Continue
@continue.dev
Ship faster with Continuous AI
continue.dev
continue.dev
Most of the time, maintaining your codebase and fixing what's broken is the difficult part.
That's one of the reasons why we built Next Edit. From callback-to-async conversions to comprehensive bug fixes, it understands real developer editing patterns.
🔗 blog.continue.dev/next-edit-po...
That's one of the reasons why we built Next Edit. From callback-to-async conversions to comprehensive bug fixes, it understands real developer editing patterns.
🔗 blog.continue.dev/next-edit-po...
August 20, 2025 at 4:08 PM
Most of the time, maintaining your codebase and fixing what's broken is the difficult part.
That's one of the reasons why we built Next Edit. From callback-to-async conversions to comprehensive bug fixes, it understands real developer editing patterns.
🔗 blog.continue.dev/next-edit-po...
That's one of the reasons why we built Next Edit. From callback-to-async conversions to comprehensive bug fixes, it understands real developer editing patterns.
🔗 blog.continue.dev/next-edit-po...
Code editing just got a lot faster.⚡Introducing Next Edit⚡
Next Edit delivers real-time, multi-line suggestions at up to 1100 tokens/sec, powered by @inceptionlabs.bsky.social Mercury Coder, the world’s first commercial-scale diffusion LLM for code.
Next Edit delivers real-time, multi-line suggestions at up to 1100 tokens/sec, powered by @inceptionlabs.bsky.social Mercury Coder, the world’s first commercial-scale diffusion LLM for code.
August 20, 2025 at 4:00 PM
Code editing just got a lot faster.⚡Introducing Next Edit⚡
Next Edit delivers real-time, multi-line suggestions at up to 1100 tokens/sec, powered by @inceptionlabs.bsky.social Mercury Coder, the world’s first commercial-scale diffusion LLM for code.
Next Edit delivers real-time, multi-line suggestions at up to 1100 tokens/sec, powered by @inceptionlabs.bsky.social Mercury Coder, the world’s first commercial-scale diffusion LLM for code.
No one wants to wait for sequential tool calls if they don't have to. That's why at Continue, we have parallel tool calling.
August 19, 2025 at 7:01 PM
No one wants to wait for sequential tool calls if they don't have to. That's why at Continue, we have parallel tool calling.
Another great Continue feature: Parallel Tool Calling.
Instead of read file A → wait → read file B → wait → read file C, it requests them all at once.
📝 Learn more in our blog: blog.continue.dev/parallel-too...
Instead of read file A → wait → read file B → wait → read file C, it requests them all at once.
📝 Learn more in our blog: blog.continue.dev/parallel-too...
August 19, 2025 at 4:05 PM
Another great Continue feature: Parallel Tool Calling.
Instead of read file A → wait → read file B → wait → read file C, it requests them all at once.
📝 Learn more in our blog: blog.continue.dev/parallel-too...
Instead of read file A → wait → read file B → wait → read file C, it requests them all at once.
📝 Learn more in our blog: blog.continue.dev/parallel-too...
Want to dig deeper into Plan Mode? We’ve pulled together resources to help you see how it works and why it matters 🧵👇
August 18, 2025 at 9:14 PM
Want to dig deeper into Plan Mode? We’ve pulled together resources to help you see how it works and why it matters 🧵👇
Continuous AI is a practical way to transform how teams write, review, and ship code.
We’re sharing our definition, the Continuous AI Maturity Model, and the metric that matters most. Read now: continue.ghost.io/ghost/#/edit...
We’re sharing our definition, the Continuous AI Maturity Model, and the metric that matters most. Read now: continue.ghost.io/ghost/#/edit...
August 13, 2025 at 8:19 PM
Continuous AI is a practical way to transform how teams write, review, and ship code.
We’re sharing our definition, the Continuous AI Maturity Model, and the metric that matters most. Read now: continue.ghost.io/ghost/#/edit...
We’re sharing our definition, the Continuous AI Maturity Model, and the metric that matters most. Read now: continue.ghost.io/ghost/#/edit...
