Memori

https://github.com/MemoriLabs/Memori

Structured, persistent memory layer for AI agents. Open source.

At a glance

Type
Structured persistent memory layer
Tier
T2
Created
2025-07
Latest release
v3.3.3 2026-05-05
License
Apache-2.0
Pricing
Free + paid (Memori Cloud; tiered plans for builders / growing / production teams)
Funding
$3.7M Seed (4 investors; round closed May 2024)

Taxonomy

storage
relational
retrieval
similarity
persistence
cross-session
update
extraction
unit
fact
governance
inspectable
conflict
append

When to use

Optimised for: structured persistence + simplicity

Anti-fit: no anti-fit explicitly stated

Pros & cons

Pros

OSS dual-mode model (conscious + autonomous ingestion) lets developers control memory decisions explicitly.

Cons

Smaller community than Mem0/Letta; documentation is uneven.

Claims & capabilities

Apache-2.0; structured persistent memory layer (relational + vector hybrid); 14.1k GitHub stars; +175/mo; v3.3.3 released 2026-05-05; dual-mode (conscious + autonomous ingestion); $3.7M seed (May 2024); founders Harish Mukhami (CEO) and Michael Montero (CTO) NYC

Technical surface

API surface
SDK: Python (memori.enable() one-liner; integrates LiteLLM, OpenAI, Anthropic)
Backend storage
SQL (SQLite/Postgres/MySQL)
Deployment
Both (Memori Cloud zero-config + self-hosted OSS)
Embedding model
multiple supported
Multi-tenancy
not applicable — library; multi-tenancy is the embedding application's concern
MCP
community port — third-party MCP wrappers
A2A
not documented publicly
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.