docs(readme): visual refresh — real product screenshots, docs links, verified facts - #236
Conversation
- Real screenshots from a production device: the desktop environment (hero) and a live agent chat showing actual tool calls (exec/glob) — captured via Playwright against a ClawBox, English UI, personal data avoided - Product photo (device on desk) from clawbox.tech into the Hardware section - Theme-aware wordmark header (light/dark <picture> swap) - New Documentation section: docs.clawbox.tech, Technical Reference, Troubleshooting/Recovery, Agent Interface, llms.txt for AI agents - New badges: Docs + latest GitHub release - Facts synced with the docs: port 18789 is token-gated (not 'localhost only'), ChatGPT-subscription lane and llama.cpp listed under Flexible AI, ~50 MCP tools (was 40+) - Discord invite standardized to the canonical discord.gg/vsTsaY4Tuk - 'How It Works' + MCP tool dump condensed to summaries linking the docs (single source — the old inline tool list had already drifted) - New Update section (System Update app / sudo clawbox update) and Contributing section (PRs target beta, CI + CodeRabbit) - Assets live in .github/assets/ (webp, 32-236 KB each)
Four-angle review applied: - Facts: wizard step order corrected (WiFi w/ language -> updates -> password -> AI -> Telegram, per SetupWizard.tsx); ALLOWED_HOSTS default gains the 10.43.0.1 AP fallback; .env.example pointer reworded (the tabled vars aren't in it); '50+' API routes -> 90+ (93 actual route.ts files); CONTRIBUTING.md stale Discord invite -> vsTsaY4Tuk (the 3 device-UI .tsx occurrences go via a separate beta PR) - Dedup: setup-wizard flow now enumerated once (was 3x with 3 orderings); built-in app list once (Layer 3 no longer re-lists); Layer 4 count dropped (stated twice above); Community & Links section removed (every link was already in badges/footer) with OpenClaw credit folded into the footer; privacy claim stated once in the intro - Polish: chat screenshot width unified with hero (920); caption trimmed; Tech Stack Bun rows merged + architecture-reference pointer added; Technical Reference docs-table row tightened; language list -> count Verified by the review: all 8 badges live (release badge reads v3.1.5), all 9 docs.clawbox.tech links resolve, all 5 assets tracked, <picture> theme swap + floated img are GitHub-sanitizer-safe, '~50 MCP tools' = 48 actual.
|
Warning Review limit reached
Next review available in: 45 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThis PR updates documentation content across README.md and CONTRIBUTING.md, including a new dark-mode logo, refreshed badges, rewritten product/feature descriptions, a revised architecture explanation, updated environment variables and project structure, and a new Discord invite link. ChangesDocumentation Updates
Estimated code review effort: 2 (Simple) | ~10 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@README.md`:
- Around line 38-56: The privacy claim in the README is too absolute because the
`ClawBox is **OpenClaw OS**` intro and `**Privacy-first**` feature text say data
never leaves the device, while the `**Flexible AI**` section explicitly mentions
external providers like Claude, GPT, Gemini, and OpenRouter. Update this copy to
describe the product as local-first or on-device by default, and clearly qualify
that cloud providers may process prompts externally when those options are
enabled; keep the wording consistent across the intro and the key features
table.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 628b772f-4a9c-4fe7-b5c3-06396efa9469
⛔ Files ignored due to path filters (2)
.github/assets/wordmark-dark.pngis excluded by!**/*.png.github/assets/wordmark-light.pngis excluded by!**/*.png
📒 Files selected for processing (5)
.github/assets/chat-agent.webp.github/assets/clawbox-device.webp.github/assets/desktop.webpCONTRIBUTING.mdREADME.md
…CodeRabbit) 'Your data never leaves the device' contradicted offering Claude/GPT/Gemini, which process prompts externally. Reworded the intro and the feature row to local-first: data lives on the box, nothing leaves with local models, cloud providers are strictly opt-in.
1 participant
Repo-front refresh with real product assets and facts synced to the docs/code.
Visuals (all real, captured from a production ClawBox)
exec/globchips visible) — the "AI-operated OS" claim, demonstrated<picture>light/dark swap), Docs + latest-release badges.github/assets/(webp, 32–236 KB each)Content
llms.txtfor AI agentssudo clawbox update; PRs targetbeta, CI + CodeRabbitFacts verified against code/docs (four-angle review)
--bind lan)SetupWizard.tsx(WiFi w/ language → updates → password → AI → Telegram)ALLOWED_HOSTSdefault gains the10.43.0.1AP fallback;.env.examplepointer correcteddiscord.gg/vsTsaY4Tuk(README + CONTRIBUTING). Note: 3 device-UI.tsxfiles still carry the old invite — that's device code, so it goes via a separate PR tobeta.Suggested follow-up for @yalexx: upload the desktop hero as the repo's Social preview (Settings) — GitHub link unfurls don't use README images.
Summary by CodeRabbit