Continue Blog

Four server racks in a row, with perforated doors, revealing stacks of variedservers with multicolored cabling and LEDs.

Continue + Stakpak: Amplifying DevOps

We've just partnered with Stakpak to bring specialized DevOps capabilities to Continue, and I'm really excited about this one. Why? Because I used to do this for a living. The DevOps Reality: It's Still Complex A long time ago, in a galaxy far, far

Simplifying AI Development with Model Context Protocol, Docker, and Continue Hub

Simplifying AI Development with Model Context Protocol, Docker, and Continue Hub

A joint post from Continue and Docker exploring how to leverage containerized MCP blocks to enhance your AI native development experience Introduction As developers integrate AI into their workflows, they face several practical challenges: limited model context windows, insufficient tooling access, and difficulty connecting models to external data sources. The

Transforming Code Search with Voyage AI: Why Your Continue Assistant Needs Better Embedding Models and Rerankers

Transforming Code Search with Voyage AI: Why Your Continue Assistant Needs Better Embedding Models and Rerankers

As your codebase grows, finding the right information at the right time becomes increasingly difficult. Everyone who's spent hours hunting for a function they wrote months ago or searching for documentation on how to use a library understands this pain acutely. While Continue's default search capabilities

Creating Rule Blocks on Continue Hub: A Developer's Guide

With guest Dan Cleary from PromptHub As developers, we constantly seek ways to make our AI assistants work better for our specific needs. One of the most powerful yet underutilized features of Continue is the ability to create custom rule blocks that shape how your AI coding assistant behaves during

Continue + nCompass: Bringing Google Gemma 3 to Your Development Workflow

Continue + nCompass: Bringing Google Gemma 3 to Your Development Workflow

We're excited to announce a new partnership with nCompass, bringing Google's cutting-edge Gemma 3 family of models to the Continue Hub! This integration exemplifies what we believe is the future of AI native development: giving developers access to the best models through an open ecosystem of

Instant Apply with Relace

Instant Apply with Relace

With guest author Eitan Borgnia Frontier models like Claude 3.7 are becoming unbelievably strong coders, but they're also slow and expensive. They generate text at ~100-200 tokens/sec and can cost upwards of $15 per million output tokens. When you use frontier models to implement edits to

Continue Hub Assistant using Ollama locally and running Google's Gemma 3.

Using Ollama and Gemma 3 with Continue: A Developer's Guide

As developers, we want tools that respect our privacy, let us customize our experience, and integrate seamlessly into our workflows. Continue paired with Ollama offers exactly that—a way to run custom AI coding assistants locally. The benefits of this include 1. Data privacy: your code stays on your machine,

Continue 1.0

🥇Continue 1.0 takes us towards an open architecture for AI-enhanced developer tools, enabling us to customize together The next step towards a future where developers are amplified, not automated Large Language Models (LLMs) are powerful, general text manipulators. To learn to use them while programming, you need to be

Use Codestral 25.01 with Continue today

Use Codestral 25.01 with Continue today

When Mistral AI launched the original Codestral model in May 2024, it immediately became the best autocomplete model—a Large Language Model (LLM) trained for code infilling and capable of low latency responses. This is why it has been our top recommendation for developers since then. And now, six months

Use QwenCoder2.5 32B on the SambaNova Cloud and never wait for replies

Use QwenCoder2.5 32B on the SambaNova Cloud and never wait for replies

We are excited to partner with SambaNova Systems to launch QwenCoder2.5 32B on their cloud! In October, they published a blog post about how to use Continue with Llama 3.1 405B. Today, Continue developers can now experience the power of getting suggestions from QwenCoder2.5 32B on the

Model Context Protocol x Continue

Model Context Protocol x Continue

Last week, Anthropic introduced the Model Context Protocol (MCP), a new open protocol that "enables seamless integration between LLM applications and external data sources and tools". Also last week, Continue added support for MCP! Let’s explore why MCP is well-suited for Continue and how you can use

Instant Apply

“UX risk” Over the last year and a half of developing features that users didn’t like, finding out they didn’t like them, and then trying again, we’ve built a better idea of what will and won’t fly. Among the biggest predictors is what I call “UX

A custom autocomplete model in 30 minutes using Unsloth (Community post)

A custom autocomplete model in 30 minutes using Unsloth (Community post)

This is a guest post on the Continue Blog by Sophia Parafina, a developer advocate who has previously worked at Pulumi, Anaconda, and Docker. Continue is an open-source AI code assistant. It's a compound AI system that uses a set of models (chat, autocomplete, embeddings, etc) along with

Protecting the Continue community

Protecting the Continue community

Continue is the leading open-source AI code assistant, already having tens of thousands of users, nearly 200 contributors, and a vibrant, growing community. We envision an ecosystem of products that build with and around Continue, and that is part of why we released our project under an Apache 2.0

Root path context: The secret ingredient in Continue's autocomplete prompt

Root path context: The secret ingredient in Continue's autocomplete prompt

If you interpreted “root path” as the root directory of your computer, don’t worry! Continue wants nothing to do with this. What we’re going to share is our strategy for gathering (and caching) autocomplete context, which relies heavily on the root path: the path from a node in

Why we’re excited about prompt caching for engineering teams

Why we’re excited about prompt caching for engineering teams

Anthropic’s rollout of prompt caching, also known as context caching, follows similar offerings from providers like DeepSeek and Google and has been getting a lot of attention recently. At Continue, we're particularly excited about the potential impact on engineering teams, as prompt caching can significantly reduce costs

Happy 1st birthday, Continue!

Happy 1st birthday, Continue!

Looking back on the first year of Continue Just over a year ago, we launched Continue on Hacker News. Since then, the Continue community has taken shape and grown considerably: * 300k+ downloads across VS Code and JetBrains extensions * 14k+ stars on GitHub, 5k+ Discord members, and 140+ contributors * Lots of

A framework for evaluating AI code assistants

A framework for evaluating AI code assistants

Throughout hundreds of conversations with users, we’ve heard lots about what they need in a great AI code assistant. In this post we’ll share a set of criteria that are representative of those we find companies caring about the most, especially once they have the hindsight of running