root/goodbuddy
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

fix: clarify site positioning and keep downloads prominent
Cross-platform packages / Validate source (push) Canceled after 0s
Details
Cross-platform packages / Authorize desktop packaging (push) Canceled after 0s
Details
Cross-platform packages / linux arm64 (push) Canceled after 0s
Details
Cross-platform packages / macos arm64 (push) Canceled after 0s
Details
Cross-platform packages / windows arm64 (push) Canceled after 0s
Details
Cross-platform packages / linux x64 (push) Canceled after 0s
Details
Cross-platform packages / macos x64 (push) Canceled after 0s
Details
Cross-platform packages / windows x64 (push) Canceled after 0s
Details
Cross-platform packages / Publish GitHub and OSS release (push) Canceled after 0s
Details
Deploy website to GitHub Pages / Deploy static website (push) Canceled after 0s
Details

Browse Source 
Highlight domestic platform support and built-in coding agents, replace placeholder demos with task workflows, and add bilingual setup FAQs. Keep downloads directly after the hero and improve mobile demo layout.

Release note: Update the bilingual website with clearer product copy and demos, prominent downloads, and setup guidance. DeepSeek Harness and LoongArch retain their preview labels.
This commit is contained in:
mesalogo
2026-09-28 12:10:22 +08:00
parent 013e72f69e
commit 83a3ea261e
5 changed files with 436 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sites/en.html
+117 -53
View File
@@ -5,14 +5,14 @@
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta
name="description"
content="GoodBuddy is an open-source desktop AI assistant for model chat, coding agents, knowledge, notes, and scheduled work. No GoodBuddy account is required."
content="GoodBuddy is an open-source desktop AI workspace with built-in OpenCode, Continue, and DeepSeek Harness (preview) integrations for coding, knowledge, notes, and scheduled work."
/>
<link rel="canonical" href="https://mesalogo.github.io/goodbuddy/en.html" />
<link rel="alternate" hreflang="zh-CN" href="https://mesalogo.github.io/goodbuddy/" />
<link rel="alternate" hreflang="en" href="https://mesalogo.github.io/goodbuddy/en.html" />
<link rel="alternate" hreflang="x-default" href="https://mesalogo.github.io/goodbuddy/en.html" />
<meta name="theme-color" content="#f6f8fb" />
<title>GoodBuddy | Open-source desktop AI assistant</title>
<title>GoodBuddy | Open-source desktop AI workspace</title>
<link
rel="icon"
href="./assets/goodbuddy-light.png"
@@ -72,8 +72,10 @@
<nav class="site-navigation" id="site-navigation" aria-label="Main navigation" data-navigation>
<a href="#download">Download</a>
<a href="#features">Highlights</a>
<a href="#assistant">Desktop assistant</a>
<a href="#workflows">Workflows</a>
<a href="#features">Features</a>
<a href="#assistant">Assistant</a>
<a href="#faq">FAQ</a>
</nav>
<div class="header-actions">
@@ -119,17 +121,17 @@
Windows · macOS · Linux
</div>
<h1 id="hero-title">
No account required.<br />
Model chat and coding agents<br />
<span>on your desktop.</span>
Your desktop<br />
<span>AI workspace.</span>
</h1>
<p class="hero-lead">
GoodBuddy manages conversations, knowledge, notes, and tasks on the desktop.
Its Agent Runtime connects direct models, OpenCode, Continue, and DeepSeek Harness.
Code, consult your sources, keep notes, and schedule follow-ups in GoodBuddy.
Built-in integrations bring three coding agents to the desktop:
OpenCode, Continue, and DeepSeek Harness (preview), alongside direct model chat.
