Memoria (MatrixOrigin)

https://medium.com/@matrixorigin-database/benchmarking-memoria-on-longmemeval-strong-memory-retrieval-clear-reader-separation-ee6c89c75d76

Memory layer from MatrixOrigin. Strong-retrieval / clear-reader-separation design.

At a glance

Type
Retrieval-strong memory layer
Tier
T2
Created
searched not found
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
searched not found
Funding
searched not found

Taxonomy

storage
hybrid
retrieval
similarity
persistence
long-term
update
extraction
unit
fact
governance
inspectable
conflict
none

When to use

Optimised for: retrieval quality ("retrieval-strong")

Anti-fit: searched not found

Pros & cons

Pros

Backed by MatrixOrigin's HTAP DB engine — memory benefits from mature transactional substrate.

Cons

Tied to MatrixOrigin database; primarily Chinese-market positioning.

Claims & capabilities

Reports 88.78% overall on LongMemEval-S; near-perfect single-session recall; strong on multi-session reasoning, temporal reasoning, and knowledge updates.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Both (Memoria Cloud API + self-hosted MatrixOne DB)
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
not documented publicly
A2A
not supported
OpenTelemetry
not documented publicly

Similar systems

Other dedicated memory layers in the catalog, ranked by inbound references.

  • Mem0 T1

    Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.

  • Zep & Graphiti T1

    Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.

  • Cognee T1

    "Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.

  • Hindsight (Vectorize) T1

    Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.

  • Memvid T2

    Single-file memory layer (one .mv2 file). No DB, no server. Append-only sequence of immutable Smart Frames with timestamps + checksums. Native Rust core (rewritten from Python).

  • Supermemory T1

    Memory engine with API, app, browser extension, and MCP server. Extracts facts, tracks updates, resolves contradictions, auto-forgets expired info. Plugins for Claude Code, OpenCode, OpenClaw, Hermes.

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.