# Toolhouse

[**Toolhouse**](https://app.toolhouse.ai) is a Backend-as-a-Service (BaaS) to build, run, and manage AI agents. Toolhouse simplifies the process of building agents in a local environment and running them in production. 

With Toolhouse, you define agents as code and deploy them as APIs using a single command. Toolhouse agents are automatically connected to the Toolhouse MCP Server; it gives agents access to RAG, memory, code execution, browser use, and all the functionality agents need to perform actions. You can add MCP Servers and even define custom code that the agent can use to perform actions not covered by public MCP Servers.

Toolhouse has built-in eval, prompt optimization, and agentic orchestration.

## Features <a href="#features" id="features"></a>

### Agentic Backend-as-a-Service <a href="#tool-management-platform" id="tool-management-platform"></a>

Toolhouse allows you to define agents and deploy them as APIs. Our backend integrates curated MCP servers, RAG, memory, and all the other tools you need to ship useful agents. Our globally distributed runtime is built for high availability and ensures consistent performance.

{% content-ref url="agent-workers/running-agents-asynchronously" %}
[running-agents-asynchronously](https://docs.toolhouse.ai/toolhouse/agent-workers/running-agents-asynchronously)
{% endcontent-ref %}

### Local Development

`th` is the Toolhouse CLI. It allows you to create, run, and manage agents directly from your favorite environment. You can integrate `th` in your CI/CD pipeline to test and deploy agents with the rest of your code.

{% content-ref url="quick-start-for-developers-cli" %}
[quick-start-for-developers-cli](https://docs.toolhouse.ai/toolhouse/quick-start-for-developers-cli)
{% endcontent-ref %}

### Schedules

Schedules are Toolhouse's cron service. You can schedule agents to run a specific intervals using cron expressions.

{% content-ref url="agent-workers/schedule-autonomous-runs" %}
[schedule-autonomous-runs](https://docs.toolhouse.ai/toolhouse/agent-workers/schedule-autonomous-runs)
{% endcontent-ref %}

### **Observability**

You can inspect each agent run. Agent Logs show you the entire execution lifecycle of each agent you run. For a deeper drill down, you can use Execution logs to check the MCP servers called by your agents.

{% content-ref url="execution-logs" %}
[execution-logs](https://docs.toolhouse.ai/toolhouse/execution-logs)
{% endcontent-ref %}

### Toolhouse SDK <a href="#toolhouse-sdk" id="toolhouse-sdk"></a>

The Toolhouse SDK allows you to run Toolhouse in your existing codebase. You can use the SDK if you want to use your own custom agents. The SDK integrates with Vercel AI and LlamaIndex.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.toolhouse.ai/toolhouse/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.