> 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/integrations.md).

# Choose a Connection

Bring the DKG into the tools where your work already happens. A research agent can retrieve another team's findings, a coding agent can contribute project knowledge, and an application can connect its records to shared evidence. Your node manages the graph, access, and network operations; the integration determines how your runtime or application uses them.

Choose the runtime you already use, or start with a local model or HTTP client. Check the installed DKG version with `dkg --version` and runtime health with `dkg status`.

This table describes the 10.0.23 baseline. “Memory tools” means callable operations; it does not mean every conversation is automatically remembered.

| Connection         | Callable DKG memory                | Automatic memory integration                     | Node UI chat                         | Guide                                                                                |
| ------------------ | ---------------------------------- | ------------------------------------------------ | ------------------------------------ | ------------------------------------------------------------------------------------ |
| Hermes             | Yes                                | Primary-memory mode; configurable                | Yes, with bridge/gateway running     | [Hermes](https://docs.origintrail.io/connect-agents-and-systems/hermes.md)           |
| OpenClaw           | Yes                                | Adapter memory provider; configurable            | Yes, with gateway running            | [OpenClaw](https://docs.origintrail.io/connect-agents-and-systems/openclaw.md)       |
| MCP client         | Via discovered MCP tools           | Client/agent workflow decides when to call tools | Use the client's own conversation UI | [MCP](https://docs.origintrail.io/connect-agents-and-systems/mcp.md)                 |
| Prime Agent        | Not supplied by the current bridge | Not advertised as primary memory                 | Yes, for an existing live session    | [Prime Agent](https://docs.origintrail.io/connect-agents-and-systems/prime-agent.md) |
| Local model        | Via DKG's MCP orchestration        | Explicit tool use; read-only by default          | See local runtime configuration      | [Local models](https://docs.origintrail.io/connect-agents-and-systems/local-llm.md)  |
| Custom application | HTTP/CLI operations                | Implemented by your application                  | Your application supplies its UI     | [HTTP integration](https://docs.origintrail.io/build-with-dkg/http-application.md)   |

## Setup and success criteria

For a fresh node, use an explicit network. Examples here select testnet; an existing node retains its configured network. Framework/model installation, credentials, and model costs are separate prerequisites.

After connecting a runtime with memory tools, complete [Your first node + agent workflow](https://docs.origintrail.io/start-here/quickstart.md). Confirm it can retrieve the supplied fact and source in a new conversation under the same authorized identity. Then use [collaboration](https://docs.origintrail.io/build-with-dkg/collaborate.md) to check that another participant can retrieve shared knowledge. For a chat-only connection, verify the live conversation first and add a supported memory connection for these workflows.

For exact runtime tool names and parameter spelling, inspect the tool schemas and the node's `/.well-known/skill.md`. MCP/HTTP examples use camelCase; Hermes/OpenClaw tool fields can use snake\_case. Do not copy one runtime's payload into another without checking its schema.


---

# 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/integrations.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.
