diff --git a/src/pages/index.astro b/src/pages/index.astro index dfbedf2..4a0900c 100644 --- a/src/pages/index.astro +++ b/src/pages/index.astro @@ -30,14 +30,14 @@ const version = pkg.version ?? "";
- Zaguán Blade runs a local AI daemon that understands your entire project without sending your code to the cloud. Get the leverage of an AI coding assistant with the speed of a native editor, built specifically for engineers who need more than just autocomplete. + A lightweight AI code editor with a real diff workflow — not a chat window glued to VSCode. Full-project AI edits. Local-first. No 4GB RAM tax.
@@ -52,73 +52,109 @@ const version = pkg.version ?? ""; - -Most AI editors just predict your next line. Zaguán Blade actively manages a workspace, executes shell commands, runs your tests, and writes multi-file patches. It's an autonomous agent embedded directly in your editor.
-+ Zaguán Blade was built because modern AI editors feel bloated, opaque and cloud-dependent. +
++ Blade separates the UI from the AI daemon, keeps resource usage low, and respects Git as the source of truth. It’s built for engineers who care about control and hate silent failures. +
++ Used daily to develop Zaguán Blade and zcoderd. Tested on real production projects. +
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 | +
Instead of just looking at open files, Blade reads your workspace structure, searches for patterns, and compresses history into artifacts. It knows your codebase like a teammate.
-Native performance with Vite's lightning-fast build system. Custom CodeMirror 6 editor with "Vertical Diff Blocks" for AI code generation.
-The editor GUI stays lightning fast while a dedicated Go backend handles all AI logic, system prompts, and tool execution out of the main thread.
-Long conversations are automatically distilled into retrievable artifacts. The AI knows when and how to access this context - maintaining coherence without the overhead.
-Visualize the last 50 commits in an interactive Git graph with a details popup for commit information. Powered by gix for fast, native Git operations.
Run your AI locally or in the cloud. Full support for Ollama Cloud alongside the existing Ollama local model integration.
-After a UI reload or crash, streaming resumes automatically and the chat scrolls to the latest message — no lost context, no stuck states.
-Snappier autoscroll, instant settings saves, modernized title bar, faster model selector, and a redesigned app icon across the board.
+No magic behind the scenes. Just predictable operations and complete transparency.
- Zaguán Blade is under heavy development. Download today to get a fully functional local AI editor, native Git integration, and our advanced context engine. Expect rapid updates and occasional breaking changes as we build toward v1.0.0. + Zaguán Blade is under heavy development. Expect rapid updates, occasional breaking changes, and a fast feedback loop as we build toward v1.0.0.
Zaguán Blade
Tauri v2 + Vite + React
User interface only
Tauri v2 + Vite + React
User interface only.
Lightning fast.
Zaguán Coder Daemon (Go server)
State management
Tool execution & AI
Go server
State management
Tool execution & AI
Communication layer
Real-time sync
AI editor control
Local or remote.
Ollama, Anthropic, OpenAI, etc.
You choose.