</p>
<div class="hero-actions">
<a class="button button--primary" href="#download">Download now</a>
<a class="button button--secondary" href="#features">Explore Agent Runtime</a>
<a class="button button--secondary" href="#workflows">Explore workflows</a>
</div>
<ul class="hero-facts" aria-label="Product highlights">
<li>
@@ -138,7 +140,7 @@
</li>
<li>
<svg viewBox="0 0 20 20" aria-hidden="true"><path d="m5 10 3 3 7-7" /></svg>
Four Agent Runtime options
Built-in coding agents, configurable models
</li>
<li>
<svg viewBox="0 0 20 20" aria-hidden="true"><path d="m5 10 3 3 7-7" /></svg>
@@ -150,7 +152,7 @@
<div
class="product-stage"
role="img"
aria-label="GoodBuddy desktop app showing an AI coding task running through the unified Agent Runtime"
aria-label="GoodBuddy coding workspace: Continue fixes a search issue with file changes and test results"
data-tilt-stage
>
<div class="stage-glow stage-glow--one"></div>
@@ -159,7 +161,7 @@
<div class="window-bar">
<div class="window-dots" aria-hidden="true"><span></span><span></span><span></span></div>
<div class="window-title">GoodBuddy</div>
<div class="window-status"><span></span> Runtime connected</div>
<div class="window-status"><span></span> Agent connected</div>
</div>
<div class="app-layout">
<aside class="app-sidebar" aria-hidden="true">
@@ -180,13 +182,13 @@
<div class="app-content">
<div class="app-content-header">
<div>
<strong>Fix cross-platform build</strong>
<span>Project: Desktop client</span>
<strong>Fix empty search results</strong>
<span>Project: Knowledge search</span>
</div>
<div class="mode-pill">Continue · Execute</div>
</div>
<div class="message-area">
<div class="message message--user">Fix the build and validate all three desktop platforms.</div>
<div class="message message--user">Search returns nothing with extra spaces. Fix it and add tests.</div>
<div class="message message--assistant">
<div class="assistant-label">
<span class="assistant-avatar" aria-hidden="true">
@@ -197,15 +199,15 @@
</span>
<strong>GoodBuddy</strong>
</div>
<p>Agent Runtime loaded the project, Skills, and controlled tools.</p>
<p>Trimmed the query. Searches with no matches still show the empty state.</p>
<div class="tool-card">
<div class="tool-icon">
<svg viewBox="0 0 24 24" aria-hidden="true"><path d="M4 6h16M4 12h10M4 18h7" /></svg>
</div>
<div><strong>Preparing environment</strong><span>Continue · Project scope · Controlled tools</span></div>
<span class="tool-state">Ready</span>
<div><strong>File changes</strong><span>search.ts · search.test.ts</span></div>
<span class="tool-state">Updated</span>
</div>
<div class="plan-lines" aria-hidden="true"><span></span><span></span><span></span></div>
<div class="demo-result"><code>query.trim()</code><span>Tests passed: whitespace and no-match cases</span></div>
</div>
</div>
<div class="composer">
@@ -217,9 +219,9 @@
</div>
<div class="floating-card floating-card--approval">
<span class="floating-icon">
<svg viewBox="0 0 24 24" aria-hidden="true"><path d="M12 3 5 6v5c0 4.5 2.8 8.6 7 10 4.2-1.4 7-5.5 7-10V6l-7-3Z" /><path d="m9 12 2 2 4-4" /></svg>
<svg viewBox="0 0 24 24" aria-hidden="true"><path d="m8 7-5 5 5 5M16 7l5 5-5 5M14 4l-4 16" /></svg>
</span>
<span><strong>Unified Agent Runtime</strong><small>Direct models · OpenCode · Continue · DSH</small></span>
<span><strong>Built-in coding agents</strong><small>OpenCode · Continue · DeepSeek Harness (preview)</small></span>
</div>
<div class="floating-card floating-card--scope">
<span class="scope-dot"></span>
@@ -229,15 +231,6 @@
</div>
</section>
<section class="proof-strip" aria-label="Platform and Runtime support">
<div class="section-inner proof-grid">
<div><strong>4 Runtimes</strong><span>Multiple AI coding paths</span></div>
<div><strong>3 platforms</strong><span>Windows / macOS / Linux</span></div>
<div><strong>2 architectures</strong><span>x64 / arm64</span></div>
<div><strong>1 workspace</strong><span>Select, configure, run, audit</span></div>
</div>
</section>
<section class="section download-section" id="download" aria-label="Cross-platform downloads">
<div class="section-inner">
<div class="download-grid">
@@ -285,15 +278,53 @@
</div>
</section>
<section id="workflows" class="section workflows-section" aria-labelledby="workflows-title">
<div class="section-inner">
<div class="section-heading">
<div><p class="kicker">Everyday workflows</p><h2 id="workflows-title">From research to follow-up</h2></div>
<p>Search project material, save decisions, and set reminders for what comes next.</p>
</div>
<div class="workflow-grid">
<article class="workflow-card">
<div class="workflow-copy">
<p class="kicker">Knowledge and citations</p>
<h3>Find an answer and check its source</h3>
<p>Ask questions about local documents or your organization's knowledge base. Follow citations in the answer to the original material.</p>
