Continue Updates 🚀 We launched Continue 1.0, which included a press release and TechCrunch coverage ⏩ The Continue Hub makes it easy to create, share, and use custom AI code assistants Code x AI Updates 🌀 The End of Programming as We Know It makes the case that AI-enhanced development is not

Continue 1.0 Launch 🎉 Instead of our usual monthly newsletter, here is a recap of our launch this past week AP News release: Continue Launches 1.0 with Open-Source IDE Extensions and a Hub that Empowers Developers to Build and Share Custom AI Code Assistants TechCrunch coverage by Paul Sawers:

Continue Updates 🔒 Stacklok introduced CodeGate—local, open source privacy controls that encrypt secrets before they find their way into your prompts and alerts you when dangerous dependencies are suggested—and created a tutorial on how to use it with Continue ✏️ There was a drastic improvement to mid-line autocomplete suggestions thanks

Continue Updates 📝 Introducing multi-file Edit! Use cmd+I or cmd+shift+I to select multiple files at a time and iterate on them all at once, from the same sidebar as Chat ✨ Chat got a makeover: links to code symbols, a “sticky” chat input box, autodetected documentation suggestions, a much

Continue Updates 🌐 The new “@web” context provider lets you reference content from around the internet to answer questions 🖥️ Full screen mode got a full redesign! You can now open Continue in its own entire window, with the history bar displayed to the side like in ChatGPT ᝰ We’ve shipped

Continue Updates 🍊 Garry Tan (President & CEO of Y Combinator) showed public support for the amplified.dev movement on Twitter and LinkedIn ▶️ Continue’s new instant apply button often makes it possible to bring suggested code from the chat sidebar to your files without any wait! 🌳 Root path context: The

Continue Updates 🎉 We recapped our first year and looked forward to our next year in our Happy 1st birthday, Continue! blog post 👴 We enabled support for prompt caching with Anthropic and DeepSeek, which we detailed in Why we’re excited about prompt caching for engineering teams on our blog 🪨 Tobias

Continue Updates 🦙 Llama 3.1 (8b, 70b, and 405b) is finally here! It can be used in Continue with Groq, Ollama, LM Studio, Together AI, Fireworks, Replicate, and other providers 📕 Improved @docs management and indexing make this core feature more reliable 🧠 Upgrades to @codebase retrieval and local indexing lead to

Continue Updates 🐋 Continue now supports Claude 3.5 Sonnet (our new #1 commercial LLM for coding) and DeepSeek Coder v2 (our new #1 open weights LLM for coding) 🚦It's now possible to easily switch between different models for autocomplete, and you should notice a drastic reduction in noisy

Continue Updates 🐝 We partnered with Mistral AI to launch their latest model, Codestral, in May! Follow this walkthrough to begin using it and read more about how to try it out with Ollama here 🎧 We heard a lot of requests for the currently open file to be used as context,

Continue Updates 🌠 Our open-source VS Code and JetBrains extensions crossed 10K stars on GitHub 🦙 Llama 3 8B and 70B, which match the capabilities of models of significantly larger size, and Gemini 1.5 Pro with a 1,000,000 token context length are available in Continue 🤠 Continue's codebase

Continue Updates 🔴 Significant improvements to cmd/ctrl+I in VS Code: better prompt for all models, easier to undo changes, accept/reject one-by-one, cleaner diffs, and more 🟡 Personal usage analytics! Continue now locally tracks the tokens you generate each day, so you can view the breakdown per day and per

Continue Updates ❤️ Our open-source, local tab autocomplete made it into beta in February 🌊 Lots of new models to try like Gemma 7B, Mistral Large, StarCoder2, and more 🌲 @rootedbox and @NinjaPerson24119 built Postgres / database context providers ✨ @theBenForce contributed another awesome context provider for Jira issues 🚒 The JetBrains extension shares most of

Continue Updates 🐋 New context providers: @directory uses RAG to find relevant files, @problems shows the LLM any lint warnings in the open file, and @docs crawls and indexes docs pages 🚌 Local codebase embeddings are back with support for multiple providers of embeddings, including transformers.js, OpenAI, Ollama, and Together embeddings

Continue Updates 🐍 No more Continue Python server, so the extension now always immediately works 🚒 cmd/ctrl+shift+l enables you to make quick edits without opening the sidebar in VS Code (i.e. edits are streamed in line by line without a side-by-side diff) 〽️ Inline context providers that allows files,

Continue Updates 🐥 The model and provider setup experience has been simplified with config.json 📗 Use /so to automatically include Stack Overflow search results in the LLM’s context 🦙 Run local, open-source models easily using llamafile as your provider with Continue ⭐ The Continue repository crossed 5,000 stars on GitHub this

Continue Updates 🧇 The JetBrains extension was officially released to the store—it is still going through alpha testing, but it has already reached full feature parity with VS Code 🔍 Codebase retrieval is now available in the VS Code pre-release, which allows you to cmd+enter to “talk to your codebase”

Continue Updates 🐳 Codebase embeddings let you ask questions about your workspace (experimental) 💫 We started alpha testing the JetBrains extension with early users this past week 🚒 Use /cmd to generate a command and have it automatically placed in your terminal 🐍 We integrated w/ the Language Server Protocol in Python (more languages

What's new? 🦙 Code Llama from Meta AI dropped on August 24th! Many of you began using it through Continue via Ollama, Replicate, and Together, and posts about us ended up on the front page of Hacker News that day as well as the next week. ✏️ There are many

How can you help? ⬆️ Press the "Notify me" button here and then upvote our Product Hunt launch on Tuesday 💬 Join our Discord and chat with us about your experience using Continue 💪 Open a GitHub Issue with a bug you found or a feature request you have What'