PrivateMind
Get API key

Coding agents

Use PrivateMind with your favorite coding agent, IDE, or editor. OpenAI-compatible endpoint, no proxy required.

Every major coding agent and AI-powered IDE speaks the OpenAI API. PrivateMind is the same shape, just a different base URL.

Swap https://api.openai.com for https://api.privatemind.com, paste your PMIND key, and pick a model from your org's catalogue.

The general setup

Setting Value
Base URL https://api.privatemind.com/v1
API key Your PMIND key from Settings → API Keys
Model Anything from your catalogue — fast, reasoning, or a specific model id

If your tool lets you set a custom OpenAI-compatible endpoint, it works. The tool sends prompts, PrivateMind responds. No proxy, no local server.

Cline

Cline is a VS Code extension for AI-assisted coding. File edits, terminal commands, completions.

1. Install
Open VS Code → Extensions → search Cline → Install.

2. Open provider settings
Click the Cline icon in the Activity Bar, open Settings (⚙), and choose OpenAI Compatible.

3. Fill in PrivateMind

Setting Value
Base URL https://api.privatemind.com/v1
API Key Your PMIND key
Model ID fast or any model from your catalogue

Click Done. Cline now routes every completion through PrivateMind.

4. Test it
Open a file, ask Cline to explain a function or refactor something. Responses come from your org's models, not OpenAI's.

Continue

Continue is an open-source autopilot for VS Code and JetBrains. Tab completion, chat, inline edits.

Edit ~/.continue/config.yaml (or .vscode/settings.json for workspace-scoped):

YAML 
models:
  - title: PrivateMind Fast
    provider: openai
    model: fast
    apiKey: PMIND...:...
    apiBase: https://api.privatemind.com/v1

  - title: PrivateMind Reasoning
    provider: openai
    model: reasoning
    apiKey: PMIND...:...
    apiBase: https://api.privatemind.com/v1

Pick a model in Continue's dropdown and start typing. Tab completions and chat both work through the same endpoint.

Cursor

Cursor is an AI-native code editor. Composer, Cmd+K, and tab completion all support custom providers.

  1. Open Cursor Settings → Models.
  2. Scroll to OpenAI API.
  3. Turn on Use your own key.
  4. Set:
    • OpenAI Base URL: https://api.privatemind.com/v1
    • OpenAI API Key: Your PMIND key

Cursor composers and completions now run on your PrivateMind deployment instead of Cursor's built-in models.

OpenCode

OpenCode is a terminal-based coding agent that talks to any provider via the AI SDK.

Edit opencode.json (project root or ~/.config/opencode/opencode.json):

JSON 
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "privatemind": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "PrivateMind",
      "options": {
        "baseURL": "https://api.privatemind.com/v1",
        "apiKey": "PMIND...:..."
      },
      "models": {
        "fast": {
          "name": "Fast",
          "limit": { "context": 128000, "output": 4096 }
        },
        "reasoning": {
          "name": "Reasoning",
          "limit": { "context": 200000, "output": 65536 }
        }
      }
    }
  }
}

Run npx opencode and pick the PrivateMind provider in /models. Done.

What works

Because PrivateMind is OpenAI-compatible, these tools and many more work out of the box:

  • VS Code extensions: Cline, Continue, Tabnine (BYOK mode), Codeium (BYOK mode)
  • IDEs: Cursor, Windsurf, Zed
  • Terminal tools: Aider, Opencode, ollama (with remote endpoint configured)
  • Automation: n8n, Make.com, Zapier (use the HTTP module with the OpenAI format)

If it asks for an OpenAI API key or base URL, give it your PMIND key and https://api.privatemind.com/v1.

Where next