openclaw/docs/channels/raft.md

summary	read_when	title	sidebarTitle
Raft External Agent support through the Raft CLI wake bridge	You want to connect OpenClaw to a Raft workspace You are configuring a Raft External Agent You are debugging Raft wake delivery	Raft	Raft

Raft connects an OpenClaw agent to a Raft External Agent through the local Raft CLI. Raft sends authenticated wake hints to the Gateway; the agent then uses the Raft CLI to check and send messages. Direct chat only (no groups).

Install

Raft is an official external plugin. Install it on the Gateway host:

openclaw plugins install @openclaw/raft
openclaw gateway restart

Details: Plugins

Prerequisites

• A Raft workspace with an External Agent.
• The Raft CLI installed on the same host as the OpenClaw Gateway, on the service's PATH.
• A Raft CLI profile that is already signed in and associated with that External Agent.

The plugin does not store Raft credentials; the Raft CLI keeps that authentication in its own profile.

Configure

Set the profile in config:

{
  channels: {
    raft: {
      enabled: true,
      profile: "openclaw",
    },
  },
}

For the default account, you can instead set RAFT_PROFILE in the Gateway environment:

RAFT_PROFILE=openclaw

Use a named account when one Gateway connects to more than one Raft External Agent:

{
  channels: {
    raft: {
      accounts: {
        support: {
          profile: "support-agent",
        },
        engineering: {
          profile: "engineering-agent",
        },
      },
    },
  },
}

Interactive setup records the same profile:

openclaw channels add --channel raft

How it works

When the Gateway starts, the plugin:

1. Opens a loopback-only HTTP wake endpoint on an ephemeral port.
2. Starts raft --profile <profile> agent bridge with that endpoint and a per-process token.
3. Accepts only authenticated, content-free wake hints with a replay identity from the local bridge.
4. Requires one of eventId, attemptId, messageId, delivery_id, wake_id, or id on every wake payload.
5. Deduplicates retried wake deliveries by bridge event id for 24 hours, including across Gateway restarts.
6. Returns a stable runtime session for the current bridge and an empty activity-drain batch for the Raft CLI protocol.
7. Starts one serialized OpenClaw agent turn per accepted wake.

The bridge owns Raft delivery retries and reconnects. The OpenClaw turn receives only a wake notice, not a copied Raft message body. It uses the CLI to read pending messages and to send its response:

raft --profile openclaw message check
raft --profile openclaw message send

Raft is not a push-message transport. OpenClaw does not automatically send the model's final text back through the bridge, so the agent must use the Raft CLI after processing a wake.

Verify

Check that OpenClaw can find the CLI and has a configured profile:

openclaw channels status --probe
openclaw plugins inspect raft --runtime --json

Then send a message to the Raft External Agent. The Gateway log should show the Raft bridge starting, followed by an inbound wake. The agent should use the configured Raft profile to check its pending messages.

Troubleshooting

Install the Raft CLI on the Gateway host and make `raft` available on the service's `PATH`. Verify it with `raft --help`, then restart the Gateway. Verify the configured profile is signed in and belongs to the intended Raft External Agent. Run `raft --profile agent bridge` directly to see the CLI diagnostic. This is expected when the agent does not invoke the Raft CLI. The wake bridge does not carry message bodies or automatic final replies. Check the agent's tool policy and ensure it can run `raft --profile message check` and `message send`.

References

• Raft
• Raft documentation
• Hermes Raft integration