У нас вы можете посмотреть бесплатно Onit V2 - Introducing Auto-Context! или скачать в максимальном доступном качестве, видео которое было загружено на ютуб. Для загрузки выберите вариант из формы ниже:
Если кнопки скачивания не
загрузились
НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием видео, пожалуйста напишите в поддержку по адресу внизу
страницы.
Спасибо за использование сервиса ClipSaver.ru
Today, we're announcing V2 of Onit! Download here 👉 www.getonit.ai Onit is ChatGPT Desktop, but with local mode and support for other model providers (Anthropic, GoogleAI, xAI, Deepseek, etc). It's also like Cursor Chat, but everywhere on your computer - not just in your IDE. Onit is macOS for now. The source code for Onit is online! You can download a pre-built version: www.getonit.ai Or build directly from the source-code : https://github.com/synth-inc/onit ==== V2 extends on the original functionality with: Auto-Context - if enabled, Onit can use Apple’s Accessibility API to automatically load context from your computer: Auto-Context from Highlights: If you highlight text on your computer and launch Onit, Onit will read the highlighted text and add it to your prompt as context. Auto-Context from Current Window: If you launch Onit with a new shortcut (default: Cmd+Shift+Zero), Onit will read the text from your current window and add it to your prompt as context. Note: Auto-Context should set up some privacy alarm bells! I discuss starting at 2:05 in the video. To re-iterate, any context loaded via Auto-Context is NOT uploaded unless you submit a chat. In remote mode, context is sent directly to the model providers, not passed through third-party intermediaries. In local mode, context is not uploaded at all. V2 also adds features not shown in the video: Deepseek By popular demand, we’ve added Deepseek as a custom model provider. Custom Local Endpoints Running Ollama on a separate GPU machine? Now, you can set a custom HOST and PORT for your Ollama endpoint. Local Mode Advanced Params By request, we’ve added some advanced parameters to local inference including: timeout, keep_alive, context_window, temperature, top_k, top_p. Custom Remote Providers Upload a custom URL and TOKEN for any remote provider that adheres to the OpenAI API schema. Works with OpenRouter, Groq, Hyperbolic, etc. Customized Window Size & Positioning Onit V1 had a default width and always positioned itself in the top right corner. V2 “remembers” the most recent width. So, if it’s too small, expand it, and it stays that way. You can also choose top-right, top-center, or top-left in settings. Custom Font Size Customize your font size in settings. Let me know what you think!