ilia/atlas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
atlas/home-voice-agent/memory/README.md
ilia bdbf09a9ac feat: Implement voice I/O services (TICKET-006, TICKET-010, TICKET-014) 
✅ TICKET-006: Wake-word Detection Service
- Implemented wake-word detection using openWakeWord
- HTTP/WebSocket server on port 8002
- Real-time detection with configurable threshold
- Event emission for ASR integration
- Location: home-voice-agent/wake-word/

✅ TICKET-010: ASR Service
- Implemented ASR using faster-whisper
- HTTP endpoint for file transcription
- WebSocket endpoint for streaming transcription
- Support for multiple audio formats
- Auto language detection
- GPU acceleration support
- Location: home-voice-agent/asr/

✅ TICKET-014: TTS Service
- Implemented TTS using Piper
- HTTP endpoint for text-to-speech synthesis
- Low-latency processing (< 500ms)
- Multiple voice support
- WAV audio output
- Location: home-voice-agent/tts/

✅ TICKET-047: Updated Hardware Purchases
- Marked Pi5 kit, SSD, microphone, and speakers as purchased
- Updated progress log with purchase status

📚 Documentation:
- Added VOICE_SERVICES_README.md with complete testing guide
- Each service includes README.md with usage instructions
- All services ready for Pi5 deployment

🧪 Testing:
- Created test files for each service
- All imports validated
- FastAPI apps created successfully
- Code passes syntax validation

🚀 Ready for:
- Pi5 deployment
- End-to-end voice flow testing
- Integration with MCP server

Files Added:
- wake-word/detector.py
- wake-word/server.py
- wake-word/requirements.txt
- wake-word/README.md
- wake-word/test_detector.py
- asr/service.py
- asr/server.py
- asr/requirements.txt
- asr/README.md
- asr/test_service.py
- tts/service.py
- tts/server.py
- tts/requirements.txt
- tts/README.md
- tts/test_service.py
- VOICE_SERVICES_README.md

Files Modified:
- tickets/done/TICKET-047_hardware-purchases.md

Files Moved:
- tickets/backlog/TICKET-006_prototype-wake-word-node.md → tickets/done/
- tickets/backlog/TICKET-010_streaming-asr-service.md → tickets/done/
- tickets/backlog/TICKET-014_tts-service.md → tickets/done/
2026-01-12 22:22:38 -05:00

2.6 KiB
Raw Blame History

Long-Term Memory System

Stores persistent facts about the user, their preferences, routines, and important information.

Features

  • Persistent Storage: SQLite database for long-term storage
  • Categories: Personal, family, preferences, routines, facts
  • Confidence Scoring: Track certainty of each fact
  • Source Tracking: Know where facts came from (explicit, inferred, confirmed)
  • Fast Retrieval: Indexed lookups and search
  • Prompt Integration: Format memory for LLM prompts

Usage

from memory.manager import get_memory_manager
from memory.schema import MemoryCategory, MemorySource

manager = get_memory_manager()

# Store explicit fact
manager.store_fact(
    category=MemoryCategory.PREFERENCES,
    key="favorite_color",
    value="blue",
    confidence=1.0,
    source=MemorySource.EXPLICIT
)

# Store inferred fact
manager.store_fact(
    category=MemoryCategory.ROUTINES,
    key="morning_routine",
    value="coffee at 7am",
    confidence=0.8,
    source=MemorySource.INFERRED,
    context="Mentioned in conversation on 2024-01-06"
)

# Get fact
fact = manager.get_fact(MemoryCategory.PREFERENCES, "favorite_color")
if fact:
    print(f"Favorite color: {fact.value}")

# Search facts
facts = manager.search_facts("coffee", category=MemoryCategory.ROUTINES)

# Format for LLM prompt
memory_text = manager.format_for_prompt()
# Use in system prompt: "## User Memory\n{memory_text}"

Categories

  • PERSONAL: Personal facts (name, age, location)
  • FAMILY: Family member information
  • PREFERENCES: User preferences (favorite foods, colors)
  • ROUTINES: Daily/weekly routines
  • FACTS: General facts about the user

Memory Write Policy

Explicit Facts (confidence: 1.0)

  • User explicitly states: "My favorite color is blue"
  • Source: MemorySource.EXPLICIT

Inferred Facts (confidence: 0.7-0.9)

  • Inferred from conversation: "I always have coffee at 7am"
  • Source: MemorySource.INFERRED

Confirmed Facts (confidence: 0.9-1.0)

  • User confirms inferred fact
  • Source: MemorySource.CONFIRMED

Integration with LLM

Memory is formatted and injected into system prompts:

memory_text = manager.format_for_prompt(limit=20)
system_prompt = f"""
You are a helpful assistant.

## User Memory

{memory_text}

Use this information to provide personalized responses.
"""

Storage

  • Database: data/memory.db (SQLite)
  • Schema: See memory/schema.py
  • Indexes: Category, key, last_accessed for fast queries

Future Enhancements

  • Semantic search using embeddings
  • Memory summarization
  • Confidence decay over time
  • Conflict resolution for conflicting facts
  • Memory validation and cleanup