Inbox & chat
An AI agent that works your Gmail inbox for you.
Connect Gmail and an OpenHelm agent can read, label, draft and send from your own account on a schedule you set. It runs in an isolated cloud environment, keeps a log of every action, and at lower autonomy levels leaves drafts for your sign-off rather than sending anything itself.
What agents do with Gmail. Recurring jobs, checked every run.
Morning inbox triage
Every weekday at 8am, scan unread mail, classify each message by intent and urgency, apply labels, and send you a short needs-reply digest.
Reply drafting in your voice
Draft responses to routine enquiries using the context of the thread. Drafts sit in Gmail for your approval, or send automatically at the highest autonomy level.
Follow-up chasing
Track sent threads still waiting on an answer and send a polite nudge after a set number of working days, stopping the moment a reply lands.
Inbox to data table
Extract structured details from incoming mail, such as enquiries, invoices or booking requests, into an OpenHelm data table your other jobs and reports can use.
Connect Gmail. A few minutes, once.
Connect Gmail
Add Gmail under Connections in the OpenHelm app and complete the hosted sign-in, or mint a connect link programmatically with POST /v1/connections/links.
Describe the job in plain English
Tell OpenHelm what you want done and how often. It drafts a plan with a schedule, the tools it will use, and a clear definition of done.
Approve the plan
No job fires until you have reviewed the plan. Set the autonomy level to control whether writes execute directly or queue for your approval.
It runs, self-checks and reports
Runs execute in isolated cloud sandboxes on schedule. An independent evaluator scores each run against the goal, and results arrive as logs, emails or data-table rows.
Or provision it over the API (see the Connections API docs):
curl https://api.openhelm.ai/v1/connections/links \
-H "Authorization: Bearer oh_live_..." \
-H "Content-Type: application/json" \
-d '{ "provider": "<provider id>", "name": "Gmail" }'
# Returns a short-lived hosted link. Open it once to authorise,
# then poll GET /v1/connections until it shows as authenticated.Questions
Can the agent send email as me?
Yes. It sends from your connected Gmail account, so replies land in the same thread from your address. Whether it sends immediately or queues drafts for your approval is controlled by the autonomy level you set on each job.
How does OpenHelm connect to Gmail?
Through a scoped OAuth grant: you sign in to Gmail once via a hosted connect flow, in the OpenHelm app or via a connect link minted with POST /v1/connections/links. OpenHelm stores no passwords, the grant is limited to what your jobs need, and you can revoke it at any time.
Can the jobs run on a schedule without me?
Yes, that is the point. Jobs run once, on an interval, or on a cron expression. A scheduler fires them, a watchdog times out anything hung, and a separate evaluator checks each run actually advanced the goal. You approve the plan before anything runs for the first time.
Is my Gmail data safe?
Each run executes in an isolated cloud sandbox with scoped, revocable credentials and no middle-layer copy of your data. Every action is logged per run, results come back with evidence, and the agent never fabricates data it could not verify.
More in Inbox & chat
Give your product a team that never clocks off.
Start free in the browser, or run it on your Mac with your own Claude Code or Codex plan.