Harvey

An autonomous sales agent that runs on your Claude Code subscription.

Harvey finds businesses worth selling to, learns something specific about each one, writes cold email that references it, sends it, reads the replies, and works the conversation toward a meeting. It runs on your machine, in a loop, on its own.

The unusual part: there is no API bill. Harvey drives the claude CLI in headless mode, so every decision, every email, every reply it handles is billed against the Claude Pro or Max subscription you already pay for. Not an API key. Not per-token. The subscription.

$ harvey run

============================================================
Harvey is online. Always Be Closing.
============================================================
Checking pipeline state...
Decision: prospect (only 3 new prospects; pipeline needs leads)
  discover  → 41 businesses in Portland, OR       ($0.00, OpenStreetMap)
  profile   → 41 sites read, 288 observations     (free, no model calls)
  scout     → 12 scored against your ICP
Decision: write_campaign (12 new prospects with no drafts)
  writer    → 3-email sequence for Cascade Landscaping
  outbox    → 12 emails waiting for your approval
Cycle complete. Sleeping for 15 minutes.

And the dashboard it keeps, at localhost:5555 — confirming a signal, building a cohort out of the confirmed ones, pricing a discovery run before it spends anything, and approving mail one message at a time:

Table of contents

• Why the subscription thing matters
• What Harvey actually does
• Quick start
• You confirm what it looks for
• The prospecting pipeline
• The skills library
• The sub-agents
• Nothing sends without you
• The dashboard
• How the data is stored
• Configuration
• Legal and deliverability
• Troubleshooting
• Project structure
• Philosophy
• Roadmap

Why the subscription thing matters

Every other autonomous sales agent bills you per token. That is the whole reason they cost what they cost: an agent that thinks in a loop, all day, is an agent that burns API credits in a loop, all day. Vendors solve this by thinking less — shorter prompts, cheaper models, fewer passes.

Harvey sidesteps it. It shells out to the claude CLI:

claude -p "<prompt>" --output-format json --dangerously-skip-permissions

That is the same subscription-billed path claude uses interactively. So Harvey can afford to think properly: full skills library in context, careful personalization per prospect, real reply handling.

What this costs you:

For comparison, the tools Harvey replaces start at $250–500/month — and they are weakest precisely where Harvey is strongest: small local businesses with 5–50 people, where single-provider contact coverage caps out around 30% and micro-businesses are frequently absent entirely.

Harvey also budgets itself. It reads your live subscription quota the same way /usage does, and throttles so it always leaves headroom for your own interactive Claude work. Set max_daily_claude_percent: 80 and Harvey will stop before it starts costing you your own rate limit.

Honest caveat. Running an agent against a subscription is a grey area worth understanding for yourself. Anthropic's terms permit personal automation of your own account; they prohibit reselling access or sharing credentials. Harvey runs locally as you, with your login. Don't turn it into a service for other people.

What Harvey actually does

Harvey runs a heartbeat: wake up, check the budget, decide what most needs doing, do it, log it, sleep. Every 15 minutes by default.

                 ┌──────────────────────────────────────┐
                 ↓                                      │
   Wake  →  Quiet hours?  →  Budget OK?  →  Decide  →  Act  →  Log  →  Sleep
                 │               │
              (sleep)         (sleep)

It decides deterministically, not by asking Claude what to do — that would burn a call on something derivable from four counts:

handle replies  >  send campaigns  >  write campaigns  >  prospect  >  idle (analyze)

Profiling and outbox draining ride along on every cycle regardless, because they cost nothing and have to happen on schedule.

Quick start

Prerequisites

• Python 3.11+ — check with python3 --version. macOS ships 3.9; if that's what you have, brew install python@3.13 first.
• An active Claude Pro or Max subscription, with the CLI logged in (claude login)
• A mailbox to send from — Gmail/Workspace recommended, on a dedicated secondary domain

Easiest: let Claude set it up

git clone https://github.com/ethanplusai/harvey.git
cd harvey
claude

Then say: "set up Harvey for me". The repo ships a CLAUDE.md that turns Claude Code into the setup wizard — it checks what state you're in, installs what's missing, asks what it needs, and trains Harvey on your product.

Or do it yourself

# 1. Install — note python3.13, not python3. On macOS bare `python3` is the
#    system 3.9, and a venv built from it can't run Harvey.
python3.13 -m venv .venv && source .venv/bin/activate && pip install -e .

# 2. Configure — every variable is documented inline with where to get it
cp .env.example .env && $EDITOR .env

# 3. Learn your product from your website
harvey train https://your-company.com

# 4. Choose what makes a good prospect (see below — this one matters)
harvey signals --confirm free

# 5. Find businesses. Free source, no account needed.
harvey discover

# 6. Watch it work
harvey dashboard          # http://localhost:5555
harvey run

You confirm what it looks for

This is the part that makes Harvey different from a black box, and it is deliberately not skippable.

Harvey knows how to collect 23 signals about a business. It does not collect any of them until you say so. On first run it proposes the catalog; you confirm, skip, or reject each one in the dashboard or from the terminal:

harvey signals                       # review the catalog
harvey signals --confirm free        # everything that costs nothing (21 of them)
harvey signals --confirm SERP_RANK   # a paid one, opted into explicitly

Every signal shows what it is in plain language, what it costs, and how many companies already carry it.

Then a cohort is a query, not a list

Once signals are confirmed, the dashboard's cohort builder turns them into a target set — pick what a good prospect must have and what disqualifies them, and it counts the matches live:

Has a marketing agency  AND  running Google Ads  AND NOT  already has online booking
→ 23 companies

That is a campaign with a reason behind it. You know exactly why each of those 23 is on the list, and so does the email Harvey writes them.

The prospecting pipeline

Four stages. Each one runs independently, re-runs safely, and states its cost.

1. DISCOVER — who exists

The only stage that spends money, so it always estimates first and never calls anything until you press go.

harvey discover --providers   # the menu, with real prices
harvey discover --estimate    # projected spend, then exits
harvey discover               # go