Ollama: VS Code Integration Takes Center Stage
Today we're diving into a major milestone for Ollama - native VS Code integration! Eva H and the team delivered a comprehensive `ollama launch vscode` command that seamlessly connects your local models with GitHub Copilot Chat. Plus, we've got important memory leak fixes for MLX users and some thoughtful UX improvements across the board.
Duration: PT3M53S
Episode overview
This episode is a short developer briefing from Ollama.
It explains recent repository work in plain language.
- Show: Ollama
- Published: 2026-03-26T10:11:22Z
- Audio duration: PT3M53S
Transcript excerpt
This excerpt keeps the crawler page concise. Listen to the episode or use the RSS feed for the full update.
Hey there, amazing developers! Welcome back to another episode of the Ollama podcast. I'm your host, and wow - do we have some exciting updates to share with you today! Grab your favorite beverage because we're about to dive into what feels like a real game-changer for how we interact with Ollama.
So picture this - you're coding away in VS Code, and you want to chat with one of your local Ollama models. Up until now, that meant switching contexts, maybe opening a terminal, or using a separate interface. Well, not anymore! Eva H just merged an absolutely fantastic pull request that adds native VS Code…
This isn't just a basic integration either - we're talking about the full experience here. When you run this command, Ollama registers itself as what's called a "bring your own key" vendor, which means GitHub Copilot Chat can discover both your local models and cloud models automatically. Even cooler? The model…
The implementation is pretty impressive too - over 1,100 lines of new code across seven files, including comprehensive tests. Eva worked alongside Parth Sareen to make this happen, and honestly, the attention to detail shows. They've even handled edge cases like pulling cloud…
No…
Nearby episodes from Ollama
- Legacy Compatibility and Developer Experience Wins
- Smoothing the Launch Experience
- Fixing the Inconsistencies That Matter
- Smart Caching and Better User Experience
- Precision Revolution - New Float Formats and Testing Powerhouse
- MLX Performance Breakthrough and Smarter Caching
- Nvidia Partnership Takes Center Stage
- Bug Squashing Bonanza