continue

https://github.com/continuedev/continue Apache licensed.

This has been covered here before[0]. And I remember the questionable approach to add some of its dependencies[1]. I like meilisearch and used it in one project, but downloading some binary at runtime isn't really trustworthy IMHO. [0]: https://news.ycombinator.com/item?id=36882146 [1]: https://github.com/continuedev/continue/blob/33a0436193aa65a...

There's an opensource IntelliJ plugin from https://github.com/continuedev/continue that allows you to do this. It supports a couple different providers and models, e.g. LocalAI with Code Llama.

Continue | Founding Engineer | ONSITE | Full-time | San Francisco | $130-$170K + 1-2% Equity At Continue, we are on a mission to make building software feel like making music. We are creating the open-source autopilot for software development—an IDE extension that brings the power of ChatGPT to VS Code and JetBrains (https://github.com/continuedev/continue). You are likely a good fit if you - have founded or want to found your own startup one day - have experience with frontend, backend, and ML technologies - are enthusiastic about AI/LLMs, open source, developer tools - get excited about supporting users and helping customers - want to work in-person in SF the majority of the time More info: https://www.ycombinator.com/companies/continue/jobs/smcxRnM-...

Continue | Founding Engineer | ONSITE | Full-Time | San Francisco | $130-$170K + 1-2% Equity At Continue, we are on a mission to make building software feel like making music. We are creating the open-source autopilot for software development—an IDE extension that brings the power of ChatGPT to VS Code and JetBrains (https://github.com/continuedev/continue). You are likely a good fit if you - have founded or want to found your own startup one day - have experience with frontend, backend, and ML technologies - are enthusiastic about AI/LLMs, open-source, developer tools - get excited about supporting users and helping customers - want to work in-person in SF the majority of the time More info: https://www.ycombinator.com/companies/continue/jobs/smcxRnM-...

Oof I'm not a fan of their method of disabling telemetry either: https://github.com/continuedev/continue/issues/567

Hi HN! Since launching Continue two months ago (https://news.ycombinator.com/item?id=36882146), we've received amazing feedback, added features, and greatly improved reliability. But one of the biggest things we heard was the desire for a JetBrains extension. My co-founder Ty and I are super excited to share that we've released an extension for PyCharm, Intellij, WebStorm, and most other JetBrains IDEs - ready for alpha users at https://plugins.jetbrains.com/plugin/22707-continue. Perhaps the most exciting part is that this effort was kickstarted and in great part developed by a community contributor! If you're curious what it took to make this happen, check out the PR here (https://github.com/continuedev/continue/pull/457). We hope to eventually support every IDE, so we made adding a new extension as easy as implementing a single class.

We've done work to set Continue up to be a JetBrains plugin—it's a matter of just a) figuring out the basics of putting a webview in a JetBrains plugin and b) implementing this class (https://github.com/continuedev/continue/blob/main/extension/...) that communicates with the server. So long story short, we're planning on this soon and welcome PRs. It's a medium-sized task.

Hi HN, Code Llama was released, but we noticed a ton of questions in the main thread about how/where to use it — not just from an API or the terminal, but in your own codebase as a drop-in replacement for Copilot Chat. Without this, developers don't get much utility from the model. This concern is also important because benchmarks like HumanEval don't perfectly reflect the quality of responses. There's likely to be a flurry of improvements to coding models in the coming months, and rather than relying on the benchmarks to evaluate them, the community will get better feedback from people actually using the models. This means real usage in real, everyday workflows. We've worked to make this possible with Continue (https://github.com/continuedev/continue) and want to hear what you find to be the real capabilities of Code Llama. Is it on-par

Nice! I've been trying out both models for coding (using Ollama + http://github.com/continuedev/continue - disclaimer, author of Continue), and I have to say, it feels like "alignment tax" is real. Uncensored seems to perform slightly better.

We were actually doing this a couple weeks ago, but due to limitations of VS Code, it was slightly buggy (issues mainly around knowing the terminal window size when setting up a pseudo-terminal). That work still exists here, and we hope to find a solution eventually: https://github.com/continuedev/continue/blob/main/extension/...

No longer: https://github.com/continuedev/continue/commit/8db5b39170229... Definitely not intending this type of behavior. We want to do everything to keep Continue completely private.

I'm not aware of any reason we would be connecting to windows.net. I would be surprised if VS Code did not already have access to Desktop / Documents / etc. but if this is the case, then Continue reads the currently open files as context for the LLM. It would be very useful to hear more about the details of these two cases so we can try to better reproduce and solve the problem. Would you be interested in opening a new issue? (https://github.com/continuedev/continue/issues/new) Continue will cache Python packages in ~/.continue/server/env after the first download, but there might be something else causing slower startup. Will look into this as well! Meilisearch is an open-source search library. We connect to meilisearch.com only in order to download the software, which then runs completely locally to power search in the dropdown as you ty

"Continue works with any LLM, including local models using ggml" Which of the local models have you seen the best results with? UPDATE: Found a note here https://github.com/continuedev/continue/blob/ce76e391775034c... that says "While these models don't yet perform as well, they are free, entirely private, and run offline." and points to the documentation here for how to run one, but doesn't really recommend a specific model: https://github.com/continuedev/ggml-server-example

Just deleted: https://github.com/continuedev/continue/commit/eba2f57a6462f... Neither were doing anything, we simply forgot to `npm uninstall` after (a while ago) playing around to decide which service to use. Thanks for pointing it out.