Call Me
Summary
Call Me connects large language models to outbound and inbound phone calls through an agent interface.
The service lets an LLM place or receive calls and carry on spoken conversations without separate telephony code. It targets the gap between chat-only models and tasks that require reaching people by voice. No pricing information is published. The largest drawback is the total lack of public benchmarks, logs, or independent tests, so reliability and latency remain unknown until a user tries it directly.
Bottom line: *Try only for low-stakes experiments; skip when call quality or uptime matters.*
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Call Me
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Agents that run unattended hit a wall when a decision requires a human. Call Me bridges that gap by giving Claude Code agents the ability to ring your actual iPhone, speak a question aloud, and receive your spoken reply as text the agent can read and act on. The workflow is iOS app first — you install the app, tap through onboarding, and receive a personal 10-digit Call Me number. You hand that number to the agent, and from that point the agent can phone or text you whenever it decides a step needs your input. The vendor describes two slash commands to add the plugin to Claude Code, followed by a session restart to bring up the inbound monitor.
The differentiating detail here is that the contact channel is a real phone call to a real iPhone, not a webhook, a Slack ping, or an email that gets buried. If you are away from the keyboard — in a meeting, driving, off the laptop entirely — the agent can still reach you. Your spoken answer comes back as text, so the agent continues without requiring you to type anything or open a terminal.
This tool fits tightly inside one workflow: Claude Code sessions where the developer is the human the agent needs to reach. It handles persistent reminders across long-running sessions and spoken confirmations before the agent proceeds with a consequential step. The wall appears the moment you step outside that boundary. There is no API, so integrating phone-out capability into a non-Claude-Code agent requires forking the plugin. The integration is also personal by design — it calls your number, not a queue of on-call engineers, which means it does not scale to team on-call rotation without custom work.