Bespoke AI

AI autocomplete for prose and code in VS Code — powered by your Claude subscription or API key

Early release — Please bear with the rough edges. 👷 Expect occasional bugs and fluctuating (or poor) quality in some scenarios. Open an issue if you run into any problems.

💻 macOS, Linux, and Windows — Also works in VSCodium.

🖊️ Writing, not just code — Inline completions for prompts, journals, notes, docs, and code. Matches your voice and style in prose; language-aware in code.

🔑 Subscription or API key — Use your Claude subscription through Claude Code (no per-token costs), or bring your own API key from xAI, OpenAI, Anthropic, Google, OpenRouter, or Ollama.

✨ One-click commit messages — Hit the sparkle button in Source Control to generate a commit message from your staged diffs.

✏️ Suggest edits — One-command typo, grammar, and bug fixes for visible text.

🔧 Context menu — Right-click to Explain, Fix, or Do custom actions on selected text. (Requires Claude Code backend.)

Screenshots

Writing — autocompleting a prompt to Claude:

Code — filling in a function body:

Commit messages — the sparkle button in Source Control:

🚀 Getting Started

1. Install from the VS Code Marketplace (search for "Bespoke AI")
2. On first launch, the extension detects whether you have the Claude Code CLI — if not, it offers to help you set it up or switch to API key mode
3. Start typing — completions appear as gray suggestion text after a ~2-second pause

That's it. The extension walks you through setup. Details for each path below if you need them.

Triggering Completions

Completions appear automatically after a ~2-second pause (the relaxed preset). Press Alt+Enter to trigger one instantly at any time.

If Alt+Enter doesn't work, another keybinding is likely intercepting it. Open Keyboard Shortcuts (Ctrl/Cmd+K Ctrl/Cmd+S), search for alt+enter, and rebind any conflicts — Inline Chat is the most common one.

Change trigger behavior via the status bar menu: relaxed (~2s), eager (~800ms), or on-demand (Alt+Enter only).

Modes

Override via settings or the status bar menu.

💡 Why This Exists

I tried every open-source AI autocomplete extension I could find. Most handled code fine but fell apart with prose — breaking paragraphs mid-thought, injecting code syntax into journal entries, producing gibberish outside of source files. Nothing came close to Copilot for non-code text.

So I built my own. And since I was already paying for a Claude subscription, I realized I could wire it up to use Claude Code instead of raw API calls — getting frontier model completions (Haiku, Sonnet, even Opus) at no additional per-request cost. Built on the Claude Agent SDK, it took extensive prompt engineering, but the result handles writing just as well as code.

The Claude Code backend uses your existing subscription (Pro, Team, or Enterprise). Heavy use may be subject to Anthropic's rate limits. The API backend uses standard per-token pricing from your chosen provider.

🧩 Available Models

The API backend includes presets for popular providers. Change the active preset via the status bar menu or the bespokeAI.api.preset setting.

API keys: Store keys via the Enter API Key command (Command Palette → "Enter API Key"). Keys are saved in your OS keychain. As a fallback, the extension also checks environment variables and ~/.creds/api-keys.env:

xAI → XAI_API_KEY · Anthropic → ANTHROPIC_API_KEY · OpenAI → OPENAI_API_KEY · Google → GEMINI_API_KEY · OpenRouter → OPENROUTER_API_KEY · Ollama → no key needed

Custom models: Run Bespoke AI: Add Custom Model from the Command Palette for a guided setup wizard. Any OpenAI-compatible endpoint works (LM Studio, Together, Mistral, etc.), plus Anthropic, Google, and OpenRouter. You can also add presets manually:

"bespokeAI.api.customPresets": [
  { "name": "My Llama", "provider": "openai-compat", "modelId": "llama3.2", "baseUrl": "http://localhost:1234/v1" }
]

⚙️ Configuration

All settings live under bespokeAI.* in VS Code settings.

📋 Commands

User types → Mode detection → Context extraction → LRU cache check
  → Debounce → Backend Router → Claude Code CLI or API → Cleanup → Ghost text

🔍 Troubleshooting

Completions not appearing?

• Check the status bar — is it showing "AI Off"? Click to re-enable.
• If it shows "Setup needed", the Claude Code CLI may not be installed or authenticated.
• Check if trigger preset is "on-demand" — in that mode, press Alt+Enter to trigger.
• Open the Output panel ("Bespoke AI") and check for errors.
• Run the "Bespoke AI: Restart Pools" command from the Command Palette.

"Claude Code CLI not found"?

• Install Claude Code: curl -fsSL https://claude.ai/install.sh | bash (macOS/Linux) or npm install -g @anthropic-ai/claude-code (any platform)
• Restart VS Code after installation.

"Authentication required"?

• Run claude in your terminal and follow the login prompts.
• Ensure you have an active Claude subscription (Pro, Team, or Enterprise).

Windows: Explain/Fix/Do commands garbled?

• Context menu commands use bash-style shell escaping. On Windows with PowerShell or cmd.exe, text containing $, backticks, or special characters may not pass through correctly.
• Workaround: set your VS Code terminal to Git Bash or WSL.

Still not working?

• Check for orphaned processes:
  • macOS/Linux: pkill -f "claude.*dangerously-skip-permissions"
  • Windows: Use Task Manager to end node.exe processes running Claude
• Check for a stale lockfile at ~/.bespokeai/pool.lock and remove it.
• Disable and re-enable the extension.

🔒 Privacy

Bespoke AI sends the text surrounding your cursor (prefix and suffix context) to the configured backend for completion. Commit message generation sends your staged diff, and suggest edits sends the visible editor content. No other files or data are transmitted. When using the Claude Code CLI backend, requests go through your local Claude Code installation. When using the API backend, requests go directly to your chosen provider's API endpoint. All API keys are stored in your OS keychain via VS Code SecretStorage.

🛠️ Development

npm install && npm run compile    # Build
npm run watch                     # Watch mode (F5 to launch dev host)
npm run check                     # Lint + type-check
npm run test:unit                 # Unit tests
npm run test:quality              # LLM-as-judge quality tests

Tested Models

These are the models the quality test suite runs against. Contributors should test prompt changes against at least one model per extraction strategy (e.g., CLI sonnet, GPT-4.1 Nano, xAI Grok).

Coverage: all 3 extraction strategies, 6 providers, 3 cost tiers, code-specialized model, local option. See CLAUDE.md for testing commands.

🤝 Contributing

Contributions welcome — fork the repo, create a branch, and open a pull request.

• Run npm run check before submitting (must pass)
• See CLAUDE.md for architecture details, testing workflows, and coding conventions
• Open an issue for bugs or feature ideas

👤 Author

Built by Trent McNitt — AI developer specializing in agent development, prompt engineering, and full-stack applications.

Available for contract work on Upwork →