Iris
PerceptionReads expression, gaze and on-screen context in real time, so the interviewer notices hesitation and adapts.
ManavOS Custom Agents
Companions, concierges, museum guides, onboarding hosts. Design a persona in Studio or through the API, give it knowledge and tools, and put it anywhere.
Your persona
Real-time render of Your persona. Scripted preview; try a live conversation.
The problem
People trust, remember and enjoy conversations with faces. Until now, building one meant a studio, a render farm and a year.
ManavOS gives you rendering, perception, turn-taking and memory as building blocks. You bring the idea.
5min
From API key to first conversation.
6stock faces
Or create your own from a short video.
AnyLLM
Claude by default. Bring your own if you prefer.
1API
Personas, sessions, memory, knowledge, webhooks.
Product capabilities and design targets for the ManavOS beta.
What you get
How it works
Describe it
Personality, purpose and boundaries.
Equip it
Knowledge, memory and tools.
Ship it
Embed, link or call the API.
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.
The same models, tuned for different conversations. Each starts from a ready persona you can make your own.
Contact
Tell us what you’re hiring or building for. A person on our team, not a bot, will reply within one business day.
Prefer email? hello@manavos.ai
ManavOS · Dream your own