Skip to content
AgentsIndex

Vektor Memory

Verified owner

Local persistent agent memory with SQLite, MAGMA graph retrieval, and MCP tools.

Best for
VEKTOR is best for AI engineers who need fast, local persistent memory for agents.
GitHub stars
4

What we checked

Pages last read
Facts checked
1 fact

From 1 source, read 25 October 2026

AI answers
Too few read

58 buyer-question answers read, November 2026

At a glance

Tags
HIPAA, Local AI, No training on your data, Self-hosted

Code

Last push
17 September 2026

For developers

Works with
LangChain, OpenAI Agents SDK, Ollama, OpenRouter, Le Chat, Claude Desktop and 24 more

What is Vektor Memory?

Vektor Memory is a local-first persistent memory system for AI engineers and agent builders that stores context in SQLite and retrieves it through a self-organizing 4-layer MAGMA graph. It combines ONNX embeddings, BM25 keyword recall, cross-encoder reranking, REM Compression, and a developer SDK with MCP tools. It works across Claude Desktop, Cursor, VS Code, Windsurf, Claude Code, and LangChain. Plans start at $9/month for Slipstream and VEKTOR Slipstream.

What does Vektor Memory do?

VEKTOR handles persistent agent memory by storing context locally in SQLite and organizing it through a self-organizing 4-layer MAGMA graph. Its pipeline combines ONNX embeddings, BM25 keyword recall, and cross-encoder reranking so agents can retrieve relevant memories, resolve contradictions, and compress noise into signal during idle periods.

The system also exposes memory operations through a local API and MCP tools, so it can sit inside existing agent workflows rather than replacing them. At scale, VEKTOR is built for low-latency recall: the site cites 8ms average recall, under 50ms p95 latency, and 42× faster production performance versus cloud memory.

It keeps data local by default with zero egress and no telemetry, and the security pages describe local SQLite storage, locally computed embeddings, and no shared tenant infrastructure. The docs and downloads pages show it working across Claude Desktop, Cursor, VS Code, Windsurf, Claude Code, and LangChain, with customer names including Anthropic, OpenAI, and Google Play.

Why use Vektor Memory?

  • Local-first architecture keeps memory on your machine, which avoids cloud egress and third-party data exposure.
  • The 8ms average recall and under-50ms p95 latency make memory retrieval feel immediate in production workflows.
  • SQLite portability means the memory graph travels with the user instead of living in a vendor-controlled service.
  • The system combines retrieval, curation, and compression, so memory can improve over time instead of just growing larger.
  • Native MCP and SDK support let teams add persistent memory without rewriting their existing agent stack.
  • Security and compliance pages show zero telemetry, encrypted credentials, and no shared infrastructure.

Who is Vektor Memory for?

  • AI engineers who want persistent memory inside existing agent workflows.
  • Developer teams who need local-first storage with no cloud dependency.
  • Agent builders who want recall, graph context, and memory curation in one stack.
  • Teams shipping MCP-connected tools who need memory across editors and hosts.
  • Privacy-conscious product teams who need data to stay on their own machine.

What are Vektor Memory's key features?

Local-first vector memory

Stores memory in a local SQLite file with 100% local, zero-egress processing, keeping recall fast at 8ms average latency and avoiding cloud embedding costs.

self-organising 4-layer graph

Organizes memories across semantic, temporal, causal, and entity layers in a 4-layer memory architecture, improving retrieval quality and graph accuracy for complex context.

Spec-decoding retrieval

Uses spec-decoding retrieval to answer from memory with sub-50ms p95 latency, helping agents pull relevant context quickly during live workflows.

Zettelkasten-linked edges

Connects notes with Zettelkasten-style edges and a visual memory graph, making relationships easier to inspect across 4,200+ memories and 7,180 edges.

MAGMA graph engine

Runs the MAGMA 4-layer memory graph to build structured memory history, supporting 99.1% graph accuracy and cross-namespace recall for agent workflows.

REM Compression

Compresses conversational fragments through the REM cycle, removing 98% noise and achieving a 50:1 compression ratio to keep memory compact and usable.

AUDN curation

Uses the AUDN loop for autonomous update curation, continuously refining memory with 0.02% deviation per cycle and surfacing durable facts.

Developer SDK

What are Vektor Memory's use cases?

Persistent memory for AI engineers

AI engineers who want persistent memory inside existing agent workflows use Vektor Memory to keep recall available across sessions, using Local-first vector memory and Spec-decoding retrieval to surface the right context fast. They can also use the Developer SDK to wire memory into current tools without adding cloud dependency.

