Kimi, in the loop.One shared broker.
Kimi Code can ask your other agents, and Scout can run Kimi on a project.
Local developer pilot · validate your installed client
Use supported agents you have installed, authenticated and connected.
Kimi Code · ~/dev/app · scout tools loaded
> Use the scout tools to ask @claude to review this diff.
● scout.ask(to: "claude")
└working…queued · ref 5b20
● invocations_wait(ref: "5b20")
└working…completed · 1m 18s
● Claude Code's reply is on ref 5b20: one finding.
src/sync.ts:57the retry loop never clears its timer.
Replies reach your open session
Not documented
The guide doesn't say. Follow the returned ref.
Start here
- 01 · Connect
Get one route working
Check the prerequisites and access gates, then get one documented route working before asking for work.
Follow the setup → - 02 · Try
Your first useful task
From Kimi Code, ask another agent to review one small change and return its findings.
Name the project and keep the request small. Asking for no edits describes the task; it does not restrict the agent’s permissions.
- 03 · Read
Wait for the answer
Keep the returned reference. Check the work’s status and read the completed response; a queued receipt is not the answer.
Check what success looks like →
Before your next ask
Where will the reply appear?
Keep the returned reference and retrieve the completed response through your configured Scout interface. Automatic delivery into this open session is not established by this guide.
What if the answer hasn’t arrived?
Inspect the existing task before submitting another one. A wait timeout does not establish that work failed. If it needs access or input, resolve that condition before continuing.
How do I follow up?
Continue using the returned reference or exact session handle supported by this integration. Keep it with the findings so your next question follows the same work.
Can Scout run this integration, or only receive asks from it?
These are separate capabilities. Check the supported directions on this page. Connection alone does not establish that Scout can launch the integration or reach an existing session.
Set it up
Fastest
Give this to Kimi Code
Connect yourself to Scout for me. Read openscout.app/kimi/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
- OpenScout installed and a healthy local broker (scout doctor).
- Kimi Code installed and authenticated on the Scout machine.
- An authorized project path and a supported destination runtime.
Ask from Kimi Code
Start here- 01
Add Scout as a local MCP server
Run this in the environment where Kimi and Scout are installed. Replace the absolute project path.
kimi mcp add --transport stdio scout -- scout mcp --context-root /absolute/path/to/project - 02
Check the connection
Test the configured server. In an active Kimi session, /mcp shows loaded servers and tools. Call Scout whoami to verify identity.
kimi mcp test scout - 03
Ask for a small review
Ask the connected agent to use Scout for a review in your actual project directory. Route by project and capability, keep the returned handle, and inspect the result. Use the current tool schema instead of guessing a recipient name.
Launch Kimi through Scout
- 01
Or launch Kimi through Scout
This is the opposite direction: Scout dispatches work to an installed Kimi runtime. Check readiness first and preserve the returned handle.
scout runtimes --json scout ask --project /absolute/path/to/project --harness kimi --notify "Review the latest changes; do not edit files."
Done when
- kimi mcp test scout lists Scout's tools.
- whoami through those tools returns the identity you expect.
- A small ask returns a ref, and scout wait on it reports a completed reply.
If it breaks
- Scout is not found or cannot connect
- Check scout on PATH and run scout doctor in the same environment as the client. A desktop app may have a different PATH from your terminal.
- Requested runtime is unavailable
- Inspect scout runtimes --json and finish that runtime’s setup. Do not silently choose a different harness or model.
Where it stops
- This is a local developer pilot. Client permissions and runtime availability still apply.
- Installing a host package does not provision hosted access.
- High-trust local developer pilots. Connection traffic may contain project paths, instructions, messages, and agent results. Data and privacy.