Tier 1    — Semantic memory       entities, memories, relations, vectors
Tier 1.5  — Episodic memory       conversation sessions, turn-by-turn transcripts
Tier 1.75 — Working memory        short-lived task scratchpads, promote-on-close
Tier 2    — Time-series store     readings (numeric/categorical/composite), rollups, schedule
Tier 3    — Pattern engine        background task: promotes stable trends → Tier 1 memories
Tier 4    — Prospective memory    intentions: trigger_text → action_text, checked on each turn
Tier 5    — Spatial memory        last-known object locations with confidence decay

# Install deps
pip install -r requirements.txt

# Pull embedding and LLM models (Ollama default)
ollama pull nomic-embed-text
ollama pull llama3.2

# Run MCP server (for OpenHome abilities)
python server.py

# Run HTTP API + admin UI (for HA webhooks, Node-RED, scripts)
python api.py          # listens on :8900
                       # admin UI at http://localhost:8900/admin/

# Default (local Ollama)
export MEMORY_AI_BASE_URL=http://localhost:11434/v1
export MEMORY_EMBED_MODEL=nomic-embed-text   # 768-dim
export MEMORY_LLM_MODEL=llama3.2

# OpenAI
export MEMORY_AI_BASE_URL=https://api.openai.com/v1
export MEMORY_AI_API_KEY=sk-...
export MEMORY_EMBED_MODEL=text-embedding-3-small
export MEMORY_EMBED_DIM=1536
export MEMORY_LLM_MODEL=gpt-4o-mini

# nomic-embed-text on a Raspberry Pi 4, LLM on a GPU machine
export MEMORY_AI_BASE_URL=http://pi4.local:11434/v1
export MEMORY_LLM_BASE_URL=http://gpu-host.local:11434/v1

export MEMORY_DECAY_HALFLIFE_DAYS=90          # global default
export MEMORY_DECAY_CATEGORY_HALFLIFE='{"preference": 180, "insight": 30}'
export MEMORY_LOCATION_DECAY_HALFLIFE_HOURS=24

export MEMORY_AI_TIMEOUT=30    # seconds; applies to both embed() and LLM calls

pip install -r requirements.txt
python -m pytest                     # full suite (722 tests, no Ollama needed)
python -m pytest tests/test_tools.py # just tool tests
python -m pytest tests/test_spatial.py # just spatial/location tests

{
  "mcpServers": {
    "memory": {
      "command": "python",
      "args": ["/path/to/memory-mcp/server.py"]
    }
  }
}

TIER 1
  entities          id, name*, type, meta(JSON), created, updated
  memories          id, entity_id, fact, category, confidence, source, created, updated,
                    last_accessed, access_count, superseded_by
  relations         id, entity_a, entity_b, rel_type, meta(JSON), created,
                    valid_from, valid_until
  memory_vectors    rowid=memories.id, embedding FLOAT[768]   ← sqlite-vec

TIER 1.5
  sessions          id, entity_id, started_at, ended_at, summary, meta
  session_turns     id, session_id, role, content, ts

TIER 1.75
  working_memory_tasks   id, name, entity_id, status, ttl_ts, created, closed_at
  working_memory_slots   id, task_id, key, value(JSON), created, updated

TIER 2
  readings          id, entity_id, metric, unit, value_type, value_num,
                    value_cat, value_json, source, ts
                    (composite readings also decomposed into {metric}.{key} child rows)
  reading_rollups   id, entity_id, metric, bucket_type, bucket_ts,
                    count, avg_num, min_num, max_num, p10_num, p90_num, mode_cat
  rollup_watermarks entity_id, metric, last_ts   ← incremental build tracking
  schedule_events   id, entity_id, title, start_ts, end_ts, recurrence, meta, created

TIER 3
  promoted_patterns id, entity_id, metric, pattern_key, memory_id, detected

TIER 5
  locations         id, entity_id, container_id, container_name, confidence,
                    last_confirmed_ts, active, source, note, created
                    (active=1 → current location; active=0 → archived sighting)

GET  /health                    liveness + row counts
GET  /entities                  list all entities
POST /remember                  store a memory
POST /recall                    semantic search (mode=vector|keyword|hybrid, recency_weight, min_confidence)
POST /get_context               relevance-filtered context snapshot
GET  /profile/{entity_name}     full profile
POST /relate                    create relationship
POST /forget                    delete memory or entity
POST /record                    ingest a reading
POST /record/bulk               ingest multiple readings at once
POST /query_stream              query time-series
POST /get_trends                trend summary
POST /schedule                  add schedule event
POST /cross_query               unified search
POST /prune                     delete readings older than RETENTION_DAYS
GET  /fading                    memories below a confidence threshold (most faded first)

