Chert is Vapi for FaceTime. Build and deploy interactive AI video agents that can answer and place FaceTime calls with just a few lines of code. Deploy agents for remote support, field service, telehealth intake, guided onboarding, or anything that's easier to show than explain. Try it live: FaceTime an agent right now and show it something.
Loading comments…
Achievement
Project Info
Product Keywords
Chert is a developer platform for building and deploying interactive AI video agents that work over FaceTime. It positions itself as "Vapi for FaceTime," meaning it brings the same ease of voice-agent deployment to the video-call world. With just a few lines of code, you can create agents that both answer and place FaceTime calls, using the caller's live camera feed as visual context. Instead of describing a problem over audio, the agent can actually see what the caller is showing—a cable, a machine part, a wound, a document—and respond with precise, actionable guidance.
You define the agent's job, instructions, model, voice, and behavior before any call is placed. The prompt is the core of the agent—write it once, and the system handles the rest, from turn-taking to interruption behavior.
Chert lets you choose the avatar and framing that match your brand or use case. Whether you want a mid-shot professional or a more casual presence, the persona is configurable per assistant.
Deployment is as simple as publishing an assistant and assigning it to a provisioned FaceTime line. The platform manages the line, so you don't need to handle telephony or call routing yourself.
Before going live, you can test the agent in a browser preview. This checks the prompt, voice, microphone, interruption handling, avatar, and cleanup flow—without placing a single FaceTime call.
"Voice agents are blind. Chert isn't."
That's the core insight: a video agent can use the caller's camera context to understand what they are showing, not just what they say. Where a voice-only agent might ask "Uh, which cable?" and get a vague answer, Chert's agent sees the blue cable second from the left and names it directly. This visual grounding transforms support calls from frustrating guesswork into guided, step-by-step resolution. It's a fundamental shift from audio-only interaction to a shared visual workspace.
You're building any workflow where the caller's environment is part of the problem—remote support, field service, telehealth intake, guided onboarding, or visual inspections. If you've ever wished a support bot could just look at what the customer is seeing, Chert is worth a serious look. Note that the FaceTime API is currently in a controlled private preview, so production readiness is still being validated—but the browser preview lets you evaluate the experience before committing.
Other tools you might consider
We allow companies that operate in the physical world (home remodeling, roofing, trades) to automate inbound and outbound calling & texting and run multi-threaded campaigns spanning several weeks. Our AI agents can hold 100+ parallel conversations, speak in multiple languages and integrate into any CRM. We help put appointment scheduling, customer service & confirmation calls on autopilot and eliminate missed calls, slow speed to lead and insufficient lead follow ups for our customers.
Octopoda is an open source infrastructure layer that gives AI agents persistent memory, automatic loop detection, and full observability. Agents forget everything between sessions. Octopoda fixes that with a remember/recall API that survives restarts, crashes, and deployments. The loop detection system monitors 5 signals to catch agents stuck repeating themselves before they burn your API budget, with real-time cost estimation showing exactly how much each loop wastes. A built-in dashboard shows every agent's health score, memory explorer with version history, audit trail logging every decision with reasoning, and a timeline replay that lets you scrub through everything your agent did step by step. Works with LangChain, CrewAI, AutoGen, and OpenAI Agents SDK with one-line integrations. Runs locally with SQLite or connects to cloud with one environment variable. Free tier, MIT licensed. 177 signups, 120 GitHub stars, zero marketing spend.
Hyring is an advanced AI recruitment software platform designed to automate and streamline the entire hiring process. Using intelligent AI agents for screening, interviewing, and assessments, it helps HR teams hire faster and smarter. By reducing manual effort and bias, Hyring enables scalable, data-driven talent acquisition.
Ditch your scraper. One API gives your code everything it needs from the web: structured JSON, clean markdown, cited research, and browser automation. No browser, LLM, or pipeline for you to run. Use it from the tools you already work in: an MCP server, CLI, Raycast extension, or as an Agent Skill. Grab a key and make your first call in less than three minutes. Mozilla-backed. Your data is never sold, never trained on.
Maker
calm_kit
Loading comments…
