# Frameworks

## OpenClaw

Modular agent runtime with built-in memory, tools, and multi-channel support.

### Configuration reference

**Identity**

| Field | Required | Notes         |
| ----- | -------- | ------------- |
| Name  | ✅        | Display name  |
| Bio   | ✅        | Max 500 chars |

**Personality**

| Field                   | Description                                      |
| ----------------------- | ------------------------------------------------ |
| Additional Instructions | System directives appended after core config     |
| Seed Knowledge          | PDF/TXT files injected into memory at first boot |

**Thinking Level**

| Level  | Behavior                         |
| ------ | -------------------------------- |
| Off    | Single-pass — fastest            |
| Low    | Light planning                   |
| Medium | Moderate reasoning (recommended) |
| High   | Deep reasoning                   |

**Included Capabilities**

| Capability          | Description                   |
| ------------------- | ----------------------------- |
| Web Search          | Real-time web search          |
| Web Fetch           | Read content from any URL     |
| Image Understanding | Analyze images from users     |
| File Access         | Read/write files in workspace |

### Built-in tools

**System**

| Tool             | Description                         |
| ---------------- | ----------------------------------- |
| `character-cfg`  | Agent's core configuration          |
| `agents`         | Lists all agents in workspace       |
| `knowledge-base` | Injects knowledge base into context |
| `SCULPT_TO`      | Formats output to structured lists  |

**Agent-managed**

| Tool           | Description                     |
| -------------- | ------------------------------- |
| `MEMORIZE`     | Store in long-term memory       |
| `THINKING`     | Internal reasoning step         |
| `CONSULT_AI`   | Delegate to sub-process         |
| `TOOL_CALL`    | Interact with external entities |
| `MULTITASK`    | Run parallel tasks              |
| `PLAN_ACTIONS` | Update action queue             |
| `memory`       | Read from memory store          |


---

# 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.guayaba.run/frameworks.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.