Let AI answer your
support emails.
Plug your AI into your support inbox. It reads every customer profile and every past reply. You decide whether it sends, drafts, or just looks things up.
SuppyHQ brings the inbox. Your AI brings the product knowledge.
Sarah Doe
sarah@example.com · monthly, $174 LTV
Quick question — is there an annual plan? I'd love to save a bit if I'm committing for the year.
Sarah · 4 minutes ago
Hi Sarah, yes — annual is $190/yr, ~$38 cheaper than monthly. I switched your plan and credited the unused portion. Anything else?
Sent by Claude on behalf of Carlos.
Three ways to use it.
Pick what fits. The customer cares about the answer, not who typed it.
Full auto
AI answers. You read in the morning.
It sends every reply. A 30-second window opens in your operator UI so you can pull anything back.
"Handle the inbox while I'm in meetings."
Draft mode
AI writes. You hit send.
It saves drafts to your composer in your voice. You skim, edit, send. The middle ground most operators start in.
"Draft a refund reply matching how I usually answer."
Read only
AI looks things up. You write.
Customer history, payment status, past threads, all pulled before you type a word. The reply is yours.
"Show me Sarah's history before I reply."
The reply tells the truth.
Every email tells the customer who sent it. No fake signature, no pretending.
When you reply
Refund's on its way, Sarah. 5–10 days. Anything else?
Carlos
SuppyHQ
When AI replies
Refund's on its way, Sarah. 5–10 days. Anything else?
Sent by Claude on behalf of Carlos.
Silence means human. An attribution line means AI. The asymmetry is the point.
One curl. Skill included.
The installer drops the binary on your $PATH, writes the Agent Skill, and suppyhq auth login opens a browser. Click Allow, you're done.
Open source · MIT · github.com/karloscodes/suppyhq-cli
A few honest answers.
- How does login work?
- suppyhq auth login opens your browser, you click Allow, the token saves to your machine. Never your clipboard, never your shell history, never your AI's context. Same flow gh auth login uses.
- Will the AI hallucinate?
- It can. Run the skill in a session that already knows your product (a Claude Code project rooted in your codebase, for example). The skill brings the inbox surface; your AI brings the facts to cite from.
- What if it sends something wrong?
- Two layers. Every reply queues 30 seconds before send, cancellable from the operator UI. And you can ask it to draft instead of reply: it writes, you read, you send.
- Does this lock me into one AI?
- No. The CLI works on its own and the skill plugs into Claude Code, Cursor, Codex, OpenCode. Switch anytime. Your data lives in SuppyHQ, not the agent.
- Is the CLI really open source?
- MIT, on GitHub.
Stop typing. Sign up.
$19/mo. Free until you've talked to more than 10 people. No card.