Introducing Plan Mode! Read more about it in the July Continue Newsletter
July 17, 2025 at 5:14 PM
Introducing Plan Mode! Read more about it in the July Continue Newsletter
Leverage rules as a context provider now in Continue 📜
June 14, 2025 at 12:53 AM
Leverage rules as a context provider now in Continue 📜
"They don't want the thing they love, that they were present as kids at the beginning of, to be automated, replaced by human shepherding of natural language and remote agent workflows. I believe folks still yearn to type curly braces"
- @chadmetcalf.com from "Am I Nuts or Just Old?"
- @chadmetcalf.com from "Am I Nuts or Just Old?"
June 5, 2025 at 1:22 PM
"They don't want the thing they love, that they were present as kids at the beginning of, to be automated, replaced by human shepherding of natural language and remote agent workflows. I believe folks still yearn to type curly braces"
- @chadmetcalf.com from "Am I Nuts or Just Old?"
- @chadmetcalf.com from "Am I Nuts or Just Old?"
“Developers will be the ones who drive how many languages we have. Their actions and their stewardship of their niche programming languages will determine whether we have more or less”
- @ty.energy in 'The programming languages facing an AI-driven existential crisis' by @karimcmack.bsky.social
- @ty.energy in 'The programming languages facing an AI-driven existential crisis' by @karimcmack.bsky.social
June 3, 2025 at 11:51 AM
“Developers will be the ones who drive how many languages we have. Their actions and their stewardship of their niche programming languages will determine whether we have more or less”
- @ty.energy in 'The programming languages facing an AI-driven existential crisis' by @karimcmack.bsky.social
- @ty.energy in 'The programming languages facing an AI-driven existential crisis' by @karimcmack.bsky.social
💻 Agent mode just went local! Today, Mistral AI released Devstral, an Apache-2.0, 24B-parameter model trained for tool calling in real-world software development environments
To try it out, just add `ollama/devstral` in Continue. See below for a quickstart with Ollama 👇
To try it out, just add `ollama/devstral` in Continue. See below for a quickstart with Ollama 👇
May 21, 2025 at 4:25 PM
💻 Agent mode just went local! Today, Mistral AI released Devstral, an Apache-2.0, 24B-parameter model trained for tool calling in real-world software development environments
To try it out, just add `ollama/devstral` in Continue. See below for a quickstart with Ollama 👇
To try it out, just add `ollama/devstral` in Continue. See below for a quickstart with Ollama 👇
⚡️ Agent mode got a bit faster this week
Even in large, multiple-hundred-line files, Continue can now make small edits in seconds
Even in large, multiple-hundred-line files, Continue can now make small edits in seconds
May 9, 2025 at 6:29 PM
⚡️ Agent mode got a bit faster this week
Even in large, multiple-hundred-line files, Continue can now make small edits in seconds
Even in large, multiple-hundred-line files, Continue can now make small edits in seconds
April 14, 2025 at 9:23 PM
@chadmetcalf.com wrote about how he has switched to using Google Gemini 2.5 Pro for debugging because its context window is 5x larger. He's at Google Cloud Next 2025 this week. Let him know if you around!
April 8, 2025 at 4:40 PM
@chadmetcalf.com wrote about how he has switched to using Google Gemini 2.5 Pro for debugging because its context window is 5x larger. He's at Google Cloud Next 2025 this week. Let him know if you around!
The future is custom assistants that understand your specific development context. For DevOps, it means understanding infrastructure-as-code formats, cloud provider requirements, and organization-specific practices. This is where Stakpak comes in 🧱
April 1, 2025 at 5:23 PM
The future is custom assistants that understand your specific development context. For DevOps, it means understanding infrastructure-as-code formats, cloud provider requirements, and organization-specific practices. This is where Stakpak comes in 🧱
@bizza.pizza shared about how his Go programming journey was accelerated by a customized coding assistant that helps him learn Go idioms and best practices
dev.to/bdougieyo/th...
dev.to/bdougieyo/th...
