Status basis: npm_downloads_7d momentum fell to -205 per 3d from 441 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -205 per 3d from 441 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -140 per 3d from 376 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -554 per 3d from 907 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 441 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -466 per 3d from 907 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 376 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 907 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 907 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 210 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 210 (<= 40% of the prior window)
- Anomaly daily change 753.0 is 4.5 standard deviations from this entity's own prior mean (-211.3±214.0, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 753.0 is 4.5 standard deviations from this entity's own prior mean (-211.3±214.0, baseline excludes this point) — unusual, not necessarily adoption
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 3 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | chrome | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
It bridges the gap between static model knowledge and real-time web data, significantly enhancing agent utility and autonomy.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“control browsers with sandboxed JavaScript scripts”— readme
“const page = await browser.getPage("main"); await page.goto("https://example.com"”— readme
“Persistent pages - Navigate once, interact across multiple scripts”— readme
“Connect to your running Chrome (enable at chrome://inspect/#remote-debugging)”— readme
FAQ
What is dev-browser?
A Claude skill that enables AI agents to browse the web, improving their ability to access real-time information.
What does dev-browser do?
To equip Claude AI agents with web browsing capabilities for retrieving current, dynamic information during automated workflows.
Why does dev-browser matter?
It bridges the gap between static model knowledge and real-time web data, significantly enhancing agent utility and autonomy.
How much does dev-browser cost?
Not specified
Is dev-browser open source?
Yes — dev-browser is open source.
What does dev-browser integrate with?
chrome
How popular is dev-browser?
As tracked by KanonAgent: 33 upvotes (first indexed 2026-07-08).
What are the best dev-browser alternatives?
Similar AI agents tracked by KanonAgent: open-design, Agent-Reach, deer-flow, ruflo, career-ops, archify.