MemHouseGoverned AI Memory
For AI Engineers, System Architects & Tech Leads

Stop building memory systems
from scratch.

MemHouse gives you a production-ready, highly concurrent memory backend and pgvector database in a single deployable container. Build stateless agents; we handle state, extraction, and retrieval.

Read Official Documentation

High-Concurrency Engine

Why MemHouse? Single-threaded memory pipelines can stall under lock contention. MemHouse uses BEAM process isolation for concurrency and fault containment; a reproducible 10,000-ingests/sec benchmark remains a published engineering target, not a released result.

Developer Web Console & CLI

Explore memory graphs visually, execute Mix tasks for operations, inspect raw JSON provenance payloads, and trigger re-indexations without restarting database nodes.

No Vendor Lock-In

Because MemHouse runs on standard PostgreSQL with pgvector, your memory state lives in relational tables. Export, dump, or query via standard SQL anytime.

Developer First Architecture

Stateless agents, stateful engine.

Keep your agent prompts lightweight. Pass observation payloads to MemHouse, and query governed memories through the HTTP API. SDK and packaged MCP examples are clearly marked when they are illustrative or coming soon.

agent_memory_example.py
# Python SDK coming soon. Use the shipped HTTP API today.
import requests

base_url = "https://memhouse.internal.company.com"
headers = {"Authorization": "Bearer YOUR_API_KEY"}

response = requests.post(
    f"{base_url}/api/v1/context",
    headers=headers,
    json={"scope_path": "/support/tickets/INV-9042", "budget_chars": 4000},
)
response.raise_for_status()
print(response.json()["data"])