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

# Release 3.13

> Release 3.13 adds Claude Haiku 4.5 to the AI Router and introduces a verified n8n integration for workflow automation with 1,000+ apps.

<Update label="Claude Haiku 4.5 now Available" description="v3.13.0">
  Claude Haiku 4.5, Anthropic's latest AI Model is now available in the [AI Router](/docs/model-garden/overview).
</Update>

<Update label="n8n Integration now Available" description="v3.13.0">
  Orq.ai is now available as a verified integration on [n8n](https://n8n.io), the workflow automation platform trusted by technical teams worldwide. Connect your **Orq.ai** [Deployments](/docs/deployments/overview) with over 1,000 apps, services, and data sources to build AI-powered automations.

  ## What's New

  **Verified n8n Node**

  Build sophisticated workflow automations by connecting Orq.ai directly into your n8n workflows. The integration is built and maintained by Orq.ai and verified by n8n, ensuring reliability and security.

  **Key Capabilities:**

  * **Seamless Deployment Integration**: Invoke any Orq [Deployment](/docs/deployments/overview) directly from your n8n workflows
  * **Knowledge Base Search**: Search through [Knowledge Bases](/docs/knowledge/overview) and retrieve relevant content.
  * **1,000+ App Connections**: Connect your LLM applications with popular tools including databases, APIs, CRMs, messaging platforms, and more.

  ## Use Cases

  * Automate content generation workflows across multiple platforms.
  * Build intelligent data processing pipelines with RAG-enabled Deployments.
  * Orchestrate complex multi-step AI workflows with conditional logic.
  * Integrate LLM outputs with CRMs, databases, and notification systems.

  ## Getting Started

  1. Install the Orq Deployment node in your n8n instance (requires owner permissions).
  2. Configure authentication with your Orq.ai [API Key](/docs/administer/api-keys).
  3. Add a Orq Deployment node or Knowledge Base node to your n8n workflow.
  4. Connect with other n8n nodes to build complete automations

  <Note>
    Learn more about the integration on [the n8n Integration Page](https://n8n.io/integrations/orq-deployment/)
  </Note>

  <Note>
    Read the [Github Repository for the n8n node](https://github.com/orq-ai/orqkit/tree/main/packages/n8n-nodes-orq).
  </Note>
</Update>

<Update label="Tools API" description="v3.13.0">
  We've introduced a new [**Tools API**](/docs/tools/overview), making it easier to integrate and manage custom tools programmatically.

  #### What’s new

  * **HTTP Tools** – External API integrations with templating & authentication.
  * URL templates with `{{parameter}}` substitution
  * Support for HTTP methods (GET, POST, PUT, DELETE, etc.)
  * Custom headers (including authentication)
  * Parameter definitions with types, descriptions, default values
  * Control over which parameters are visible to the LLM (`send_to_model`)
  * **Function Tools** – Define tool schemas via API (same as in the UI).
  * OpenAPI-style schemas for custom business logic
  * Function name, description, parameters
  * Strict parameter validation
  * Optional manual approval before execution
  * **Code Tools (Python)** – Run custom Python code in a secure sandbox.
  * Define parameters in JSON Schema
  * Access `params` variable for LLM-provided inputs
  * Supports return value processing & error handling
  * Fully isolated execution environment
</Update>

<Update label="Memory Stores API" description="v3.13.0">
  We've just introduced our new [**Memory Stores API**](/reference/memory-stores/list-memory-stores), enabling persistent, entity-based memory across conversations so your agents can recall context and build more intelligent interactions.

  ## Key Features

  ### Persistent & Isolated Memory

  * **Entity-based Isolation**: Use `entity_id` to scope memory per user, session, or organization.
  * **Multi-Tenant Support**: Secure separation of data across entities.

  ### Structured Memory Storage

  * [**Memory Stores**](/docs/agents/agent-api#memory-management): Named containers for storing different types of contextual data.
  * **Built-in Tools**: Automatic read, write, and query operations for seamless integration.

  ### Agent Memory Workflow

  * **Discover First**: Agents must use `retrieve_memory_stores` to discover available memory before interacting with them.
  * **Query Smartly**: Once discovered, use `query_memory_store` to fetch relevant information before responding.
  * **System Prompt Guidance**: Example:

  > "Use retrieve\_memory\_stores to see what memory stores are available, then use query\_memory\_store to search for relevant information before responding."

