Call Me
Summary
Call Me runs an LLM agent that places and conducts live phone calls for users.
The service connects to telephony infrastructure so the model can speak, listen, and respond during actual calls without a human on the line. It targets repetitive outreach tasks where voice contact is still required but constant supervision is not. No pricing information is published. The clearest drawback is the complete absence of public benchmarks or failure-rate data, leaving users to test reliability themselves.
Bottom line: Use it for scripted outbound calls; skip it when accuracy or compliance cannot be verified in advance.
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
Most background agent jobs either block waiting for input or push past a decision point they shouldn’t touch alone. Call Me connects Claude Code to a personal iPhone number — the iOS app assigns a dedicated 10-digit number, and any running agent that has that number can place a voice call, ask a question in synthesized speech, and receive the transcribed spoken reply as text back in the session. The Claude Code plugin adds the inbound monitor on session start; individual agent skills handle outbound calls and texts.
The differentiating detail is voice, not just text. Where most agent notification tools send a push or a webhook you read later, Call Me rings the phone. The agent waits, you answer, you speak, and the session continues with your actual words as input. For deployment confirmations or code review sign-offs where a yes/no text feels too low-stakes to check promptly, a ringing phone changes the response latency from minutes to seconds.
The tool fits a narrow but real scenario: a single developer running long or overnight Claude Code sessions who wants to stay reachable without polling a dashboard. It does not fit team environments — there is no routing to multiple recipients, no escalation chain, and no SLA around delivery if the phone is off or on Do Not Disturb. The repo is a personal open-source project with seven stars and no open issues, which means community-driven fixes are sparse and the maintenance surface is effectively one person.
Installation follows two slash commands in Claude Code (`/plugin marketplace add radres/call-me` then `/plugin install call-me@call-me`) followed by a session restart to bring up the inbound monitor. The CLI also ships a `callme qr` command that prints a scannable QR code for the App Store link and a `callme setup` command that prints the full setup steps — useful when working in a terminal without a browser.