Call Me
Summary
Call Me provides an LLM-based agent framework focused on voice telephony interactions.
The product lets developers connect large language models to phone systems so agents can handle outbound or inbound calls. It occupies the narrow space between standard agent orchestration libraries and actual telephony infrastructure. No public pricing is listed. The main documented limitation is the complete absence of open-source code or independent benchmarks, leaving users dependent on vendor claims for performance and reliability.
Bottom line: Consider it only when proprietary voice integration is required and alternatives have been ruled out.
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
Agent workflows that include a human review step almost always implement that step as a polling loop against a dashboard, a Slack message nobody sees until the sprint is over, or a blocking prompt in a terminal that times out. Call Me takes a different route: when an agent reaches a decision point, it calls your iPhone, speaks the question using a voice response, and waits for your spoken reply — which comes back as text the agent can act on. The iOS app assigns you a personal 10-digit Call Me number, and that number is all the agent needs. The repo includes a Claude Code plugin installable via three slash commands and a skill layer for use in broader agent workflows.
The differentiating feature is the voice round-trip. Most human-in-the-loop tools stop at sending a notification; Call Me closes the loop by transcribing your spoken answer and returning it to the agent as structured text. This means an agent mid-run can ask an open-ended question — not just a yes/no — and act on whatever you say. For scripts or cron jobs running outside a terminal session, that is a meaningful difference from a missed Slack ping.
This fits tightly in one scenario: a solo developer running Claude Code locally who wants to stay reachable during long or risky agent runs without watching a terminal. It does not fit multi-developer teams, shared CI pipelines, or any workflow where the person the agent needs to reach does not have an iPhone. The GitHub repo has eleven commits and seven stars at the time of curation — the vendor states the app is free and open-source, but there is no documentation of server infrastructure, uptime guarantees, or what happens to voice transcription when the service is under load.
Installation follows a three-message flow inside Claude Code: one slash command adds the plugin from the marketplace, a second installs it, and a third message prompts Claude to complete the rest of the setup automatically. The CLI also exposes a `callme qr` command that prints a scannable QR code and a `callme setup` command that walks through the steps in the terminal — useful when setting up on a remote machine.