  ### Streaming & Entity Tracking

  * **Streaming Support**: Use `entity_id` for real-time memory tracking during ongoing conversations.
</Update>

<Update label="Improved Experiments" description="v3.13.0">
  <img src="https://mintcdn.com/orqai/1clR3dRdy0GtV4iZ/images/ec535b410ae98eeb9158776e574bfe1f47b06489ed6d63dc91c8390127838f2b-Screenshot_2025-10-03_at_15.23.21.png?fit=max&auto=format&n=1clR3dRdy0GtV4iZ&q=85&s=ef7a4f8903fc16d25ad5d6f753165c98" alt="Experiment duplication dialog allowing reuse of an existing experiment configuration on a new dataset." width="1430" height="640" data-path="images/ec535b410ae98eeb9158776e574bfe1f47b06489ed6d63dc91c8390127838f2b-Screenshot_2025-10-03_at_15.23.21.png" />

  You can now **duplicate an existing experiment** and run it on a new dataset with the same configuration. This makes it easy to reuse setups and compare results across datasets without manually recreating settings.

  <Note>
    To learn more about setting up and running experiments, see [Experiments](/docs/experiments/overview)
  </Note>
</Update>

<Update label="Claude Sonnet 4.5 now Available" description="v3.13.0">
  Claude Sonnet 4.5, Anthropic's latest AI Model is now available in the [AI Router](/docs/model-garden/overview).

  <img src="https://mintcdn.com/orqai/W8gaV2S7D8ydczdf/images/95ff9863cb22fe00fc98eb49a6c0837a4ec53996c6d4dabd6b80f8210c0cc16e-image.png?fit=max&auto=format&n=W8gaV2S7D8ydczdf&q=85&s=a30017e9f0716e57adf3073e79614f14" alt="Claude Sonnet 4.5 model now available in the AI Router model selection." width="772" height="378" data-path="images/95ff9863cb22fe00fc98eb49a6c0837a4ec53996c6d4dabd6b80f8210c0cc16e-image.png" />
</Update>

<Update label="Agents - Now in BETA" description="v3.13.0">
  We've just delivered our new **Agents Beta API** to build single and multi-agent systems, making it easier than ever to build and run powerful agents.

  ## Key Features

  ### Built on Modern Standards

  [**Using A2A Protocol**](https://a2a-protocol.org/latest/) for reliable multi-agent coordination

  ### Intelligent Memory & Context

  * [**Memory Stores**](/docs/agents/agent-api#memory-management): Persistent context across conversations with entity-based isolation.
  * [**Knowledge Base**](/docs/knowledge/overview): Ground responses in your data with dynamic discovery and querying

  ### Multi-Modal Processing

  * **File Processing** - Handle images and PDFs with support varying per given model
  * **Search & Web Scraping** - Bring in real-time insights with built-in search and scraping tools

  ### Flexible Tool Ecosystem

  * **HTTP Tools** - Seamless external API integrations with parameter templating and authentication
  * **Function Tools** - Custom business logic and access to internal systems with OpenAI function calling schema validation
  * **Code Tools** - Custom Python logic and transformations in secure sandbox environments

  ### Architecture

  * **Multi-Agent Systems** - Build sophisticated hierarchies with specialized sub-agents and intelligent delegation.
  * **Synchronous and streaming endpoints** for different use cases.

  Orq handles memory, orchestration, and execution so you can focus on your agent’s role and behavior.

  ## Example

  Initiate an Agent call with a single call to the `/v2/agents/run` API as follow:

  ```bash cURL theme={"theme":{"light":"github-light","dark":"github-dark"}}
  curl --location 'https://api.orq.ai/v2/agents/stream-run' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: $ORQ_API_KEY' \
  --data '{
  "key": "simple-agent-1",
  "role": "Assistant",
  "description": "A helpful assistant for general tasks",
  "instructions": "Be helpful and concise",
  "settings": {
  "max_iterations": 3,
  "max_execution_time": 300,
  "tools": [
  {
  "type": "current_date"
  }
  ]
  },
  "message": {
  "role": "user",
  "parts": [
  {
  "kind": "text",
  "text": "What'\''s today'\''s date and day of the week?"
  }
  ]
  },
  "model": "openai/gpt-4o",
  "path": "Default/agents",
  "memory_stores": [],
  "team_of_agents": []
  }'
  ```

  <Note>
    To learn more about agents, see [Agents](/docs/agents/overview) and browse through the advanced usages of our new API.
  </Note>
</Update>