ZaguanAI/zblade.dev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update the main page with more info about zcoderd

Browse Source
This commit is contained in:
Stig-Ørjan Smelror
2026-02-05 13:48:27 +01:00
parent 44eaadc353
commit 6732060fd2
1 changed files with 18 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pages/index.astro
+21 -23
View File
@@ -30,10 +30,8 @@ const version = pkg.version ?? "";
<span class="meta-item">v{version}</span>
</div>
<p class="hero-description">
The graphical frontend ("The Body") for the Zaguán AI system.
Built with Vite + React Router as recommended by Tauri developers.
A lightweight, high-performance interface with deep AI integration through the Blade Protocol.
Supports Local AI via Ollama and OpenAI-compatible connections.
What you see is just the interface. The real magic lives in the <strong>Zaguán Coder Daemon</strong>—a Go-powered backend where all AI reasoning happens.
Its standout feature is <strong>Unlimited Context</strong>: instead of hitting token limits, we intelligently compress your conversation history and tool results into retrievable artifacts. The AI always gets exactly what it needs to work efficiently, without the bloat.
</p>
<div class="hero-actions">
<a href="#download" class="action-primary">
@@ -58,35 +56,35 @@ const version = pkg.version ?? "";
<div class="feature-primary">
<div class="feature-num">01</div>
<div class="feature-content">
<h3>ZAGUÁN CODER DAEMON</h3>
<p>The actual brain of the operation. A Go server that handles all AI logic, system prompts, and context management. This is where the heavy lifting happens—your editor stays lightweight and responsive.</p>
<div class="feature-tag">CORE ENGINE</div>
</div>
</div>
<div class="feature-row">
<div class="feature-item feature-highlight">
<div class="feature-num">02</div>
<h3>UNLIMITED CONTEXT</h3>
<p>We've solved the token limit problem. Chat history and tool results are actively compressed into artifacts. The AI retrieves only what it needs—efficient, focused, and without arbitrary limits.</p>
</div>
<div class="feature-item">
<div class="feature-num">03</div>
<h3>TAURI V2 + VITE</h3>
<p>Native performance with Vite's lightning-fast build system and React Router. Custom CodeMirror 6 editor with "Vertical Diff Blocks" for AI code generation. Built following Tauri's recommended stack.</p>
<div class="feature-tag">PERFORMANCE</div>
<p>Native performance with Vite's lightning-fast build system. Custom CodeMirror 6 editor with "Vertical Diff Blocks" for AI code generation.</p>
</div>
</div>
<div class="feature-row">
<div class="feature-item">
<div class="feature-num">02</div>
<h3>BLADE PROTOCOL V2</h3>
<p>Real-time sync between editor and AI. The protocol allows the AI to "pilot" the editor with seamless state management.</p>
</div>
<div class="feature-item feature-highlight">
<div class="feature-num">03</div>
<h3>WEB RESEARCH VISUALIZATION</h3>
<p>See what the AI is reading and thinking. Visualize research context as the AI gathers information from the web.</p>
</div>
</div>
<div class="feature-row">
<div class="feature-item feature-highlight">
<div class="feature-num">04</div>
<h3>BODY / BRAIN SEPARATION</h3>
<p>Lightweight GUI client with zero AI logic. All intelligence lives in the external Go-powered brain (Zaguán Coder Daemon).</p>
<p>The GUI contains zero AI logic—it's purely interface. All intelligence lives in the Coder Daemon. This means a lighter client and a more powerful, updatable backend.</p>
</div>
<div class="feature-item">
<div class="feature-item feature-highlight">
<div class="feature-num">05</div>
<h3>MULTI-MODEL ACCESS</h3>
<p>Connect to multiple AI models through the backend. Smart routing and context management for optimal results.</p>
<h3>SMART ARTIFACTS</h3>
<p>Long conversations are automatically distilled into retrievable artifacts. The AI knows when and how to access this context—maintaining coherence without the overhead.</p>
</div>
</div>