VEKTOR Memory
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.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 34 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Local-SQLite + AUDN-loop + TypeScript-native vendor fix
- Tier
- T2
- Section
- Dedicated memory layers
- Created
- searched not found fix
- Latest release
- v1.7.8 Preview (2026-07-16) repo fix
- License
- proprietary (commercial licence) repo fix
- Pricing
- Solo $9/mo (3 licences); Team $35/mo (5); Studio $59/mo (10); Enterprise $99/mo (25) repo fix
- Funding
- searched not found fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial repo fix
- Protocols
- mcp-server vendor fix
Memory 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
- yes — bundled MCP server (npx vektor mcp) with 50+ tools; Claude Code/Desktop integration
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Alternatives to VEKTOR Memory → live options ranked by shared design, licence, hosting and MCP support
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.
- Letta / MemGPT T1
Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompts over time.
- Memori T2
Structured, persistent memory layer for AI agents. Open source.
Sources (33 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Local-SQLite + AUDN-loop + TypeScript-native vendor
- What it does & what's distinct Node.js/TypeScript-native memory layer. SQLite + local Transformers.js embeddings (~80MB… vendor
- Claims / benefits Only production-grade memory library targeting Node.js agents specifically with no cloud… vendor
- Modalities text vendor
- Latest release v1.7.8 Preview (2026-07-16) repo
- License proprietary (commercial licence) repo
- GitHub Vektor-Memory/Vektor-memory — ~5 stars, latest changelog 2026-07 repo
- Customers / scale unknown ppl No identifiable standalone memory-layer startup found vendor
- Pricing Solo $9/mo (3 licences); Team $35/mo (5); Studio $59/mo (10); Enterprise $99/mo (25) repo
- Compliance not applicable — local-only (no cloud; data stays on user's server) vendor
- Deployment Local-only (Node.js; Transformers.js via WebAssembly; SQLite; no cloud infrastructure) vendor
- Memory volume / scale no scale claim vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites vendor
- MCP support yes — bundled MCP server (npx vektor mcp) with 50+ tools; Claude Code/Desktop integration repo
- Integration count 0 vendor
- Orchestration single-agent vendor
- Programmatic control full CRUD via Node/TS lib vendor
- Pricing specifics per-seat subscription $9/mo OR one-time $159 commercial license (3 machines) vendor
- Validated verticals Node.js/TypeScript agent developers repo
- Time to running <10min (npm install, local SQLite) repo
- Anti-fit not for Python-only stacks repo
- Optimised for TypeScript-native developer experience repo
- Adjacent infrastructure BYO LLM; SQLite local repo
- Pros Vector-native memory framework with built-in embedding pipeline; minimal setup for new a… vendor
- Cons Vector-only — no graph or KV layer; smaller ecosystem. vendor
- Project & sources DEV writeup vendor
- architecture-deployment-locus local vendor
- licensing-bucket commercial repo
- positioning-platform-vs-product both vendor
- taxonomy-three-layer-rollup agent-infra repo
- protocol-support mcp-server vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-22
- License “not applicable — not OSS” → “proprietary (commercial licence)” source
- Latest release “not applicable — not OSS” → “v1.7.8 Preview (2026-07-16)” source
- Pricing “$9/month subscription OR one-time $159 commercial license (activates on up to 3 machines)” → “Solo $9/mo (3 licences); Team $35/mo (5); Studio $59/mo (10); Enterprise $99/mo (25)” source
- MCP support first recorded as “yes — bundled MCP server (npx vektor mcp) with 50+ tools; Claude Code/Desktop integration” source