Coordination layer · Not another agent

One queue for every agent you run.

Namu doesn't run your agents. It's the layer above them, pulling every interrupt from Claude Code, Cursor, Copilot and Codex into a single priority decision queue.

Sits above the agents you already run
Claude Code Cursor Copilot Windsurf Zed Codex
Why this exists

Every agent is capable.
Together, they make you the middleware.

Claude Code finishes a migration and waits for a yes. Cursor flags a failing test in another repo. Copilot has a draft ready. Codex hits a rate limit. Each one is confident, capable, and completely blind to the other three.

None of them know you're running the rest, so you become the router. You hold the whole picture in your head and re-explain the same rule to a different tool every time you switch windows.

As the agents get more capable, the constraint stops being their output. It becomes your attention. Namu is the layer that manages that, not another agent competing for it.

They're great individually, but I end up being the human middleware, copy-pasting between Claude windows and manually coordinating who works on what.

Reported on Hacker News, on running multiple coding agents.
Third-party account collected during Namu's problem research, not a Namu customer.
How it works

Three moving parts.
One surface.

Namu reads each agent platform's decision and status events and puts them on one board. It does no work of its own, and it never touches your source.

01 / Decision inbox

A single, priority-ordered queue.

Every interrupt from every running agent lands in one place: the blocker in plain language, the session it came from, and how urgent it is. You decide once, in order, instead of alt-tabbing to find who is stuck.

Reordered by urgency, not by which window you happened to open
Diagram · interrupts → one order blocking waiting running
Cursortests failing after merge Copilottouches payment code Claude Codemigration done, open the PR? Codexcleanup, not blocking 01 02 03 04 one queue
02 / Status across vendors

One view of what's actually running.

See what is running, paused, or blocked across every platform at once. This is the one screen a single-vendor tool structurally cannot show, because it only ever sees its own agents. Namu sees all of them because it sits above them.

Real coverage today: Claude Code, Cursor, Copilot, Windsurf, Zed, Codex
Every vendor · one board
Claude Code
Cursor
Copilot
Windsurf
Zed
Codex
one surfaceno more alt-tab
03 / Standing rules

Boundaries that persist across tools.

Set a rule once and Namu holds every agent to it, no matter which vendor the decision comes from. The boundary stops evaporating every time you switch windows.

See it below
Diagram · one rule, every agent
RULE Escalate payment code Claude Code Cursor Copilot Codex
Standing rules

Set the boundary once.
Every agent respects it.

A CLAUDE.md only governs Claude Code. Switch tools and that context is gone, so you re-explain the same boundary to the next agent by hand.

Standing rules live in Namu instead, above the agents, so one rule applies across every vendor you run. It holds whether Claude Code, Cursor, or Codex is the one that hits it.

Written in plain language. No config file per tool.
Persist cross-vendor by default.

Your rules · applied to every agent
Escalate security and payment decisions immediately.applies across all agents
Batch routine approvals; surface them every 2 hours.applies across all agents
Auto-approve doc-only edits under 50 lines.applies across all agents
Never merge to main without a human yes.applies across all agents
Early access pricing

Founding rates,
before launch.

Namu is pre-launch. These are the rates we're opening early access at, sourced from our go-to-market plan. Not live billing yet.

Solo
For one developer running their own fleet of agents.
$18/month
or $180 billed yearly
  • Up to 5 concurrent agent sessions
  • Personal decision inbox
  • Standing rules across every agent
  • Claude Code, Cursor, Copilot, Codex adapters
Get early access
Enterprise
For orgs standardizing how agents are governed.
Custom
starting around $500/month
  • Unlimited users and sessions
  • Custom agent integrations
  • Dedicated onboarding
  • Priority support
Talk to us
Early-access pricing, not a live commitment. Locked in for founding members.
Questions

Before you join

Does Namu run agents for me?
No. Namu doesn't run or automate your agents. It surfaces the decisions they're already waiting on you for, in one priority-ordered place.
Which agents does it work with?
Claude Code, Cursor, Copilot, and Codex today, with Windsurf and Zed in the same coverage. More adapters land as the waitlist grows.
Does Namu see my code?
Namu reads each platform's decision and status events, not your source. It's a coordination layer above your agents, not a proxy for your repository.
When do I get access?
We're opening early access in waves as the waitlist fills. Join now for an earlier slot and founding pricing.

Stop being the router.

Join the waitlist and run every agent through one queue. One email when your slot opens.

No spam. Founding pricing for early members.