Live in production · real sending + free sandbox

Cold email infrastructure your agent can run end to end.

Connect Codex, Claude Code, Cursor, or any MCP/HTTP-capable agent to one tenant-scoped system for domains, mailboxes, warmup, campaigns, and replies. Your agent owns strategy and copy; Coldrig runs the durable machinery.

Connect your agent Free sign up
01 tenant token 24 intent-level tools Tenant-scoped state
✣ Agent workspace
working
YS

Launch founder outreach for Northstar. Keep it personal and protect the brand.

I’ll set up isolated infrastructure, warm each mailbox, then launch only when the rig is healthy.

✓ setup_infrastructure 8 mailboxes
↻ infrastructure_status day 12 of 14
·· launch_campaign waiting for health
Rig health
96/ 100
8 healthy0 paused
Guardrail appliedDaily volume held at 24/mailbox

The agent stays the brain.

Coldrig handles the machinery.

You stay in control.

A smaller, smarter surface

One system from first domain
to first reply.

Most outreach stacks make your agent juggle registrars, mailbox vendors, sequencers, warmup tools, and inboxes. Coldrig collapses the machinery into a few high-level intents.

01 / Tools

Intent in.
Infrastructure out.

Your agent asks for outcomes, not vendor plumbing. Twenty-four carefully scoped tools keep context small and execution legible.

Explore the tool surface →
02 / Isolation

A clean rig for every brand.

Dedicated domains and mailboxes keep reputation contained. Nothing is shared across customers.

03 / Guardrails

Safety isn’t a prompt.

Send caps, suppression, unsubscribe handling, and health-based pausing are enforced below the agent layer.

04 / Control

Designed for agents.
Clear for humans.

Your agent operates the system. You get a calm control room for health, activity, campaigns, and conversations.

Human ↔ agent handoff

Brief it like a teammate.
Inspect it like a system.

Coldrig is built around the way agent-led work actually happens: the human sets the outcome, the agent plans and operates, and the product makes every action visible.

  1. 1
    Set the outcomeDescribe the audience, offer, and boundaries.
  2. 2
    Let the agent operateIt provisions, waits, launches, and triages.
  3. 3
    Step in when it mattersReview replies, health changes, and decisions.
Coldrig
Northstar YS
GOOD MORNINGEverything is running clean.
ACTIVE CAMPAIGNS3+1 this week
REPLIES478 need review
RIG HEALTH96All systems normal
Campaign activityLast 14 days
Agent activityLive
  • ✓

    Paused Atlas / inbox 04bounce rate crossed 3%

  • ↗

    Launched Founder signal420 leads · 3 steps

  • !

    Needs your review8 positive replies

Product illustration · simulated account data

Verify before you commit

Prove the workflow.
Before you commit.

Start with a fault-injecting sandbox that simulates provisioning, warmup, replies, bounces, timeouts, and rate limits — a safe technical pilot before you commit. Real sending is live in production for activated accounts; new accounts activate through a short concierge step.

Free sign up →See agent setupInspect the source ↗
terminal

$ npx agent-cold-email demo

Creating isolated demo tenant…

✓ infrastructure ready

✓ replies + failures simulated

↳ no real spend · no real sends

_

Plain-English status: the API, MCP endpoint, npm CLI, sandbox, and real sending are all live. New accounts activate real sending through a short concierge step while self-serve activation rolls out. Coldrig never guarantees inbox placement. Read the honest FAQ →

Live in production

Your strategy.
One rig underneath.