Call Me
Summary
Call Me is an agent framework that links large language models directly to telephony infrastructure for spoken conversations.
The system lets developers construct agents capable of placing and handling phone calls where an LLM manages the dialogue flow in real time. It occupies the narrow intersection between text-based model orchestration and legacy voice networks that most frameworks leave unaddressed. Its concrete differentiator is native outbound dialing rather than text or chat interfaces alone. Pricing is not disclosed by the provider. The main drawback is its closed-source status, which prevents code review or self-hosting.
Bottom line: *Choose it only when live voice calling is mandatory and transparency is secondary.*
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 agent that finishes work and a human who needs to know about it. The core workflow: install the Claude Code plugin with two slash commands, enter your personal Call Me number from the iOS app, and the agent gains two new capabilities — place a voice call to your iPhone that reads a question aloud and transcribes your spoken answer back as text, or send a text message and capture your reply as input to the next step. The vendor describes this as agent-side tooling; the iOS app handles telephony, and the repo provides the integration layer.
The differentiating feature is the voice call loop. Most agent notification schemes are one-way — a webhook fires, a Slack message posts, and the agent moves on regardless of whether you saw it. Here the agent blocks, waits for your spoken response, and gets that response back as transcribed text it can act on. That makes it viable for approval gates, clarification requests mid-task, and scripted callbacks where the answer changes what happens next.
The integration surface is narrow by design. The repo ships a Claude Code plugin and a standalone CLI skill. There is no hosted API and no documented integration path for other agent frameworks. If your agents run outside Claude Code — in LangChain, a custom Python loop, a CI/CD runner — this tool does not reach them without additional work that the docs do not describe. The iOS app is also required on the receiving end; there is no Android support mentioned in the repository.
Installation follows a specific two-message sequence in Claude Code — the docs note that slash commands only run one per message, so both commands must be sent separately. After that, telling Claude to ‘set up Call Me’ triggers a configuration flow that stores your number and sends a confirmation text. The CLI also exposes a QR code command and a setup walkthrough for terminal-first workflows.