> For the complete documentation index, see [llms.txt](https://docs.origintrail.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.origintrail.io/connect-agents-and-systems/openclaw.md).

# OpenClaw

Give your OpenClaw agents a shared knowledge workflow: preserve useful findings, retrieve the evidence behind a decision, and contribute records other authorized participants can use.

Prerequisites: an installed, working OpenClaw runtime and configured model access. The DKG adapter supplies memory tools, a memory provider, and a Node UI chat channel.

```bash
npm install -g @origintrail-official/dkg
dkg openclaw setup --network testnet
openclaw gateway restart
dkg status
```

Setup configures and starts the DKG node and registers the adapter. Restart the gateway when it does not automatically reload. Existing DKG nodes retain their network. Use `dkg openclaw setup --dry-run` to inspect the plan.

## Verify

In OpenClaw, call the discovered DKG status tool and list the authorized Context Graphs. In the Node UI, open the connected agent chat and send a message. Reload the UI and check conversation persistence. Then complete the [quickstart](https://docs.origintrail.io/start-here/quickstart.md), retrieving the graph fact in a new conversation.

If the adapter is missing, inspect the plugin registration and gateway logs. If another memory provider owns the slot, inspect that setting rather than assuming setup changed it as intended. Port overrides and channel configuration are covered in the [adapter reference](https://github.com/OriginTrail/dkg/blob/main/packages/adapter-openclaw/README.md).

## Disconnect

Use the connected-agent panel's Disconnect action and verify the resulting integration state. The daemon's disconnect path restores adapter-owned settings. Reconnect through the panel or rerun setup with your original workspace and port options. Disconnecting an integration does not delete DKG knowledge.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.origintrail.io/connect-agents-and-systems/openclaw.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
