alongside discovered local options, the interface displays configured models and cloud models provided by GitHub Copilot. Discovery does not automatically add models to the system. Instead, developers must choose a discovered model, review its provider and endpoint details, and then confirm whether to add and use it for the current session or add it without switching.
Requirements and Session Management
When using the new discovery feature, developers can apply the model in their current session without needing to restart the CLI. However, the system relies on pre-existing installations; Ollama and the target model must already be installed on the machine, as this workflow does not handle runtime installations or model downloads.
Additionally, models must support both tool calling and streaming to function properly within the experience. If any provider connection failures occur, they appear directly in the picker with a clear explanation, helping developers quickly identify what needs attention.
Provider Experience and Settings
This latest CLI update builds upon the same conceptual foundation as the GitHub Copilot app’s provider experience, which centers on letting developers choose the model that best fits their work. Detailed instructions on setting up your own model provider in the GitHub Copilot app can be found in the documentation.
Users of the app can add a supported provider by navigating to Settings and selecting Model providers.
Offline Mode and Telemetry Considerations
GitHub notes that choosing a local model does not automatically turn on offline mode or disable GitHub telemetry. Within the command-line interface, offline mode remains an explicit choice that must be set using COPILOT_OFFLINE=true.
Even when operating in offline mode, a remote provider can still receive prompts and code context over the network. Developers should review the official CLI provider and offline-mode documentation for complete configuration details and limitations.
Future Developments and Intelligent Routing
Alongside the local model discovery feature in the CLI, announcements regarding intelligent routing with local models have also been shared. More information can be found through the announcement on the Microsoft Command Line blog, with further updates regarding availability expected in the future.
Sources
- GitHub ChangelogDiscover local models in GitHub Copilot CLI
Continue chronologically
Related entity coverage
Related stories
GitHub Copilot in VS Code September 2026 Releases
Explore the GitHub Copilot updates for VS Code spanning v1.136 through v1.140, focusing on streamlined agent-driven development and workspace automation.
GitHub Copilot App Introduces Local Sandboxing in Preview
GitHub has announced local sandboxing for the GitHub Copilot app in public preview, helping to reduce the potential impact of unintended commands.
GitHub Copilot Expands Code Review Configurations
GitHub Copilot code review introduces general availability for personal configurations across more plans and adds enterprise-level default settings.
GitHub Adds Feature Engagement to Copilot Dashboard
GitHub’s Copilot impact dashboard now shows regular feature use, while enterprise and organization reports add 28-day engagement data.
