Call Me
Summary
Call Me is a closed agent framework that wires LLMs directly to telephony for outbound voice interactions.
Call Me lets developers connect language models to phone systems so the models can dial numbers, speak, listen, and complete tasks such as appointment setting or follow-ups. It occupies the space between text-only LLM tools and the still-dominant channel of voice calls that many organizations use for customer outreach. No concrete pricing is listed. The largest practical constraint is that the system is not open source, so users depend entirely on the provider for reliability, updates, and data handling.
Bottom line: *Choose Call Me when voice reach matters and closed code is acceptable; skip it when self-hosting or full transparency is required.*
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.
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
Call Me bridges the gap between an autonomous Claude Code session and a human who has stepped away from the keyboard. The agent uses the plugin’s built-in tools to dial a personal number provided by the companion iOS app, speaks a question, and receives the transcribed spoken answer back inside the active session — or sends an SMS if a voice call is overkill. Setup is two slash commands in Claude Code followed by a session restart; the app itself is free and generates a personal ten-digit number on first launch.
The differentiating feature is the voice round-trip: the agent does not just fire a notification and forget it. It waits, captures the spoken response as text, and can use that text to decide what to do next. That loop — agent asks, human speaks, agent continues — is the specific gap this tool fills that a webhook ping or email cannot.
The tool fits a narrow but real scenario: a solo developer or researcher who runs long Claude Code sessions overnight or in the background and wants to stay in the loop on decisions that require judgment without babysitting a terminal. It breaks immediately when the use case expands — there is no API surface, so programmatic integration from other runtimes is not possible, and the iOS app means the recipient must be on an iPhone. Teams that need to route escalations to multiple people, or to a non-iPhone user, hit that constraint on the first real deployment.
Installation follows two separate slash-command messages in Claude Code (`/plugin marketplace add radres/call-me` then `/plugin install call-me@call-me`), and the docs note the inbound monitor only initialises in a fresh session after both commands run. The repo also ships a CLI (`callme qr`, `callme setup`) for terminal-first workflows.