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

feat(index): revise hero title and description

Browse Source 
Update hero messaging to emphasize local-first AI with optional cloud
usage. Simplify title to value-focused copy and adjust meta tags to
reflect flexibility between local and cloud models.
This commit is contained in:
Stig-Ørjan Smelror
2026-03-18 15:18:34 +01:00
parent 0611967330
commit 458cde9045
1 changed files with 6 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pages/index.astro
+6 -8
View File
@@ -18,21 +18,19 @@ const version = pkg.version ?? "";
<div class="hero-content">
<div class="hero-label">// NEXT-GEN EDITOR</div>
<h1 class="hero-title">
<span class="title-line-1">ZAGUÁN</span>
<span class="title-line-2">BLADE</span>
<span class="title-accent">AI-NATIVE CODE EDITOR</span>
<span class="title-line-1">Run AI locally.</span>
<span class="title-line-2">Or use cloud models.</span>
</h1>
<div class="hero-meta">
<span class="meta-item">RUNS LOCAL</span>
<span class="meta-divider">/</span>
<span class="meta-item">LOCAL AI</span>
<span class="meta-item">FULL PROJECT CONTEXT</span>
<span class="meta-divider">/</span>
<span class="meta-item">WHOLE PROJECT CONTEXT</span>
<span class="meta-divider">/</span>
<span class="meta-item">NO CLOUD REQUIRED</span>
<span class="meta-item">CLOUD OPTIONAL</span>
</div>
<p class="hero-description">
Zaguán Blade + zcoderd are built for long-running coding sessions. In our 250-turn benchmark, context compression and selective retrieval reduced token cost by ~31% on average, with higher gains in context-heavy runs. It’s not always cheaper in lean sessions — it’s designed to prevent context bloat when history grows.
Your code stays on your machine. No API required.
Switch to cloud when you need speed. , It’s not always cheaper in lean sessions — it’s designed to prevent context bloat when history grows.
</p>
<p class="hero-description" style="margin-top: var(--space-sm);">
Connect to local models via Ollama or any OpenAI-compatible endpoint. Your code, your AI, your hardware — fully private and offline capable.