> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runflow.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Standalone Modules

> Standalone module exports

## Standalone Modules

```typescript theme={null}
// Single-agent (caller's own scope)
import { Memory, KV, Knowledge, RAG, LLM } from '@runflow-ai/sdk';

// Cross-agent (operate on another agent's data within the tenant)
import { Agents } from '@runflow-ai/sdk/agents';
import { Executions } from '@runflow-ai/sdk/executions';
import { Threads } from '@runflow-ai/sdk/threads';
import { MemoryAdmin } from '@runflow-ai/sdk/memory-admin';

// Reviews (production execution reviews — single or cross-agent)
import { Reviews } from '@runflow-ai/sdk/reviews';
```

## Single-agent modules

<CardGroup cols={2}>
  <Card title="Memory" icon="brain" href="/core-concepts/memory">
    Conversation history for the caller's own agent.
  </Card>

  <Card title="KV Store" icon="database" href="/core-concepts/kv-store">
    Persistent key-value storage with TTL, namespaces and pattern search.
  </Card>

  <Card title="Knowledge / RAG" icon="book" href="/core-concepts/knowledge-rag">
    Vector search and retrieval-augmented generation.
  </Card>

  <Card title="LLM" icon="microchip" href="/core-concepts/llm-standalone">
    Direct LLM calls outside the Agent abstraction.
  </Card>

  <Card title="Prompts" icon="message" href="/core-concepts/prompts">
    Versioned prompt templates.
  </Card>
</CardGroup>

## Cross-agent modules

The cross-agent SDK lets one agent operate on another agent's data within the same tenant. All operations are tenant-scoped — cross-tenant access returns 404 (existence never leaked). See [Cross-Agent SDK](/core-concepts/cross-agent) for the full guide.

<CardGroup cols={2}>
  <Card title="Agents" icon="paper-plane" href="/core-concepts/cross-agent#agents">
    Invoke other agents (`invoke` / `invokeAsync`), list, get.
  </Card>

  <Card title="Executions" icon="list-check" href="/core-concepts/cross-agent#executions">
    Read execution rows and paginated trace trees.
  </Card>

  <Card title="Threads" icon="comments" href="/core-concepts/cross-agent#threads">
    Walk grouped conversations. `getFullThread` returns thread + executions + traces in one call.
  </Card>

  <Card title="MemoryAdmin" icon="brain" href="/core-concepts/cross-agent#memory-admin">
    Manage another agent's memory: get / set / append / clear / search / list / summarize.
  </Card>
</CardGroup>

## Reviews

<CardGroup cols={2}>
  <Card title="Reviews" icon="clipboard-check" href="/core-concepts/cross-agent#reviews-full-lifecycle">
    Create, list, resolve, and dismiss production execution reviews. Used by reviewer agents and human reviewers in the portal.
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Cross-Agent SDK" icon="diagram-project" href="/core-concepts/cross-agent">
    Full guide to cross-agent primitives.
  </Card>

  <Card title="Observability" icon="chart-line" href="/api-reference/observability">
    View observability exports
  </Card>

  <Card title="API Client" icon="code" href="/api-reference/api-client">
    View API client exports
  </Card>
</CardGroup>