Docs platform
Astro Starlight docs and AI agent readiness
6 of the 97 products tested serve their documentation on Astro Starlight.
Scores run from 42.5% to 88.8%, averaging 68.8%. Every Astro Starlight product tested passes Markdown mirror. The AI Agent Readiness Test scores the documentation, never the platform, so these numbers describe what these 6 teams published rather than what Astro Starlight can do.
Scores on Astro Starlight
| Product | Category | Grade | Score | Reading | Surface | llms | full | .md | MCP | AI |
|---|---|---|---|---|---|---|---|---|---|---|
| Warp | Coding agents | B+ | 88.8% | 21/30 | 50/50 | pass | pass | pass | pass | pass |
| Netlify | Cloud & developer platforms | C+ | 77.5% | 22/30 | 40/50 | pass | fail | pass | pass | pass |
| LlamaIndex | Agent frameworks & memory | C- | 71.2% | 27/30 | 30/50 | pass | fail | pass | pass | fail |
| Letta | Agent frameworks & memory | C- | 70.0% | 26/30 | 30/50 | pass | fail | pass | fail | pass |
| Daytona | Agent sandboxes & browsers | D- | 62.5% | 20/30 | 30/50 | pass | pass | pass | fail | fail |
| OpenCode | Coding agents | F | 42.5% | 24/30 | 10/50 | fail | fail | pass | fail | fail |
Agent surface on Astro Starlight
- llms.txt 5 of 6
- llms-full.txt 2 of 6
- Markdown mirror 6 of 6
- MCP server 3 of 6
- Docs AI 3 of 6
Recorded as Astro Starlight during testing. A sample of 6 shows what these teams shipped and does not establish a platform default.
All docs platforms · Every score in one table
Put another docs site through the battery.
Nominate a docs site