agent-device is a skill AI agent for Allow AI agents to remotely control iOS and Android devices to perform automated testing, simulation, or real-world interactions. Pricing: not stated on the product page. As of 2026-11-05, KanonAgent records 38 upvotes. First indexed by KanonAgent on 2026-07-16.
CLI tool to control iOS and Android devices for AI agents, enabling real-world automation and interaction.
38 upvotes
Tracked by Kanon since Jul 16, 2026
Status basis: npm_downloads_7d momentum fell to 32501 per 3d from 83867 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to 32501 per 3d from 83867 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 83867 per 3d from 233380 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 28348 per 3d from 420852 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 28348 per 3d from 420852 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 233380 in the last 3d vs 123313 in the 3d before (ratio 1.9x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 233380 in the last 3d vs 123313 in the 3d before (ratio 1.9x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 222218 in the last 3d vs 26474 in the 3d before (ratio 8.4x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 123313 in the last 3d vs 26474 in the 3d before (ratio 4.7x, threshold 1.5x)
- Anomaly daily change 215820.0 is 11.6 standard deviations from this entity's own prior mean (-225.9±18631.0, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -92507 per 3d from 26474 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 123313 in the last 3d vs 26474 in the 3d before (ratio 4.7x, threshold 1.5x)
- Anomaly daily change 215820.0 is 11.6 standard deviations from this entity's own prior mean (-225.9±18631.0, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 26474 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 26474 in the last 3d vs 10933 in the 3d before (ratio 2.4x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 10933 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 26474 in the last 3d vs 10933 in the 3d before (ratio 2.4x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -115777 per 3d from 4955 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -115777 per 3d from 12135 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 13442 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 4955 per 3d from 44042 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 12135 in the last 3d vs 6159 in the 3d before (ratio 2.0x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 12135 per 3d from 36862 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 13442 in the last 3d vs 4852 in the 3d before (ratio 2.8x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 8487 in the last 3d vs 4852 in the 3d before (ratio 1.7x, threshold 1.5x)
🔎 Known / Unknown
13 of 23 fields unknown
| 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.
🤖 Agent teardown · skill
Job to be doneAllow AI agents to remotely control iOS and Android devices to perform automated testing, simulation, or real-world interactions.
AutonomyL2 · tool-calling(evidence: "run device actions, and save evidence…")
Who it is forAI developers
Prerequisitesopen source · self-hostable
Integrationsmcp
Traction · why it is rising38 votes highlight its importance in enabling tangible, physical-world actions for AI agents.
Why it matters
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
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building agent-device? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
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: Stealth Venture, archify, open-design, deer-flow, ruflo, career-ops.