Local-First AI Code Editor

Your code stays yours. Cloud when you want it.

Local-First / No API Key Required / Any Model Provider

Most AI editors ship your context to a server you don't control. Blade keeps it local by default. No API key required.

Run Ollama locally or connect to any OpenAI-compatible endpoint. Switch to cloud when you need speed. Your choice, not the editor's.

Why Another Editor
Exists

Existing AI editors make you trade control for convenience. Blade doesn't ask for that trade.

The UI is separate from the AI daemon. Resource usage stays low. Git is the source of truth, not a history you can't export. No telemetry. No cloud dependency unless you choose it.

Used daily to develop Blade and zcoderd. Tested on real production projects — not just demos.

The Lightweight Difference

Engineers trust metrics. Here is what idle resource usage looks like:

Tool Idle RAM
Zaguán Blade ~320 MB
VSCode + AI ~1.9 GB
Windsurf ~2.8 GB

Not for Everyone

  • If you want a VSCode clone, this isn't it.
  • If you need heavy UI plugins, this isn't it.
  • If you want lightweight, controlled AI workflows — this is for you.

What It's Actually
Good At

What It's Actually Good At

  • + Refactoring across multiple files.
  • + Updating changelogs and build configs.
  • + Reviewing AI patches safely with diff control.
  • + Running locally with your own models.

Typical Flow in Blade

  1. Ask for change.
  2. AI calls project tools.
  3. Diff appears.
  4. You review.
  5. Accept or revert via Git.

No magic behind the scenes. Just predictable operations and complete transparency.

Zaguán Blade is under heavy development. Expect rapid updates, occasional breaking changes, and a fast feedback loop as we build toward v1.0.0.

1
Active

Zaguán Blade (UI)

Tauri v2 + Vite + React
User interface only.
Lightning fast.

2
Active

zcoderd (AI daemon)

Go server
State management
Tool execution & AI

3
Active

Model Provider

Local or remote.
Ollama, Anthropic, OpenAI, etc.
You choose.

Zaguán AI
Required

Without Subscription
Manual edits, no AI features
With Subscription
AI tool calls, code review, multi-model access
Multi-model routing Priority support (email) Early access to new tools Funding development
View Pricing & Plans