VEKTOR Memory

https://dev.to/vektor_memory_43f51a32376/vektor-openai-agents-sdk-production-memory-in-three-lines-59p6

Node.js/TypeScript-native memory layer. SQLite + local Transformers.js embeddings (~80MB model via WebAssembly). AUDN loop (Add/Update/Delete/None) resolves contradictions before write rather than at retrieval — read-after-write consistency.

At a glance

Type
Local-SQLite + AUDN-loop + TypeScript-native
Tier
T2
Created
searched not found
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
$9/month subscription OR one-time $159 commercial license (activates on up to 3 machines)
Funding
searched not found

Taxonomy

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

When to use

Optimised for: TypeScript-native developer experience

Anti-fit: not for Python-only stacks

Pros & cons

Pros

Vector-native memory framework with built-in embedding pipeline; minimal setup for new agents.

Cons

Vector-only — no graph or KV layer; smaller ecosystem.

Claims & capabilities

Only production-grade memory library targeting Node.js agents specifically with no cloud dependency. Python port on roadmap.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Local-only (Node.js; Transformers.js via WebAssembly; SQLite; no cloud infrastructure)
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
not documented publicly
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.