March 27, 2025 at 4:50 PM
@bizza.pizza shared about how his Go programming journey was accelerated by a customized coding assistant that helps him learn Go idioms and best practices
dev.to/bdougieyo/th...
dev.to/bdougieyo/th...
Continue 1.0 is live on Product Hunt! Celebrate with us: www.producthunt.com/posts/contin... 🎉
February 27, 2025 at 4:07 PM
Continue 1.0 is live on Product Hunt! Celebrate with us: www.producthunt.com/posts/contin... 🎉
Continue 1.0 is here! Combining our open-source IDE extensions with hub.continue.dev makes it frictionless to use custom AI code assistants. Discover the models, rules, prompts, docs, and other building blocks you need to become an amplified developer ✨
February 26, 2025 at 4:37 PM
Continue 1.0 is here! Combining our open-source IDE extensions with hub.continue.dev makes it frictionless to use custom AI code assistants. Discover the models, rules, prompts, docs, and other building blocks you need to become an amplified developer ✨
💭 If you're looking for an easy way to use DeepSeek's R1 in your IDE:
1. Download Continue
2. Run `ollama run deepseek-r1`
You'll have a completely local reasoning model in your IDE
1. Download Continue
2. Run `ollama run deepseek-r1`
You'll have a completely local reasoning model in your IDE
January 30, 2025 at 7:07 PM
💭 If you're looking for an easy way to use DeepSeek's R1 in your IDE:
1. Download Continue
2. Run `ollama run deepseek-r1`
You'll have a completely local reasoning model in your IDE
1. Download Continue
2. Run `ollama run deepseek-r1`
You'll have a completely local reasoning model in your IDE
Check it out: blog.continue.dev/codestral-25...
January 13, 2025 at 7:21 PM
Check it out: blog.continue.dev/codestral-25...
You can now use Continue with Codestral 25.01, a new SOTA coding model from Mistral AI, which entered at #1 on LMSYS!
January 13, 2025 at 7:21 PM
You can now use Continue with Codestral 25.01, a new SOTA coding model from Mistral AI, which entered at #1 on LMSYS!
📝 Continue can now edit multiple files automatically
- Update logic that spans multiple files
- Generate tests for new features
- Reference files as context without editing them
- Update logic that spans multiple files
- Generate tests for new features
- Reference files as context without editing them
December 18, 2024 at 7:11 PM
📝 Continue can now edit multiple files automatically
- Update logic that spans multiple files
- Generate tests for new features
- Reference files as context without editing them
- Update logic that spans multiple files
- Generate tests for new features
- Reference files as context without editing them
Continue has crossed 20,000 stars on GitHub! 🎅🌟
December 13, 2024 at 7:38 PM
Continue has crossed 20,000 stars on GitHub! 🎅🌟
Using docs as context is now easy! And if you are using Python or TypeScript, you'll automatically get suggestions based on your dependencies. We'd love contributions for more languages ☀️
December 12, 2024 at 7:20 PM
Using docs as context is now easy! And if you are using Python or TypeScript, you'll automatically get suggestions based on your dependencies. We'd love contributions for more languages ☀️
🎯 Ensure coding standards are followed with rules:
📁 Place a .continuerules file in your project’s root directory
✍️ Define project-specific system messages with ease
💡 Ideal for reinforcing coding standards and best practices (e.g. React guidelines)
📁 Place a .continuerules file in your project’s root directory
✍️ Define project-specific system messages with ease
💡 Ideal for reinforcing coding standards and best practices (e.g. React guidelines)
December 11, 2024 at 6:28 PM
🎯 Ensure coding standards are followed with rules:
📁 Place a .continuerules file in your project’s root directory
✍️ Define project-specific system messages with ease
💡 Ideal for reinforcing coding standards and best practices (e.g. React guidelines)
📁 Place a .continuerules file in your project’s root directory
✍️ Define project-specific system messages with ease
💡 Ideal for reinforcing coding standards and best practices (e.g. React guidelines)