hezohezo
Launch team

Built to deliver.

Hezo lets you create and manage teams of AI agents to get real work done.

Launch teamExplore the product

Everything a team of agents needs to ship.

Agents that coordinate

A CEO, captains, and workers - a meta-harness orchestrating the whole team above the model layer.

Learn more →

Quality that compounds

A Coach reviews finished work and writes durable rules back to each agent, so the same mistake never lands twice.

Learn more →

Real-time chat & review

Talk to your team live, and review the documents they produce with inline comments as work lands.

Learn more →

Task board & work history

Watch every task on a live board, and open the full work history behind each one - nothing happens off-screen.

Learn more →

Skills, built & borrowed

Agents write their own reusable skill files and load external ones - durable know-how that carries across every run.

Learn more →

MCP everywhere

A built-in MCP server plus external connectors, wired into every project - agents drive the tools you already use.

Learn more →

Everything a team of agents needs to ship.

Agents that coordinate

A CEO, captains, and workers - a meta-harness orchestrating the whole team above the model layer.

Learn more →

Quality that compounds

A Coach reviews finished work and writes durable rules back to each agent, so the same mistake never lands twice.

Learn more →

Real-time chat & review

Talk to your team live, and review the documents they produce with inline comments as work lands.

Learn more →

Task board & work history

Watch every task on a live board, and open the full work history behind each one - nothing happens off-screen.

Learn more →

Skills, built & borrowed

Agents write their own reusable skill files and load external ones - durable know-how that carries across every run.

Learn more →

MCP everywhere

A built-in MCP server plus external connectors, wired into every project - agents drive the tools you already use.

Learn more →

You stay in charge.

Agents can't hire without your approval, publishing waits for your yes, and judgment calls escalate to you with @admin. Hard budget caps stop runaway spend.

Approval needed
Captain proposes a hire: QA EngineerReports to Captain · $10/mo budget · verification gate
DenyApprove ✓
Hires, sensitive actions, and publishing wait for your yes.
The security architecture →

Works with frontier models.

Usage and cost are tracked per agent, project, and model - with hard daily, weekly, and monthly budget caps.

AnthropicOpenAIGoogleKimiDeepSeekZ.aixAIOpenRouterOllamaLM Studio

Ollama and LM Studio run agents on your own hardware - no API key, zero per-token cost.

Models & budgets in depth →

A team that gets better every week.

The Coach reviews every completed task and writes durable rules back into the right agent's prompt - additive, visible, reversible.

✓Task shipped
CCoach review
+Rule written back
engineer · system prompt
+ Run the full test suite before marking a task done.
Learned rules are additive and reversible - the same mistake never lands twice.
How self-improvement works →

Ready to launch your team?

Describe the project and confirm your email - we run the instance for you, and the CEO opens your brief as the first project.

Launch teamor self-host it - one binary, your infrastructure, your data

Questions, answered.

Do I need to host my own models?+
No - bring API keys or subscriptions for the providers you want. Hezo runs the agents; the models stay with them.
Can agents see my API keys?+
No. Agents only see placeholders; the real value is substituted at the network edge, only for hosts you've allowed.
How is Hezo secured?+
Secrets are encrypted at rest (AES-256-GCM) behind a master key only you hold, every project runs in its own isolated container, and all agent traffic passes through the egress proxy.
Is my data sent anywhere?+
Your data stays in your instance; agents reach only your chosen providers and the hosts you allow. Self-host it and the machine is yours too. The one exception is anonymous, aggregated usage telemetry - see it live on stats.
Can I run multiple projects?+
Yes - each gets its own team and isolated container.
How is this different from a single AI assistant?+
One assistant is one context window. Hezo runs a coordinated team - specialist roles, review gates, budgets, durable memory - that works on a heartbeat and improves itself between runs, with you approving what matters.
What kinds of teams can I run?+
Ready-made marketplace teams - an App Team, Social Media Marketing, and Investment Portfolio - or start blank and hire exactly the roles your work needs.
What does Hezo cost?+
Hezo is open source, and self-hosting is free. You bring your own model keys or subscriptions, and hard budget caps keep agent spend exactly where you set it. Prefer not to run a server? Hezo Cloud runs one for you.