brianchilders/memory-mcp
Local semantic memory + time-series intelligence layer for AI abilities. Runs on Ollama — no cloud, no API keys. Gives your AI a persistent, searchable, self-improving memory backed by SQLite.
Platform-specific configuration:
{
"mcpServers": {
"memory-mcp": {
"command": "npx",
"args": [
"-y",
"memory-mcp"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Unified semantic memory + time-series intelligence layer for OpenHome abilities.
Tier 1 — Semantic memory entities, memories, relations, vectors
Tier 1.5 — Episodic memory conversation sessions, turn-by-turn transcripts
Tier 2 — Time-series store readings (numeric/categorical/composite), rollups, schedule
Tier 3 — Pattern engine background task: promotes stable trends → Tier 1 memoriesThe pattern engine closes the loop: raw sensor data (Tier 2) automatically becomes searchable, natural-language memory ("Brian's temperature preference is consistently 68°F") that any ability can recall semantically (Tier 1).
| File | Purpose | |-------------------|------------------------------------------------------| | server.py | MCP server (stdio transport, all 11 tools) | | api.py | FastAPI HTTP wrapper + admin UI mount | | admin.py | Admin UI router (served at /admin) | | reembed.py | Utility to re-embed all memories when swapping models| | templates/admin | Jinja2 HTML templates for the admin UI | | integrations/ | Standalone tools that connect external systems to memory-mcp via HTTP |
| Doc | Contents | |---|---| | docs/overview.md | What it is, motivation, integration patterns (OpenHome, HA, MQTT, IoT) | | docs/installation.md | Requirements, step-by-step setup, first run, verification | | docs/quickstart.md | First entity, memory, reading — common operations with curl examples | | docs/api-reference.md | Full HTTP API — every endpoint, request/response shapes, examples | | docs/admin-ui.md | Admin dashboard guide, pages, reading confidence, prune, security | | docs/ai-backend.md | AI backend config, provider examples, model swap guide | | docs/pattern-engine.md | How detectors work, all 5 detec
Loading reviews...