POST /open_session              open a conversation session for an entity
POST /log_turn                  append a turn (user/assistant/system) to a session
POST /close_session             close a session with optional summary
GET  /get_session/{id}          retrieve full session transcript
POST /extract_and_remember      LLM-extract facts from text and store as memories

POST /wm/open                   open a working-memory task scope
POST /wm/set                    set a key/value slot in an open task
POST /wm/get                    get one slot or all slots from a task
GET  /wm/list                   list tasks (?status=open|closed|expired|all&entity_name=X)
GET  /wm/{task_id}              get all slots and metadata for a task
POST /wm/close                  close a task (promote=true bundles slots into long-term memory)

POST /locate                    store/update last-known location of an object
POST /find                      return last known location with confidence + age
POST /seen_at                   confirm object is still at a location; bumps confidence
GET  /location_history/{name}   full location trail for an object

POST /search_sessions           keyword search across session turn content (FTS5/BM25)
POST /get_context_budget        token-budget context snapshot (greedy fill, truncated flag)
POST /intend                    store a prospective intention (trigger_text → action_text)
POST /check_intentions          check if text triggers any active intentions (FTS5)
POST /dismiss_intention         deactivate an intention (soft-delete)
GET  /intentions                list intentions (?entity_name=X&active_only=true)

GET  /voices/unknown            list unenrolled provisional speaker entities
POST /voices/enroll             rename provisional entity to real person
POST /voices/merge              merge provisional entity into enrolled entity
POST /voices/update_print       update voiceprint embedding (running average)

GET  /graph                     vis.js entity relationship graph (SPA)
GET  /api/graph                 entity graph data { nodes, edges }

GET  /export/markdown           export all entities as Obsidian-compatible Markdown
GET  /export/markdown/{name}    export single entity as .md file download
POST /import/markdown           import entities from Markdown files (two-way sync)

GET  /admin/                    dashboard
GET  /admin/entities            entity list
GET  /admin/entity/{name}       entity detail
GET  /admin/readings            readings stream
POST /admin/prune               prune (HTMX-friendly HTML response)

# Pull full profile (memories + latest readings + schedule)
profile = await mem.tool_get_profile("Brian")
# → inject as <memory>...</memory> in system prompt

# Or cross-query to pull what's relevant to the current question
context = await mem.tool_cross_query("how is Brian feeling today?")

# configuration.yaml — rest_command
rest_command:
  push_temperature:
    url: http://localhost:8900/record
    method: POST
    content_type: application/json
    payload: >
      {"entity_name":"{{ room }}","metric":"temperature",
       "value":{{ temp }},"unit":"F","source":"ha","entity_type":"room"}

  push_presence:
    url: http://localhost:8900/record
    method: POST
    content_type: application/json
    payload: >
      {"entity_name":"{{ person }}","metric":"presence",
       "value":"{{ state }}","source":"ha"}

  push_mood:
    url: http://localhost:8900/record
    method: POST
    content_type: application/json
    payload: >
      {"entity_name":"{{ person }}","metric":"mood",
       "value":{"mood":"{{ mood }}","confidence":{{ conf }}},"source":"avatar_ability"}

# After detecting mood from conversation
await mem.tool_record(
    entity_name="Brian",
    metric="mood",
    value={"mood": "focused", "confidence": 0.87},
    source="avatar_ability",
)
# The pattern engine will promote this to a memory like:
# "Brian's mood is predominantly 'focused' (72% of days)"

result = await mem.tool_query_stream(
    entity_name="living_room",
    metric="temperature",
    granularity="day",
    start_ts=time.time() - 7 * 86400,
)

result = await mem.tool_cross_query("who in the house prefers a cooler environment?")
# Returns: matching memories (explicit preferences) + live temperature readings scored by relevance

# 1. Set the new model and dimension via env vars
export MEMORY_EMBED_MODEL=mxbai-embed-large
export MEMORY_EMBED_DIM=1024

# 2. Pull the new model
ollama pull mxbai-embed-large   # 1024-dim — richer but slower

# 3. Re-embed all memories (non-destructive — only rebuilds memory_vectors)
python reembed.py --dry-run     # preview
python reembed.py               # run it