updated 2026-08-12 05:02 UTC

agent-device

callstack/agent-device

CLI to control iOS and Android devices for AI agents

Browser & Computer Use TypeScript Grade D Listed MIT
45.5/100
Rank #514 of 1283
Compare agent-device

How does it stack up against its Browser & Computer Use neighbours?

Pick any agent to compare →

Thin or incomplete trust evidence. Review carefully before production use.

Open compare tool Suggest correction
Listing state
Listed
Evidence coverage
Grade C · 2/5 signals
Last push
2026-08-12 · 0d ago
Recent change
New

Is agent-device safe? agent-device scores 45.5/100 (Grade D), ranked #514 of 1283 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types). The public evidence: no package-provenance attestation found; no OSSF Scorecard result yet; 97% of recent commits are signed; last pushed 2026-08-12. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Browser & Computer Use

#21 Agent-S — 48.4 (D) → #22 Browser Use Web UI — 46.6 (D) → #24 Peekaboo — 42.9 (D) → #25 MolmoWeb — 42.3 (D) →

Quick Trust Read

What Would Improve It
Add or improve OSSF Scorecard coverage so safety checks are easier to verify.
Recent Changes
2026-08-10
Newly Listed
First tracked at rank #518
Maintainer Checklist
Add Scorecard coverage Expose the repository to OpenSSF Scorecard checks so supply-chain posture is easier to verify.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
Compare with another agent Get email alerts for agent-device View Browser & Computer Use Report missing data
82.9
Activity sub-score · out of 100
#23
In Browser & Computer Use

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade D reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-08-12 05:02 UTC · Repo last pushed today

Rank Trend

2026-08-11 2026-08-12

Activity & Reach

Stars
4.1k
Forks
249
Last Push
2026-08-12
today
Commits (4 wk)
341
Downloads (7d)
131,465
npm
HN mentions (30d)
—
Open Issues
45
Rank Change
▲3
was #517

Analysis

HVTrust Dimensions vs Browser & Computer Use

45.5 / 100 · 67.0% confidence

agent-device Browser & Computer Use average (41 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
4.9 / 25
2.5 below avg 7.4
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
1.6 below avg 12.4
Transparency50% declared license · 50% OSSF Scorecard
8.5 / 17
2.3 below avg 10.8
Maintenance60% last-push freshness · 40% commit activity
20.0 / 20
7.0 above avg 13.0
AdoptionLog-scaled stars · package downloads
15.5 / 20
4.3 above avg 11.2

Activity Inputs

82.9 / 100
StarsRepository reach
21.7 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
11.2 / 20

Supply Chain Trust

Package Provenance
None
No package attestations found
OSSF Scorecard
—
Not available
Signed Commits
97%
of last 100 commits verified

Is agent-device safe?

Public trust evidence for agent-device is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.
Does agent-device publish package provenance?
No published build provenance is currently detected for agent-device. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does agent-device have an OpenSSF Scorecard?
No OpenSSF Scorecard data is currently published for agent-device. Maintainers can enable the Scorecard GitHub Action to get a public score; without it, automated supply-chain hygiene is harder for outsiders to verify.
Is agent-device actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does agent-device use?
agent-device ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are agent-device's commits signed?
97% of the last 100 commits to agent-device are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
high confidence
Implemented
agent-device appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
medium confidence
1 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
1 tags
Broad capability areas detected.
  • shell
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live

Maintain agent-device?

For maintainers

HVTrust scores agent-device from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Listed 1
2026-08-10
Newly Listed
First tracked at rank #518
GitHub → npm: agent-device

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 45.5 Grade D
Markdown:
[![HVTrust](https://hvtracker.net/badge/agent-device.svg)](https://hvtracker.net/agents/agent-device)
HTML:
<a href="https://hvtracker.net/agents/agent-device"><img src="https://hvtracker.net/badge/agent-device.svg" alt="HVTrust"></a>

Other agents in Browser & Computer Use

Data sources
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance)
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.3 · Raw JSON