MyOpenClaw
Multi-Agent AI

One AI isn't enough. Build a team.

Give each agent one job and exactly the access it needs. Your public Telegram bot stays read-only while your private coordinator handles everything else.

👤
Public user
asks a question
🎤
Host
coordinator routes
📡
Beacon
read-only answers
Build your team

Three tiers, one rule: least privilege

Give every agent exactly the access it needs, and nothing more.

Read-only

Sees and responds. Nothing more.

Can do

✓Answer questions in a public Telegram group
✓Share information from a knowledge base
✓Guide users to the right resource

Cannot do

✕Run terminal commands
✕Write files to disk
✕Delegate to other agents
✕Browse the web

Safe

Research, draft, and coordinate. No exec.

Can do

✓Draft replies and summaries
✓Look up schedules and compile reports
✓Handle task delegation from the coordinator

Cannot do

✕Run terminal commands
✕Write files to disk

Unrestricted

Full access, for your trusted coordinator.

Can do

✓Run scripts and automation
✓Write and modify files
✓Orchestrate the rest of the team

15 pre-built teams, ready in 30 seconds

Pick a template and your agents are live. Customize later, or start from scratch.

SaaS Autopilot

Autonomous ops team that runs your SaaS while you build

Ops LeadSupportAnalystInfra

Startup Team

Ship faster with a full-stack AI team

AtlasDevResearchWriter

Marketing Team

Strategy, content, and growth - all working together

Marketing StrategistContent CreatorSEO SpecialistGrowth Hacker

Dev Team

Build, secure, and document - all in one team

LeadDevSentinelScout

Creator Team

Produce content that actually performs

ManagerWriterResearchSocial

Product Team

Decisions backed by research, data, and a clear roadmap

PMUXDataRoadmap

Sales Team

From cold prospect to closed deal

Deal LeadProspectorResearcherCloser

Research Team

Deep investigation, structured insights

PlannerScoutAnalyst

Operations Team

Finance, reporting, and process - all under control

Ops LeadBookkeeperAnalystCompliance

Support Team

Triage, resolve, and retain - at scale

Support LeadTriageResolverSuccess

Design Team

Beautiful, consistent, and user-centered - by design

Creative DirectorUX ResearcherUI DesignerBrand Guardian

DevOps Team

Ship faster, sleep better

Platform LeadSRESecurity EngineerIncident Responder

Data & Analytics Team

From raw data to decisions that move the needle

Data LeadData AnalystData Engineer

Executive Team

Your AI-powered leadership bench

Chief of StaffStrategy AdvisorFinance AdvisorCommunications

Community Team

Safe public support with a private powerhouse behind it

HostBeaconConcierge

Real-world use cases

Anywhere a public AI needs safe boundaries.

Telegram community support

Thousands of members, one AI team. A read-only bot handles public questions instantly. Complex requests get routed to a coordinator behind the scenes. Members get fast answers and your private systems stay safe.

Read-onlySafeUnrestricted

Discord server moderation

A read-only bot greets new members and answers FAQs. A safe-mode assistant drafts mod responses for review. The coordinator handles escalations privately. No bot can accidentally ban a user or wipe channels.

Read-onlySafeUnrestricted

SaaS customer self-service

Your public support bot reads the knowledge base and answers product questions. It never touches customer data or runs queries. Sensitive lookups get routed to a safe-mode agent working behind the scenes.

Read-onlySafe

Frequently asked questions

QCan the public bot accidentally run code?

No. Read-only agents have exec, file writes, browser automation, and agent delegation blocked at the framework level, not just by instructions. Even if a user tries to trick the bot, the tools simply aren't available to it.

QHow does delegation work between agents?

The coordinator agent uses agentToAgent delegation to hand off tasks to specialists by name. Specialists respond directly to the coordinator, which synthesizes and replies to the user. Read-only agents cannot initiate delegation.

QCan I mix presets in a custom team?

Yes. Every agent can have its own preset (unrestricted, safe, or read-only) regardless of how many agents are on the team. You can create a fully custom team from scratch or modify a pre-built template.

QWhat's the difference between Safe and Read-only?

Safe mode blocks exec (terminal commands) and file writes. The agent can still browse the web, delegate to other agents, and do research. Read-only adds those restrictions too: no browser automation and no delegation. It's the strictest tier.

QIs this available on all plans?

Yes. The agent system including all capability presets is available on Starter, Pro, and Business plans. Pro and Business plans support additional instances and more agents per instance.

Build your team in 30 seconds

Pick from 15 pre-built templates or configure each agent individually. Capability presets are applied automatically.

Get started free