Local storage for developer teams

Developer teams that need local-first storage use Vektor Memory to keep agent state on the machine, using Local-first and Local-first SQLite to avoid cloud dependency and egress concerns. The self-organizing 4-layer graph helps them preserve structured context as projects grow.

Memory curation for agent builders

Agent builders who want recall, graph context, and memory curation in one stack use Vektor Memory to turn messy interactions into reusable knowledge, using AUDN curation and REM Compression to reduce noise. Zettelkasten-linked edges and graph-based memory help them reconnect related ideas later.

MCP memory across hosts

Teams shipping MCP-connected tools use Vektor Memory to keep memory consistent across editors and hosts, using MCP Config Sync and native adapter support to maintain the same context in Claude Desktop, Cursor, VS Code, and other connected environments. That means fewer dropped threads and faster handoffs.

How does Vektor Memory work?

  1. Connect your first data source or host through the Developer SDK, MCP Config Sync, or a native adapter, then start writing memories into Local-first vector memory on your machine.
  2. Let the self-organizing 4-layer graph organize incoming notes into the Semantic layer, Temporal layer, Causal layer, and Entity layer so context stays structured as it grows.
  3. Use Spec-decoding retrieval and Smart recall to ask for prior decisions, related entities, or session history, then inspect results in the Visual memory graph or Persistent memory terminal.
  4. Curate noisy entries with AUDN curation and REM Compression, then keep important threads alive with Flagged notes and reminders and AI-surfaced reconnections.
  5. Keep the system running across sessions with Memory checkpointing and Data export & portability, so teams can resume work, move data, and preserve local control.

How much does Vektor Memory cost?

Prices excluding tax, as Vektor Memory publishes them.

  • Slipstream

    From $9/mo

    • Single SQLite file, your machine
    • No cloud. No per-call fees. No API key for memory.
    • All future Slipstream updates included
  • VEKTOR Slipstream

    From $9/mo

    • All future updates included
    • Commercial licence · production use

Where these prices come from

vektormemory.com/product, checked

What we checked on Vektor Memory

YesPartlyNo

What it costs to startYes

What the price counts

Flat monthly subscription rather than usage billing: four fixed tiers from $9 to $99+ a month, each buying a set number of license keys (Solo one key for up to three devices, Team five, Studio ten, Enterprise twenty-five), so the price scales in seat bands and not by memory operations. The vendor states there are no embedding charges or hidden fees, though it notes separately that your own model provider's embedding costs sit on top.

First week free on Solo · $9/month after · Cancel any time · Commercial licence · Continuous updates · No embedding charges · No telemetry · No…

vektormemory.com/productChecked

How you build with itNo public code found

Open source

Its GitHub repository holds issues or documents, no code

Unified Workspace with Multi Agent memory - Slipstream - 5-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, GUI, DXT-MCP Cloak…

github.com/Vektor-Memory/Vektor-memoryChecked by us,

Questions about Vektor Memory

How much does Vektor Memory cost?
Vektor Memory costs $9 a month. From vektormemory.com/product#pricing, checked 25 October 2026.
Does Vektor Memory have an API or an MCP server?
Vektor Memory has an API.
Is Vektor Memory open source, and can you host it yourself?
Vektor Memory is open source. You can host Vektor Memory yourself.
What have we checked on Vektor Memory?
1 fact, under one heading: What it costs to start.
How do we check Vektor Memory?
We hold 1 fact on Vektor Memory, quoted from 1 page. Facts and price last checked 25 October 2026. Last change found 13 June 2026.

How we check every listing

Sources and changes

Last full check

Repository

Stars
4
Last push
17 September 2026

Vektor Memory price history

The cheapest paid plan has cost $9 a month since 11 May 2026, on all 3 readings.

PricePlanFirst seenLast seenReadingsSource
$9 a month26 October 20263 November 20262Pricing page, read 26 October 2026

From 3 readings of Vektor Memory's pricing page: 2 Internet Archive copies from 11 May 2026 and one of our own checks, on 26 October 2026. A date is when we read the page, not when the price changed.

Similar in Agent tools and integrations

See all in Agent tools and integrations

From our research

All research

Claimed by the Vektor Memory team.

We check its facts against the Vektor Memory site.Facts checked 15 November 2026

Report an error if a fact is wrong.