</div>
<div class="workflow-demo">
<div class="demo-bar">Knowledge Q&amp;A</div>
<p class="demo-question">What should we check before a staging release?</p>
<p class="demo-answer">Check configuration, run regression tests, and confirm a rollback package is available. [1]</p>
<div class="demo-source">[1] Release handbook · Pre-release checks</div>
</div>
</article>
<article class="workflow-card">
<div class="workflow-copy">
<p class="kicker">Notes and schedules</p>
<h3>Keep notes and schedule the next step</h3>
<p>Save decisions in Magic Notes and schedule a reminder for work that needs a follow-up.</p>
</div>
<div class="workflow-demo">
<div class="demo-bar">Project follow-up</div>
<p class="demo-question">Save these notes and remind me to check release readiness next Monday.</p>
<p class="demo-answer">Saved: review the search fix and check regression results before release.</p>
<ul class="demo-checklist"><li>To-do: review the search fix</li><li>Schedule: next Monday, 09:00, release readiness check</li></ul>
<div class="demo-source">Magic Notes · Release preparation</div>
</div>
</article>
</div>
</div>
</section>
<section class="section features-section" id="features" aria-labelledby="features-title">
<div class="section-inner">
<div class="section-heading">
<div>
<p class="kicker">Product highlights</p>
<h2 id="features-title">Agent Runtimes in one desktop interface</h2>
<h2 id="features-title">Projects, knowledge, and agents on your desktop</h2>
</div>
<p>
Configure Runtime selection, model connections, Skills, MCP, and work modes on the desktop.
Choose an agent for the task, connect project files and knowledge sources, and review tool calls and results.
</p>
</div>
@@ -306,10 +337,10 @@
</svg>
</div>
<span class="feature-number">01</span>
<h3>One entry point for multiple Agent Runtimes</h3>
<p>Choose direct models, OpenCode, Continue, or DeepSeek Harness for each task without learning a new entry point.</p>
<h3>Built-in OpenCode, Continue, and DeepSeek Harness</h3>
<p>Select a coding agent, configure its model, and start a task in your project from the desktop interface. DeepSeek Harness is in preview. Direct model chat is also available.</p>
<div class="provider-pills" aria-label="Supported Agent Runtimes">
<span>Direct models</span><span>OpenCode</span><span>Continue</span><span>DeepSeek Harness</span>
<span>Direct models</span><span>OpenCode</span><span>Continue</span><span>DeepSeek Harness (preview)</span>
</div>
</article>
@@ -321,8 +352,8 @@
</svg>
</div>
<span class="feature-number">02</span>
<h3>Broad desktop architecture coverage</h3>
<p>Official Windows, macOS, and Linux releases cover x64 and arm64, with a separate experimental LoongArch preview.</p>
<h3>Local and SSH projects</h3>
<p>Work with local projects, or use OpenCode and Continue with remote projects over SSH. Remote projects require the companion gbagent on the remote host.</p>
</article>
<article class="feature-card">
@@ -333,8 +364,8 @@
</svg>
</div>
<span class="feature-number">03</span>
<h3>Runtime setup in the desktop app</h3>
<p>Select the Runtime, model, work mode, and project in the desktop interface.</p>
<h3>Connect existing knowledge services</h3>
<p>Use a local knowledge base or configure Dify, FastGPT, and RAGFlow connections to retrieve material for your conversations.</p>
</article>
<article class="feature-card">
@@ -345,11 +376,11 @@
</svg>
</div>
<span class="feature-number">04</span>
<h3>Runtime-specific capabilities and work modes</h3>
<p>Skills, MCP, and tools follow each Runtime. Ask stays read-only, while Execute remains approval-controlled and auditable.</p>
<h3>Separate questions from execution</h3>
<p>Ask stays read-only. Execute runs with the current account's permissions and records tool calls. Available tools depend on the selected Runtime and configuration.</p>
<div class="mode-row" aria-label="Two work modes">
<span>Ask <small>Read-only</small></span>
<span class="is-accent">Execute <small>Controlled</small></span>
<span class="is-accent">Execute <small>Account permissions</small></span>
</div>
</article>
@@ -361,8 +392,8 @@
</svg>
</div>
<span class="feature-number">05</span>
<h3>Project context in one place</h3>
<p>Organize conversations, knowledge, tasks, and run history by project without losing context when switching Runtime.</p>
<h3>Skills and MCP tools</h3>
<p>Import Skills and connect MCP services to give your chosen agent the tools you use at work.</p>
</article>
<article class="feature-card feature-card--wide">
@@ -392,8 +423,8 @@
<p class="kicker">Desktop assistant</p>
<h2 id="assistant-title">Conversations, knowledge, notes, and tasks on your desktop</h2>
<p>
GoodBuddy keeps reference material, to-dos, and long-running work in one desktop workspace,
so everyday assistance and AI coding share the same project context.
