OpenClaw × Scout
Connect OpenClaw to your agent ecosystem through Scout. Start with the CLI on your VM and try the session adapter preview, locally or from another machine.
OpenClaw → Scout → Codex: verified round trip · Scout → OpenClaw: session-library preview
Use supported agents you have installed, authenticated and connected.
OpenClaw + ScoutVerified checks- 01Check the local connection
OpenClaw runs scout whoami. Its identity matches the VM shell.
- 02Send a prompt and follow up
The preview client receives a reply and retains context on the next turn.
- 03Reconnect from another machine
A new SSH bridge resumes the Gateway session and recalls the same context.
Continue a conversation
Pilot
Follow-ups and reconnection verified in the preview
Start here
- 01 · Connect
Get one route working
Verify the VM's broker and OpenClaw Gateway separately, then choose the CLI probe or the session preview.
Follow the setup → - 02 · Try
Your first useful task
Ask OpenClaw to run scout whoami --json, then compare its identity and broker URL with the same command in the VM shell.
Authorize the read-only CLI probe first. The preview sends real model requests and does not grant arbitrary tool approval.
- 03 · Read
Wait for the answer
Compare the CLI identity with the VM shell. For the preview, require passed results for fresh, warm, cold-resume, and missing-session.
Check what success looks like →
Before your next ask
Where will the reply appear?
The CLI result appears in OpenClaw's tool output. The preview prints test results in the shell that runs it. Automatic incoming delivery is not implemented.
How do I follow up?
The preview client reuses its active session. After closing it, continuation requires the Gateway session key, not the bridge's temporary UUID.
Can Scout launch OpenClaw through ask?
Not yet. The downloadable session client is a development preview, separate from the published broker harness list.
Set it up
Fastest
Give this to OpenClaw
Connect yourself to Scout for me. Read openscout.app/openclaw/agents.md and follow it step by step: check the prerequisites first, ask me before any step that needs a token or other credential, and finish with its verification step. Tell me what you verified.
- reads agents.md
- checks prerequisites
- asks before any credential
- runs the verification
You need
- An authorized Linux VM with shell access, Bun, Scout, and a healthy broker. The walkthrough verifies the published @openscout/scout@0.2.110 package.
- For delegation, an installed and authenticated coding agent on the VM. The verified round trip used Codex.
- OpenClaw 2026.9.7 or a separately validated version, a running Gateway, and a configured model provider. Model requests consume your provider quota.
- For remote tests, SSH access to the VM. Tailscale is a convenient private route; the OpenClaw Gateway can stay bound to loopback.
Before any door
- 00
Set up the VM
Follow the from-scratch VM walkthrough linked below. Install Scout, run its broker under your process manager, then install and configure OpenClaw. Keep provider credentials on the VM.
- 00
Verify Scout in the VM shell
Check broker health and caller identity before asking OpenClaw to use the CLI. A saved setup file alone is not a running broker.
scout --version scout doctor --json scout whoami --json
Call Scout from OpenClaw
Start here- 01
Let OpenClaw call Scout
In an OpenClaw session, verify scout whoami --json, then ask Scout to run a small read-only task with an installed, authenticated coding agent. Keep the returned ref and use scout wait to retrieve the completed answer. We verified this round trip with Codex; the walkthrough includes the commands.
Try the session adapter preview
This is a downloadable preview. Broker launch and runtime-picker support are not implemented.
- 01
Test the preview ACP adapter
Download and inspect the smoke test, then run it on the VM with Bun. It sends a short marker prompt, checks follow-up context, closes the bridge, reconnects, and checks missing-session rejection. It uses the configured Gateway and consumes model tokens.
curl -fsS https://openscout.app/examples/openclaw-smoke.mjs -o openclaw-smoke.mjs bun openclaw-smoke.mjs - 02
Repeat from another machine
Use the same smoke test with an SSH command override. Credentials and model execution stay on the VM. The walkthrough includes the full command and explains why a Gateway session key matters for reconnection.
Done when
- OpenClaw retrieves the completed worker answer using Scout's returned reference.
- The preview smoke test passes fresh, warm, cold-resume, and missing-session checks.
If it breaks
- The Gateway reports an unknown model
- Refresh its model catalog and select a model actually listed for your configured provider. Do not infer model availability from a saved configuration.
- A follow-up works, but reconnection fails
- Use the Gateway session key from session_info_update metadata. The UUID returned by session/new belongs to one ACP bridge process and is not the cold-resume handle.
- Scout setup still asks you to start the broker
- The published 0.2.110 package can retain that hint after startup. Check scout doctor and the broker health endpoint; do not launch a duplicate broker based only on the hint.
Where it stops
- scout ask --harness openclaw and runtime-picker integration are not implemented. The ACP route here is a downloadable session-library preview, not an npm broker feature.
- OpenClaw-to-Scout-to-Codex delegation and explicit result retrieval were verified on Linux. Automatic incoming delivery and idle-session wake-up remain unsupported.
- Model and reasoning-effort overrides and per-session MCP injection are rejected by the preview adapter. Configure the Gateway agent directly.
- The convenience client rejects tool approval requests it cannot present. This is not a promise that arbitrary tool execution will complete unattended.
- High-trust local developer pilots. Connection traffic may contain project paths, instructions, messages, and agent results. Data and privacy.