chrisrobison / textweb
A text-grid web renderer for AI agents — see the web without screenshots
Why this job: matched by what the repo talks about: web, agent, screenshot, text
What it does
Instead of taking expensive screenshots and piping them through vision models, TextWeb renders web pages as structured text grids that LLMs can reason about natively. Full JavaScript execution, spatial layout preserved, interactive elements annotated.
Get started
npm install -g textweb
npx playwright install chromium- Maintenance
- Inactive
- Last commit 8 months ago
- Stars
- 103
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- JavaScript
- 84% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| nottelabs / notte | 2,058 | yesterday | Custom | No downloads |
| Jeomon / Web-Use | 304 | 3 months ago | MIT | No downloads |
| alibaba / page-agent | 29,665 | 2 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- JavaScript 84%
- HTML 8%
- Python 7%
Topics
- ai
- browser
- llm
- lynx
- text
- web
Project record
- JobAutomation and scraping
- StatusListed
- Commits30
- Forks13
- Watching1
- Stars in 28 days0
- CreatedFeb 19, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026