GitHub Copilot for JetBrains adds persistent memory and Ollama support

The latest update of GitHub Copilot for JetBrains introduces persistent memory across chat sessions, support for Ollama as a local model provider and stricter controls for enterprise administrators.

Memory across conversations

Copilot memory lets the assistant retain and recall useful information across agent chat sessions, keeping context without repeating the same project details or preferences in every conversation. The feature is managed with the Copilot Memory toggle in the settings portal.

Local models with Ollama

The integration lets users enable Ollama as a BYOK provider (bring your own key) within JetBrains, with provider configuration and model selection across the IDE experience. Codex workflows were also expanded: sessions now appear in agent debug logs and support updated permission modes and customizations.

Other changes

The update improves account management, restores file and folder # references in Copilot, Claude and Codex chats, and simplifies Copilot CLI installation from the integrated terminal. It also resolves reliability issues across MCP servers, terminals, customizations and cloud agents.

The key figure

1. The number of local model integrations the tool adds with Ollama, joining already supported providers and bringing Copilot closer to teams that want to run models without sending code to the cloud.