Voice Agent - Reachy Mini

pip install reachy-mini honcho-ai openai python-dotenv numpy scipy mediapipe face-recognition

export OPENAI_API_KEY=your_openai_key
export HONCHO_API_KEY=your_honcho_key  # get at app.honcho.dev

Reachy Mini (camera, mic, speaker)
        ↓
OpenAI Realtime API (voice + tools)
        ↓
Honcho (memory + reasoning per user)

from honcho import Honcho
from honcho.api_types import PeerConfig

honcho = Honcho(api_key=api_key, workspace_id="reachy-mini")

# Robot peer - stores messages but isn't reasoned about
robot_peer = await honcho.aio.peer(
    "reachy",
    configuration=PeerConfig(observe_me=False),
)

# User peers - Honcho reasons about their preferences and history
user_peer = await honcho.aio.peer(user_id)
session = await honcho.aio.session(f"chat-{user_id}")

# Queue messages async - doesn't block audio playback
await session.aio.add_messages(user_peer.message(transcript))
await session.aio.add_messages(robot_peer.message(response))

# Recall - ask Honcho's dialectic API (returns in ~200-500ms)
result = await user_peer.aio.chat(
    "What do I know about this user?",
    session=session,
    reasoning_level="medium"
)

# Create conclusion - save a fact
await user_peer.conclusions_of(user_id).aio.create([
    {"content": "Their name is Alice"}
])

# Get briefing when user is recognized
briefing = await user_peer.aio.chat(
    "What should I know about this user? Name, interests, recent topics.",
    session=session,
    reasoning_level="low"
)

SYSTEM_PROMPT = """You are Reachy, a friendly robot. Keep responses concise.

You have a recall tool for memory. ALWAYS use it before claiming you don't
know something about the user. Never say "Nice to meet you" if you've met before."""

uv run python main.py