GIDE

Questions from the bench

Can GIDE run fully offline?

Yes. The model, your code and your prompts stay on your machine. On the standard download you sign in once to turn on the AI; after that GIDE runs fully offline and only goes online when you ask it to, like a web search or to check for updates. The editor itself works with no sign-in. On Enterprise, air-gapped deployment uses offline license activation with no sign-in and no network needed, ever.

Is my code private with GIDE?

In local mode, your code never leaves your machine. If you connect a cloud model via BYOK, only the prompts you send go to that provider, using your own API key stored in your system keychain. GIDE never routes your code through its own servers.

What AI models does GIDE use?

GIDE is model-agnostic. Ornith 1.5 9B is the default local model; Qwen and Gemma are one command away, and you can point it at any GGUF file you like. Claude, GPT, Gemini and any OpenAI- or Anthropic-compatible endpoint work too, with your own key. You can keep a local and a cloud model ready together and @mention either one for a single message with the conversation carrying over.

Does GIDE support MCP servers?

Yes. GIDE has a full MCP (Model Context Protocol) client with a gallery and management UI, and ships its own Context Memory Server: structured memory kept outside the model across sessions.

Is GIDE suitable for regulated or air-gapped environments?

Air-gapped deployment, with offline license activation and no network needed, is available on Enterprise. In every setup GIDE works only inside the folder you grant, asks before it writes, and keeps a local JSONL audit log on the device. Have specific requirements? Contact us.