AI & Agents
AgentCall
Last updated 2026-08-01 · benchmark measured 2026-08-01 — deterministic & reproducible
Connect an Android phone to your computer so a local AI agent can make real calls.
Is AgentCall production-ready?
Legit.Show scores AgentCall 73 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on AgentCall (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 80/100
- Accessibility — 95/100
- Security — 65/100
- Privacy — 25/100
- Reliability — 92/100
- Standards — 92/100
- Discoverability — 60/100
What we measured
- Security headers present: HSTS, X-Content-Type-Options, Referrer-Policy.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 286 ms to first byte.
- Returns a proper 404 for unknown routes.
- 0 of 0 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who built it
Siddharth Shinde
Who it's for
AI agent developers · Privacy-conscious users · People running local AI assistants · Those wanting to avoid cloud calling services
Pricing
Free and open source