Agents · Kiro
Kiro for teams, without collisions
In shortRun lanes init --agents kiro in your repository and commit the result. Lanes writes .kiro/hooks/lanes.json so that every Kiro edit is committed as you and published to a shared branch right after it is made. Add lanes mcp to Kiro so its agent can read the team brief and check a file before touching it.
Kiro on a team
Kiro plans work in specs and then edits many files. A teammate's agent working in the same area has no way to know. When two people's agents work in the same repository, one can overwrite the other's change in a shared file, or write new code against a function the other is renaming. Git shows the damage later, at merge time, after both agents have finished.
Lanes connects every agent on the team to one coordination server. Kiro gets teammates' changes published to the shared branch, and the rest of the team's agents see what Kiro is changing.
What Lanes installs for Kiro
Lanes writes an agent hook in .kiro/hooks/lanes.json for the Kiro IDE and Kiro CLI. Each Kiro edit is committed and published right after it is made, so teammates' agents see it and get heads-ups about it.
The file is committed with lanes init, so every teammate gets it when they pull. lanes off removes only the Lanes entries and leaves your own settings alone.
| What | Kiro with Lanes |
|---|---|
| Edits wait for a teammate's edit of the same file | No, published right after the edit instead |
Each edit committed as you and published to lanes/main | Yes |
| Team brief added to each prompt | No, use the MCP tool team_brief |
| Heads-up before reading a teammate's file | No |
| Check at the end of a turn | No |
| MCP team tools | Yes |
Set it up
- Get Lanes:
git clone https://github.com/mfmatozza/lanes && cd lanes && npm ci && npm run build. The commands below writelanesfornode /path/to/lanes/dist/lanes.cjs. - In your repository, run
lanes init --agents kiroand push the commit it makes. - Turn on shared context once per repository:
lanes team on, then commit.lanes/team.json. - Add the MCP server to Kiro:
Add this to ~/.kiro/settings/mcp.json:
{ "mcpServers": { "lanes": { "command": "node", "args": ["/path/to/lanes.cjs", "mcp"] } } }- Check the machine with
lanes doctor.
Working alone, the first session starts a local Lanes server. For a team, one person runs lanes server --host 0.0.0.0 and invites the others with lanes invite <name>.
Things to know about Kiro
- Kiro's edits are shared after the edit, not queued before it.
- Add
lanes mcpto~/.kiro/settings/mcp.jsonso the agent can call the team tools.
Status
Built from Kiro's published documentation and covered by Lanes' automated tests. It has not yet been run against the real Kiro. Issues and reports are welcome.
Mixed teams work: one person can use Kiro while teammates use Claude Code, Codex or Cursor. Every agent reports to the same server, so the brief and the heads-up name each teammate's task whatever agent they run.
Questions
Does this cover Kiro IDE and Kiro CLI?
Yes. Both read agent hooks from .kiro/hooks/.
Are Kiro's edits queued?
No. They are published right after each edit, and teammates' agents are queued and warned about them.
How does Kiro get shared context?
Through lanes mcp in ~/.kiro/settings/mcp.json.