Featured Project · Multimodal Agent

Hermes Live Companion

A human-governed, multimodal AI companion built with voice, vision, memory, tools, and interruption control.

Hermes Live Companion title card showing voice, vision, memory, and activity features
8h 46mactive MVP development
20explicit development commands
13commits before MVP
< 3 daysidea to hackathon delivery

The starting question

Can today's devices already deliver part of the AI-hardware future?

The project began during a conversation about what a future AI device might become. A laptop already has a microphone, speakers, camera, screen, network, and compute. Hermes already had sessions, memory, tools, and vision.

The missing piece was not another model. It was a governed, real-time interaction layer that could connect those capabilities without taking over the existing system.

Can the devices and agents already on hand do it first?

What was built

One session. Six connected capabilities.

The MVP connects real inputs, agent reasoning, visible controls, and natural outputs in a local-first experience.

01

Voice loop

Microphone input, speech recognition, streamed responses, and text-to-speech.

02

Vision

User-approved camera captures and scene analysis inside the same conversation.

03

Memory & sessions

Multi-turn context with explicit reset, stop, and session controls.

04

Tools & approvals

Existing Hermes tools with visible progress and human approval boundaries.

05

Interruption control

Keyboard, button, and acoustic barge-in controls keep the human in charge.

06

Local-first safety

Loopback-only services, temporary tokens, bounded files, and cleanup rules.

System architecture

A visible local runtime, not a black box.

Voice and vision enter through controlled channels. Hermes coordinates memory and tools, then streams text and speech back to the user.

System architecture diagram for Hermes Live Companion
System overview prepared for the OpenAI Build Week submission.
Bounded locally

Browser and services remain on 127.0.0.1.

Isolated worker

A dedicated worker preserves the regular Hermes environment.

Visible control

Tool progress, approvals, stop, reset, and interruption stay observable.

Development method

Human-Governed Agent Development

The speed came from clear definitions, narrow phases, explicit checkpoints, and reversible changes—not from asking AI to build everything at once.

Plan-driven

Define before building

Experience, boundaries, non-goals, safety rules, and acceptance criteria were written first.

Phase-based

Prove one chain at a time

The smallest end-to-end path was validated before voice, vision, and interruption were layered in.

Checkpoints

Keep human decisions explicit

Direction, priority, risk approval, and release readiness remained human responsibilities.

Rollback-first

Make progress reversible

Isolation, pinned dependencies, Git checkpoints, and preservation of the existing environment reduced risk.

DefineImplementTestHuman verifyCommitNext phase

Build timeline

From one question to a public submission.

The work was completed across two days of fragmented time. The 8h 46m figure is active development time, not elapsed calendar time.

  1. 01

    Question and product concept

  2. 02

    Plan and safety boundaries

  3. 03

    Text and session foundation

  4. 04

    Voice and interruption

  5. 05

    Vision and approvals

  6. 06

    Packaging and security review

  7. 07

    Demo and Build Week submission

Product evidence

The interface makes agent activity inspectable.

Conversation, camera analysis, microphone status, runtime settings, and interruption controls remain visible in one operating surface.

  • Voice, vision, and memory in one session
  • Visible runtime and model status
  • Human-accessible controls throughout
Watch the working demo ↗
Hermes Live Companion interface with conversation, camera view, and voice controls

From MVP to delivery

Shipping is part of the product.

After the MVP worked, the project still needed to become safe, legible, and verifiable outside its original machine.

01

Clean and isolate the public package

02

Test, scan, document, and rebuild

03

Prepare the demo and project evidence

04

Submit to OpenAI Build Week through Devpost

View the public hackathon project ↗

The larger lesson

AI amplifies execution. Human value moves upstream: finding the problem, defining the system, controlling risk, and deciding when the result is ready for the real world.