Iris
PerceptionReads expression, gaze and on-screen context in real time, so the interviewer notices hesitation and adapts.
ManavOS gives your AI a face, a voice and a memory. Real-time, photoreal AI humans that see, listen, remember and act, built with one API.
Aarohi
Meet the PALs
Example AI humans built on ManavOS. Pick one and start talking. Then build your own, with your face or ours.
One platform
ManavOS is the foundation for AI that meets people face to face. The same models power every persona; you decide who it is and what it does.
Use cases
ManavOS for Interviewing
Every candidate gets a real interview.
Aarohi runs structured, face-to-face first rounds around the clock, scores every answer against your rubric, and sends the evidence to your ATS.
Capabilities
The ManavOS models
An AI human is more than a talking head. Each layer is built in-house and tuned to work together, with Claude as the reasoning layer by default, or your own LLM.
Reads expression, gaze and on-screen context in real time, so the interviewer notices hesitation and adapts.
Photoreal faces and, in preview, full bodies: micro-expressions, posture and gesture rendered at video frame rates.
Voice, tone and turn-taking. Knows when you've finished a thought, and when you've only paused to think.
Remembers people across sessions, so a coach or tutor picks up exactly where you left off.
Developers
One API call gives your product a face, a voice and a memory. You own the logic; we handle rendering, perception and real-time media.
1import { ManavOS } from "@manavos/sdk";23const hos = new ManavOS({ apiKey: process.env.HUMANOS_KEY });45const interview = await hos.conversations.create({6 persona: "aarohi",7 brain: { provider: "anthropic", model: "claude" },8 rubric: "rb_data_analyst_v3",9 memory: { candidateId: "cand_0412" },10 webhook: "https://ats.example.com/manavos",11});1213// Send the candidate a join link, or embed it14console.log(interview.joinUrl);SDK shown as designed for the public beta.
Enterprise
ManavOS