yaroslavyaroslav/OpenAI-sublime-text

First class Sublime Text AI assistant with gpt-5, Opus 4.6, Gemini 3 and ollama support!

OpenAI Sublime Text Plugin – Quick Overview

What it is – A Sublime Text extension that lets you talk to large‑language‑model APIs (OpenAI, Anthropic, Google Gemini, or any OpenAI‑compatible server such as llama.cpp, ollama, llmman) directly from the editor. It works at the cursor level, letting you send selected code, whole files, build‑output or LSP diagnostics as context and receive answers inline or in a chat panel.

Key capabilities

  • Chat mode with any model you configure (including the placeholder “gpt‑5”).
  • Multiple back‑ends – you point the plugin at a remote API URL and token; it supports the standard OpenAI chat endpoint, Anthropic, Gemini, and generic OpenAI‑compatible services.
  • Context handling – you can add individual files (or the whole project) to the request, include recent build or LSP output, and even send images (png/jpg) via a clipboard‑or‑path command.
  • Inline “Phantom” UI – model replies appear as non‑intrusive overlays inside the editor, with quick actions to copy, append, replace, open in a new tab, or add to history.
  • Chat history per project – separate histories and assistant settings can be stored per‑project via a cache_prefix.
  • Streaming & status bar – server‑sent‑events streaming is supported; the status bar shows model name, token counts, etc.
  • Proxy support and optional markdown rendering with syntax highlighting.

How you use it

  1. Install via Package Control or clone the repo into your Sublime Packages folder.
  2. Add your API key (or token) in Preferences → Package Settings → OpenAI completion.
  3. Open the Command Palette and run OpenAI: Chat Model Select to pick a model/assistant and output mode (Phantom or Chat view).
  4. Type a prompt (optionally select code) and hit Enter. The response appears inline or in a panel, and you can interact with it via the phantom buttons or key bindings you define.

Configuration highlights

  • openAI.sublime-settings holds the API URL, token, model name, temperature, proxy, and UI toggles.
  • You can toggle files for context via the command palette, tab context menu, or sidebar menu.
  • Build/LSP output inclusion is controlled by build_output_limit.
  • Advertising can be disabled per‑assistant with `

Related

  • Project
    sublimelsp/LSP-copilot

    A Sublime Text plugin that integrates GitHub Copilot via a language server to provide AI-powered code completions and chat.

  • Project
    ashbuilds/payload-ai

    A Payload CMS plugin that brings LLM‑driven content generation, proofreading, translation, and voice/image creation into the CMS. Supports multiple AI providers, per‑field prompts, access control, and custom model integration. Install via `pnpm add @ai-stack/payloadcms`, configure in `payload.config.ts`, and add the Lexical editor feature to fields. Advanced options include multi‑tenant secret handling, custom media upload, and a resolver for reference images.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.

  • Project
    allenhutchison/obsidian-gemini

    Gemini Scribe is an Obsidian plugin that connects to Gemini, Ollama, OpenAI, or Anthropic models, turning the note‑taking app into an AI‑driven assistant. It offers an agent with tool‑calling (file search, create/edit notes, deep research), per‑feature provider routing, semantic vault search, smart summarisation, IDE‑style completions, scheduled tasks, lifecycle hooks, and project‑scoped skills—all stored locally as markdown files.

  • Project
    openai/openai-node

    Official OpenAI Node/TS SDK for calling OpenAI’s REST API – supports text, vision, streaming, realtime, Azure/Bedrock adapters, workload‑identity auth, and webhook verification.