Status basis: npm_downloads_7d gained 10541 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 10541 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 38247 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 2171 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 38247 in the last 3d vs 2171 in the 3d before (ratio 17.6x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 34746 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 34746 (<= 40% of the prior window)
- Anomaly daily change 32575.0 is 4.9 standard deviations from this entity's own prior mean (-7266.7±8105.6, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 32575.0 is 4.9 standard deviations from this entity's own prior mean (-7266.7±8105.6, 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 | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | mcp | 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 digital AI reasoning and physical device control, making it a critical component for real-world AI automation.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“npm install -g agent-device@latest”— readme
“run device actions, and save evidence”— readme
“Glama MCP server”— readme
“CLI to control iOS and Android devices for AI agents”— readme
FAQ
What is agent-device?
CLI tool to control iOS and Android devices for AI agents, enabling real-world automation and interaction.
What does agent-device do?
Allow AI agents to remotely control iOS and Android devices to perform automated testing, simulation, or real-world interactions.
Why does agent-device matter?
It bridges the gap between digital AI reasoning and physical device control, making it a critical component for real-world AI automation.
Is agent-device open source?
Yes — agent-device is open source.
Can I self-host agent-device?
Yes — agent-device can be self-hosted.
What does agent-device integrate with?
mcp
How popular is agent-device?
As tracked by KanonAgent: 38 upvotes (first indexed 2026-07-16).
What are the best agent-device alternatives?
Similar AI agents tracked by KanonAgent: open-design, deer-flow, ruflo, career-ops, archify, cherry-studio.