Keep reference material, to-dos, and ongoing work in one desktop workspace.
Choose project files for each conversation. See the configuration guide for each agent's context and tool support.
</p>
<a class="text-link" href="#download">
Choose your desktop release
@@ -404,11 +435,11 @@
<div class="assistant-list">
<article>
<span class="assistant-number">01</span>
<div><h3>Turn sources into searchable knowledge</h3><p>Import files, folders, and web pages, then search with full text, vectors, and a knowledge graph.</p></div>
<div><h3>Search files and web pages</h3><p>Import files, folders, and web pages, then configure full-text and vector search. Enable the knowledge graph to explore relationships between sources.</p></div>
</article>
<article>
<span class="assistant-number">02</span>
<div><h3>Notes, to-dos, and long-term follow-up</h3><p>Magic Notes captures ideas and tasks, while Heartbeat reviews progress, builds memory, and proposes next steps.</p></div>
<div><h3>Notes, to-dos, and follow-up</h3><p>Magic Notes captures ideas and tasks. Heartbeat reviews work at configured intervals; both Heartbeat and scheduled work require the desktop app to be running.</p></div>
</article>
<article>
<span class="assistant-number">03</span>
@@ -416,11 +447,42 @@
</article>
<article>
<span class="assistant-number">04</span>
<div><h3>Keep working away from your computer</h3><p>Connect messaging channels to separate conversations and hand tasks to GoodBuddy on your desktop.</p></div>
<div><h3>Reach your desktop assistant through messages</h3><p>Configure messaging channels to send tasks in separate conversations. Message processing requires your desktop to be online and the channel connection to be available.</p></div>
</article>
</div>
</div>
</section>
<section id="faq" class="section faq-section" aria-labelledby="faq-title">
<div class="section-inner">
<div class="section-heading">
<div><p class="kicker">Before you start</p><h2 id="faq-title">Frequently asked questions</h2></div>
<p>See the <a class="text-link" href="https://github.com/mesalogo/goodbuddy/blob/main/README.md">README getting-started guide</a> for installation and connection steps.</p>
</div>
<div class="faq-list">
<details>
<summary>Do I need an account or a paid model subscription?</summary>
<p>No GoodBuddy account is required. External model services may need an account or API key and charge at their own rates. Local models need a suitable runtime on your machine.</p>
</details>
<details>
<summary>Where does my data go?</summary>
<p>Conversation history and notes are stored on your machine. Using models, knowledge services, MCP tools, or messaging channels sends relevant content to the services you configure. Model requests may include retrieved passages and attachments.</p>
</details>
<details>
<summary>How do I set up a coding agent?</summary>
<p>Select an agent, configure its model connection, and open a project. Prepare or download the runtime components required by your agent and operating system. DeepSeek Harness is in preview. See the getting-started guide for installation steps.</p>
</details>
<details>
<summary>Which platforms and Chinese domestic systems are supported?</summary>
<p>Windows, macOS, and Linux releases cover x64 and ARM64, including corresponding Chinese domestic hardware. LoongArch has a separate experimental preview. For systems such as UOS and Kylin, choose the matching architecture and package; compatibility information does not imply vendor or whole-system certification.</p>
</details>
<details>
<summary>What do SSH projects require on the remote host?</summary>
<p>Remote projects with OpenCode and Continue require a working SSH connection, a companion gbagent matching your desktop version, and the required runtime environment on the host. Operations use the remote login account's permissions. See the README for setup.</p>
</details>
</div>
</div>
</section>
</main>
<footer class="site-footer">
@@ -432,11 +494,13 @@
</span>
<span>GoodBuddy</span>
</a>
<p>Open-source desktop AI assistant. No account required.</p>
<p>Open-source desktop AI workspace. No GoodBuddy account required.</p>
<div class="footer-links">
<a href="#download">Download</a>
<a href="#features">Agent Runtime</a>
<a href="#assistant">Desktop assistant</a>
<a href="#workflows">Workflows</a>
<a href="#features">Features</a>
<a href="#faq">FAQ</a>
<a href="https://github.com/mesalogo/goodbuddy/blob/main/README.md">Getting started</a>
<a href="https://github.com/mesalogo/goodbuddy" target="_blank" rel="noreferrer">
GitHub<span class="sr-only">(opens in a new window)</span>
</a>