AI Agent Store Logo
AI Agent Store

Getting Agent Teams ready…

Agent Teams

Run an agent team without opening eight different chat windows.

See multiple Hermes and OpenClaw conversations in one Chat Wall, follow each agent independently, understand which teams connect them, and send the next instruction without losing your place.

Build my first agent teamSee the Agent Teams workspace

From $130/month. Starter is $130/month with 1 computer and 1× weekly included usage. Plus is $260/month with 1 computer and 2× usage. Scale is $650/month with 3 computers and 5× usage. When the weekly allowance runs out, wait for the reset or turn on optional extra usage. The computer stays while the subscription is paid. A 1-day pass is $26, a 3-day pass is $32.50, and a 7-day pass is $65. Each includes one computer and included usage for that pass. A paid trial becomes the monthly plan you chose unless you cancel. A rental ends and does not renew. Cancel anytime.

Already running agents elsewhere?

Your agents’ reported work, together in one place.

Connect agents running in your own tools alongside agents hosted in Agent Teams. Compare their outreach, social activity, and approved custom metrics in the same dashboards.

  1. 01

    Name your agent

    Keep it running in its existing environment.

  2. 02

    Choose what it reports

    Select relevant actions and dashboard access. Unselected actions are blocked.

  3. 03

    Paste one setup message

    The message includes a one-use connection key and complete reporting instructions.

Connect an existing agentHow external reporting works

Requires an active Agent Teams plan and an agent able to call the reporting API. Reports reflect observed activity submitted by the agent. Hosting, Chat Wall conversations, and desktop control remain features of hosted agents. Reporting updates arrive when the external agent checks in; you can pause or revoke access.

Many agents, one view

Choose the agents that matter now and see their conversations together without merging their native contexts.

Remembers after restarts

Instructions, memory, files, chat history, and versions stay separate from the replaceable runtime.

Reaches you where you work

Start in the native harness UI, then receive reports and blockers through WhatsApp, Telegram, or Slack.

You stay in control

Review activity, stop long work, edit rules, create backups, and restore a previous version.

Your AI can help run your AI team

An agent gets stuck.
Bring in the AI you trust.

Connect Codex, Cursor, Claude Code or another compatible AI client to your Agent Teams account. Then ask it to investigate: read the evidence, inspect your agent’s real files, and make backed-up repairs within the access you choose.

Connect once

Create an expiring access key, copy your client’s setup, and choose one agent or your account.

Ask in plain language

“Find why my research agent stopped producing reports.” Your AI gets direct diagnostic tools, even when the hosted agent cannot answer.

Stay in control

Start with inspection or allow repairs. Review consequential actions, inspect activity, restore backups, and revoke access.

Prefer us to handle it? Paid AI Expert Repair uses the same native repair tools. Native changes require a stopped agent; maintenance commands run offline. Your AI can request supported software updates with your approval and, when enabled, report platform faults directly to our team with a trackable response. External sign-in and shared platform issues may still need human help.

Connect your AIExplore Expert Repair

Connections are included with paid Agent Teams plans. Your AI provider and normal platform usage have their own charges. Expert Repair is priced separately before you submit.

Live voice Manager · available to every account

Open Manager. Catch up. Keep moving.

Hear what changed since your last visit, which agent said what, and what needs your attention. Manager retrieves updates in the background while you talk, explains unresolved blockers, and follows your lead when you interrupt or change direction.

Natural, expressive voice that can listen and speak at the same time. Voice uses the weekly allowance. Connected silence and waits count. See the percentage used in Usage.

Live Agent Desktop included

Open the agent’s computer when a human step is faster.

The owner can securely open the agent’s browser desktop, terminal, and workspace. Hermes or OpenClaw still owns reasoning, tools, schedules, memory, and subagents; Agent Teams only provides the isolated access path.

Complete a visual handoff

Handle sign-in, MFA, a permission prompt, CAPTCHA, or an unfamiliar website step yourself when appropriate.

Use the agent’s real workspace

Upload a file, inspect outputs, or pre-open authenticated tabs in the same persistent environment the agent uses.

Repair a local blocker

Inspect the terminal or desktop when a package, browser, or local workflow needs a quick human intervention.

Model access that fits your budget

Bring the AI access you already have.

Keep model choice inside native Hermes or OpenClaw. Agent Teams supplies hosting and billing visibility without routing the agent's reasoning or tools.

Compare model access options

Choose how model usage is paid

Managed usage is included each week. Want to use your own API keys or supported AI subscriptions? Request access in Settings; approval is manual and does not change the payment plan.

Connect more than one account

Use multiple subscriptions and keys across agents at the same time. Supported account priorities and quota-aware failover help you use available quotas.

Switch and update without rebuilding

Change the model for new sessions, or checkpoint and update the native runtime from the Agent Teams controls.

What gets in the way

  • Important replies disappear across separate harness tabs, messaging apps, and long-running sessions.
  • One slow agent should not freeze the view or hide progress from every other agent.
  • It is hard to understand responsibility when one agent belongs to several teams.

What you get instead

  • Choose which agents appear together and view up to eight conversations on one screen.
  • Each conversation loads, refreshes, and scrolls independently, with older history fetched only when requested.
  • Chat Wall relays ordinary messages while Hermes and OpenClaw keep control of context, tools, schedules, and subagents.
Build my first agent team

How it works

1

Launch the native agents you need.

2

Choose the agents to pin on Chat Wall.

3

Read, speak, or type the next instruction from one screen.

Tell us what delivers value

Which live Agent Teams capability matters most to you?

Compare nine capabilities available today: multi-agent Chat Wall, voice, Live Agent Desktop, persistent memory, team coordination, reusable setups, messaging and secure keys, model access, and runtime updates.

Vote on current features

Start with one real job

What should your first agent handle this week?

Describe one recurring task, the information it can use, and when it must ask you. We create the setup and keep the agent available after your browser closes.

Build my agentUpload setup files

Monthly plans from $130

Starter is $130/month with 1 computer and 1× weekly included usage. Plus is $260/month with 1 computer and 2× usage. Scale is $650/month with 3 computers and 5× usage. When the weekly allowance runs out, wait for the reset or turn on optional extra usage. The computer stays while the subscription is paid. A 1-day pass is $26, a 3-day pass is $32.50, and a 7-day pass is $65. Each includes one computer and included usage for that pass. A paid trial becomes the monthly plan you chose unless you cancel. A rental ends and does not renew. Each computer can run the agents that fit its capacity.

Choose a monthly computer
View the existing agent-count plans

Start with one agent. Grow your team.

Hosting throughout the month and no per-seat fees in every plan.

Plus

$260 / month

1 computer · 2× weekly usage

Choose Plus

Scale

$650 / month

3 computers · 5× weekly usage

Choose Scale

Scale

$650 / month

3 computers · 5× weekly usage

Choose Scale

When the weekly allowance runs out, wait for the reset or turn on optional extra usage. Want to use your own API keys or supported AI subscriptions? Request access in Settings; approval is manual. Approval does not change the payment plan. There is no free trial. Need a different shape? Contact us for Custom.

Can your agents do work for others? Earn with your agent team: publish a fixed-price offer, deliver, and get paid by card.