mastra-ai/mastra · error · Error

Subconscious semantic knowledge requires a vector store. Pas

Error message

Subconscious semantic knowledge requires a vector store. Pass a `vector` option to Memory.

What it means

The experimental_subconscious feature stores and queries semantic knowledge, which fundamentally requires a vector store. The Memory constructor validates this eagerly: if `observationalMemory.experimental_subconscious` is set but no `vector` option was provided, construction fails with this error.

Source

Thrown at packages/memory/src/index.ts:516

    this.threadConfig = mergedConfig;

    // Validate retrieval vector config at construction time
    const omConfig = normalizeObservationalMemoryConfig(mergedConfig.observationalMemory);
    if (omConfig?.retrieval && typeof omConfig.retrieval === 'object' && omConfig.retrieval.vector) {
      if (!this.vector) {
        throw new Error(
          '`retrieval: { vector: true }` requires a vector store. Pass a `vector` option to your Memory instance.',
        );
      }
      if (!this.embedder) {
        throw new Error(
          '`retrieval: { vector: true }` requires an embedder. Pass an `embedder` option to your Memory instance.',
        );
      }
    }
    if (omConfig?.experimental_subconscious) {
      if (!this.vector) {
        throw new Error('Subconscious semantic knowledge requires a vector store. Pass a `vector` option to Memory.');
      }
      if (!this.embedder) {
        throw new Error('Subconscious semantic knowledge requires an embedder. Pass an `embedder` option to Memory.');
      }
    }
  }

  private async getKnowledgeStore(): Promise<KnowledgeStorage> {
    const store = await this.storage.getStore('knowledge');
    if (!store) {
      throw new Error(`Knowledge storage domain is not available on ${this.storage.constructor.name}`);
    }
    return store;
  }

  public async getKnowledgeSemanticIndex(): Promise<KnowledgeSemanticIndexCoordinator> {
    if (!this.vector || !this.embedder) {
      throw new Error('Subconscious semantic knowledge requires both a vector store and an embedder.');

View on GitHub (pinned to 75dd419e61)

Solutions

1. Add a `vector` option (e.g. LibSQLVector, PGVector) to the Memory constructor
2. Disable experimental_subconscious if semantic knowledge features are not required
3. Provision and connect a vector store dependency before enabling the feature

Example fix

// before
new Memory({ storage, options: { observationalMemory: { experimental_subconscious: new Subconscious({ model }) } } })
// after
new Memory({ storage, vector: new LibSQLVector({ connectionUrl: url }), options: { observationalMemory: { experimental_subconscious: new Subconscious({ model }) } } })

if (opts.options?.observationalMemory?.experimental_subconscious && !opts.vector) {
  throw new Error('experimental_subconscious requires a vector option on Memory');
}

try {
  const memory = new Memory(opts);
} catch (err) {
  if (err instanceof Error && err.message.includes('Subconscious semantic knowledge requires a vector store')) {
    // add vector store and rebuild
  } else throw err;
}

When it happens

Trigger: `new Memory({ options: { observationalMemory: { experimental_subconscious: new Subconscious({...}) } } })` without a `vector` option in Memory constructor options.

Common situations: Enabling the experimental subconscious in a memory configured only with relational storage; following older examples that predate the vector requirement; toggling the feature on in an environment without vector storage provisioned.

Related errors

• `retrieval: { vector: true }` requires a vector store. Pass
• Subconscious semantic knowledge requires an embedder. Pass a
• Subconscious ${phase} agent name is required.
• Duplicate Subconscious ${phase} agent: ${name}
• Subconscious maxSteps must be an integer between 1 and ${MAX

AI-assisted analysis of mastra-ai/mastra@75dd419e61 (2026-08-30). Data as JSON: /api/errors/1941195ab3a5ec42. Report an issue: GitHub.