amemor-ai®
Developers & builders

Memory & governance infra for your AI agents

Open-core. pip install, self-host, and give your agents durable memory and an audit trail.

🔒 Self-hosted, no lock-in; anonymisation keeps PII out of prompts you don't control.

pip install uaml-memory

Open engine, MCP tools, clean Python API.

Recall that scales

Sharded knowledge, FTS + vector, Context Broker.

Anonymise before egress

Automatic PII cipher in/out of cloud models.

Multi-agent & MCP

Orchestrate agents over a mesh with gated tool calls.

← Back to home

Under the hood

The technical capabilities behind this — from the live feature inventory.

Open-core engine

pip install uaml-memory — OSS engine, MCP tools, a clean Python API. Studio is always free.

Recall that scales

16 live shards (141k rows) + a team shard + fan-out search; Neo4j graph + 4096-dim embeddings + HNSW semantic search (45.5k gold nodes, similarity/recency/importance blend).

Temporal validity & supersession

Point-in-time queries; memory_latest_for_topic walks the chain to the current canonical answer — vector stores don't do this.

Open Knowledge Format interop

Full producer & consumer of Google's OKF v0.1 (okf_import / okf_export), lossless round-trip even with Google's sample bundles.

Per-subagent model profiles + BYOK

Give each spawned subagent its own model profile — cheap/fast for mechanical steps, top model for the hard ones — mixing local Ollama and cloud per task; one router (OpenRouter + Ollama + native SDKs) with automatic fallback, bring-your-own-key per provider.

Start free, scale when ready

Free engine on your own hardware. No credit card. Found­er pricing through 31 October 2026.

View pricing Back to home