The evolution of rules from constraints to amplifiers The concept of "rules" in software development has undergone a fundamental transformation. What once meant rigid linting configurations now represents a sophisticated approach to customizing AI coding assistants. With 82% of developers using AI assistants daily or weekly, the ability

When I was hit with the sudden urge to build a small CLI in Go, I of course went directly to the Agent mode input box and began typing out what I wanted. At this point, I’d built enough trust in Continue to know that it could generate me

When working with AI agents to write code, the difference between good and great results often comes down to the quality of your rules. In my recent video, I demonstrated how rules serve as guardrails that amplify your intentions and ensure the agent codes like a senior developer would. My

AI amplifies intent AI is an intention amplifier. If your intention is to be more productive, AI will amplify your productivity. If your intention is to learn, AI will amplify your learning. If you intention is to save mental energy, AI will amplify your mental energy savings. Our intention at

I generally pass by spicy takes on the internet. Occasionally something provocative starts my brain going. I regret nothing yet! fly.io/blog/youre-a... [image or embed] — Thomas Ptacek (@sockpuppet.org) June 2, 2025 at 2:07 PM Lots of positive reactions and chiming in from commenters who say they

Today we have a guest post from Tejas at Morph. Stop Fighting with AI Code Edits You ask Claude to refactor your authentication logic. It responds with 80 lines of beautiful code. Now what? Copy the whole thing? Manually find where each piece goes? Watch your indentation break? This is

Today, Mistral released Devstral, an Apache-2.0, 24B-parameter model trained for tool calling in real-world software development environments. It reached #1 on SWE-bench for open-source models, but more importantly in our real-world testing it has proven to be capable of navigating and autonomously editing codebases, while running entirely on a

I'm excited to announce that I'm joining Continue as CEO! After months of increasingly deep involvement with the team, first as a user, then as an advisor, it just started to make sense. And honestly, it feels like the perfect next chapter in my journey. How

At Continue, we've built our platform on a fundamental belief: developers need the freedom to choose the right AI tools for their specific workflows. This philosophy is why we've designed an open, modular architecture that can quickly integrate new innovations as they emerge in the AI-native

One of the core values of Continue has always been choice - the freedom to select the right model for the job. As I type this, I'm waiting for a load of laundry to dry so I can pack for Google Next 2025 so it seemed a fitting

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

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

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

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

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

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

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,

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

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