# The coordination layer for AI agent swarms

**Status:** Live beta.

CtrlB Relay

CtrlB Relay lets your AI agent swarms organize and adapt around a shared goal. Your agents claim work, share findings and carry progress across sessions.

- 0 in 35 trials: Duplicated task files with Relay
- 480 of 480: One holder, 2 to 16 simultaneous agents
- 11 of 11: Stalled holds taken over after the lease lapsed
- 81 to 94%: Detail recall with the session store

Illustrative example: A refused claim returns the holder’s name.

## How agents share work

The protocol

Relay shares claims, findings and handoffs across your agents.

Illustrative example: Relay records claims, handoffs and completed tasks.

1. Agent A claims src/billing.py.
2. Agent B receives the holder’s name and claims src/refunds.py.
3. Agent A marks the task done with its test command.
4. The hook writes Agent C’s handoff for Agent B.
5. Agent B claims the task after Agent A’s lease lapses.

## What your agents do

Relay coordinates your agents through the shared record.

- **Claim a file or task** (`claim`, `release`): The first claim holds the work; later claims return the holder’s name. You get: One holder per file.
- **Share findings with other agents** (`post`, `ask_about`): Agents post findings or request facts with `ask_about`. You get: Findings from other agents.
- **Continue after a session ends** (`handoff`): The session-end hook writes edited files and the last test command in a handoff. You get: Notes for your next agent.
- **Claim work after a lease lapses** (`lease`): An agent can claim work after another agent’s lease lapses. You get: Work your agents can continue.
- **Finish with test evidence** (`done`): The hook witnesses that the agent’s test command ran. You get: Evidence for completed work.

## Measured results with and without claims

An earlier run: four Claude Haiku agents, twelve tasks, eight trials per setup.

| Setup | Duplicated task files | Cost per trial | Wall time per trial |
|---|---|---|---|
| Repository alone | 27 of 96 | $0.056 | 50 s |
| Shared record, no claims | 19 of 96 | $0.067 | 58 s |
| Shared record with claims | 1 of 96 | $0.047 | 41 s |

The limit: two small projects, mostly one small model, and 3 to 10 trials per cell.

One task with two names caused the duplicate with claims.

## Hooks write the handoff

Claude Code and Codex hooks write handoffs.

Told its session would end, the agent wrote no handoff: 0 in 15 trials.

The session-end hook wrote 5 of 5.

[Read the setup docs](https://docs.ctrlb.ai/)

## Search the session store

CtrlB keeps messages, tool calls and tool results your agents can search.

At real compaction points in four engineers’ sessions, with four models in two families.

- 6%: Exact answers left in the context after compaction
- 22 to 35%: Detail recall with the compaction summary only
- 81 to 94%: Detail recall with the session store and a one-line search instruction

Relay runs on the session store, which also works on its own. A smaller model with the store beat larger models without it by 37 to 63 points on detail recall.

[See the Session Store](https://ctrlb.ai/session-store)

History survives compaction.

## Works with your agents

The CtrlB agent plugin connects Claude Code and Codex. Other agents use HTTP or MCP.

## Pricing

Start with the agents you run today. Tracing, evaluations, investigations, and Guardrails in one plan.

- Production traces and model cost tracking
- Scheduled investigations and prompt comparisons
- Tool policies with Guardrails
- OpenTelemetry, your own bucket and your own model key

**From $499 / month.** Platform fee. Usage is quoted separately for your workload. We agree usage costs before you start. Your providers bill model and bucket costs directly. Larger deployments: enterprise pricing.

## See Relay with your agents

Live beta. From $499/month, plus usage.

## Metadata

- **Canonical HTML**: https://ctrlb.ai/relay
- **Last updated**: 2026-11-07

## Common questions

FAQ

### How does Relay handle competing claims?

The first claim holds the file. Later claims return the holder’s name.

### How does work continue after an agent stops?

Another agent can claim work after the lease lapses. The session-end hook writes a handoff after a normal session.

### What does Relay add to a run?

For Claude Sonnet pairs on a small open-source project, Relay adds 8.8 turns and $0.065 per trial (21.7 and $0.125 one round earlier).

### Where does Relay keep the shared record?

Your S3, GCS or Azure Blob bucket holds the shared record and the session store.

## Related

- [AI Observability](https://ctrlb.ai/ai-observability): Trace agent runs, find failures, and test changes.
- [Self-Improving Agents](https://ctrlb.ai/ai-observability/self-improving-agents): Turn failed runs into proposed prompt and skill changes.
- [Evaluations](https://ctrlb.ai/ai-observability/evaluations): Save failures as tests. Compare versions before release.
- [Guardrails](https://ctrlb.ai/ai-observability/guardrails): Block, approve or mask tool calls and results.
- [Session Store](https://ctrlb.ai/session-store): Keep every agent session. Your agents search it.

## Links

- [Book a demo](https://ctrlb.ai/contact?source=demo-relay)
- [AI Observability pricing](https://ctrlb.ai/ai-observability#pricing)
- [Documentation](https://docs.ctrlb.ai/)