> 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/prime-agent.md).

# Prime Agent

Bring a live **Prime Intellect Prime Agent** session into the DKG Node UI so you can work with it alongside your node's projects and connected agents. The adapter handles setup, discovery, authenticated transport, and streaming chat.

At the 10.0.23 baseline, this connection supplies chat transport. Reading or contributing DKG knowledge requires a separate supported memory-tool connection or an explicit node client; automatic primary-memory integration and a model-facing DKG Python skill are not supplied by this bridge.

Prerequisites: Prime Agent installed and usable, an initialized and running DKG node, and its local auth token. Prime Agent setup does not offer the same node/bootstrap flags as Hermes or OpenClaw.

```bash
# Only for a fresh DKG node:
dkg init --role edge --network testnet
dkg start

# Connect the installed Prime Agent runtime:
dkg prime-agent setup
dkg prime-agent verify
dkg prime-agent status
```

Start or reload a Prime Agent session so the installed extension runs. Open the DKG Node UI's connected-agents panel and connect Prime Agent. An installed adapter with no live session is an idle state, not a successful conversation connection.

## Verify the session

Send a message from the Node UI and confirm that it reaches the Prime Agent session you are using and streams a reply. With multiple live sessions, unaddressed messages route to the most recently active session. An explicit session ID overrides that routing; the current panel has no session picker.

Use `dkg prime-agent doctor` for diagnostics. The bridge binds loopback and requires a bridge token. A busy session can return `429`; let the existing turn finish before resending. Setup/reload problems and upstream runtime assumptions are documented in the [adapter reference](https://github.com/OriginTrail/dkg/blob/main/packages/adapter-prime-agent/README.md).

For the [memory quickstart](https://docs.origintrail.io/start-here/quickstart.md), use a separate supported MCP/framework memory connection or your own explicit node client. This bridge alone supplies chat transport.

## Disconnect or remove

```bash
dkg prime-agent disconnect
dkg prime-agent status
# If removing the integration entirely:
dkg prime-agent uninstall
```

Use `--agent-dir` and `--profile` consistently when you configured a non-default runtime directory/profile. Reconnect with `dkg prime-agent reconnect`. Setup preserves the original settings and uninstall removes the adapter's extension entry; graph data remains on the DKG node.


---

# 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/prime-agent.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.
