Coding & Development🌐universal
hezo
Your own team of AI agents. Built to get deliver.
Quick Start
Install this Skill
npx skills add hezo-ai/hezo<p align="center">
<img src="assets/logo.svg" alt="Hezo" width="96" height="96" />
</p>
<h1 align="center">Hezo</h1>
<div align="center">
[](https://github.com/hezo-ai/hezo/actions/workflows/ci.yml)
[](https://coveralls.io/github/hezo-ai/hezo?branch=main)
[](./LICENSE.md)
[](./docs/concepts/languages-and-formats.md)
</div>
<p align="center">
<sub>
🌐
English · Deutsch · Français · Español · Italiano · Português (Brasil) ·
Nederlands · Polski · Svenska · 简体中文 · 日本語 · 한국어
</sub>
</p>
<p align="center">
<strong>Your own team of AI agents. Built to deliver.</strong>
</p>
<p align="center">
<a href="#quickstart">Quickstart</a>
· <a href="#features">Features</a>
· <a href="./docs/introduction.md">Docs</a>
· <a href="https://hezo.ai">Website</a>
· <a href="https://github.com/hezo-ai/hezo">GitHub</a>
· <a href="https://x.com/hezo_ai">X</a>
</p>
<p align="center">
<img src="assets/hero.png" alt="The Hezo web app - a project task board with its team of AI agents" width="863" />
</p>
## What is Hezo?
Hezo is a self-hosted server and web app for running **teams of AI agents like an
organisation**. You stand up a CEO, a Captain, engineers, designers, researchers -
whatever the work needs - with org charts, projects, budgets, and approvals built in. You
manage goals and projects, not twenty terminal tabs.
Because those agents run real, often AI-written code, Hezo is **secure by design**: agents
never see your real secrets, everything sensitive is encrypted behind a key only you hold,
and every project runs sandboxed in its own container. You own the machine, the model keys,
the spend, and the data.
New here? Start with the [Introduction](./docs/introduction.md) and
[the meta-harness](./docs/concepts/meta-harness.md) - the idea Hezo is built around.
## Quickstart
Hezo ships as a **single self-contained binary** - nothing to compile, no runtime or
dependencies to install, so you're up in seconds. The fastest way to get it is the
one-line installer, which detects your OS and CPU architecture and downloads the
matching [release binary](https://github.com/hezo-ai/hezo/releases/latest).
Agents only ever work inside a container, and you choose where those containers run. By
default it's your own machine, so the one prerequisite is a **Docker-compatible runtime** -
Docker, Colima, Rancher Desktop, OrbStack and Lima all work, and Hezo finds the socket
itself (see [Container runtimes](./docs/deployment/container-runtimes.md)). Point the
instance at a [managed sandbox service](./docs/containers/remote/overview.md) instead and
**this machine needs no container runtime at all**. Either way you can switch later from
**Settings > Containers**. See [Containers](./docs/containers/overview.md).
**macOS / Linux**
```sh
curl -fsSL https://hezo.ai/install.sh | sh
```
**Windows** (PowerShell)
```powershell
irm https://hezo.ai/install.ps1 | iex
```
Then start the server:
```sh
hezo
```
Open **http://localhost:3100** and follow the [first-run setup](./docs/getting-started/first-run.md)
to create your master key and connect a model. From there, see
[Your first project](./docs/getting-started/first-project.md).
Prefer a manual download? Grab the binary for your platform straight from
[GitHub Releases](https://github.com/hezo-ai/hezo/releases/latest). Full steps and the
per-platform asset names are in [Installation](./docs/getting-started/installation.md).
### Deploy to a cloud server
Want an always-on instance instead of running it on your laptop? Deploy to a cloud
VM in a couple of minutes. Each provisions Docker, the binary, automatic HTTPS
(a real cert via `<ip>.sslip.io` - no domain needed), systemd, and a locked-down
firewall, and drops you at the in-browser setup.
<p>
<a href="https://ssh.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https://github.com/hezo-ai/hezo&cloudshell_workspace=deploy/gcp&cloudshell_tutorial=tutorial.md"><img src="https://img.shields.io/badge/Deploy_on-Google_Cloud-4285F4?style=for-the-badge&logo=googlecloud&logoColor=white" alt="Deploy on Google Cloud" height="34" /></a>
<a href="https://console.aws.amazon.com/cloudformation/home?region=us-east-1#/stacks/create/review?templateURL=https://hezo-deploy.s3.us-east-1.amazonaws.com/hezo.cfn.yaml&stackName=hezo"><img src="https://img.shields.io/badge/Deploy_on-AWS-FF9900?style=for-the-badge&logo=amazonwebservices&logoColor=white" alt="Deploy on AWS" height="34" /></a>
<a href="./docs/deployment/one-click.md"><img src="https://img.shields.io/badge/Deploy_on-DigitalOcean-0080FF?style=for-the-badge&logo=digitalocean&logoColor=white" alt="Deploy on DigitalOcean" height="34
... (truncated)Related Skills
More coding & development skills you might like
Reticle
Coding & DevelopmentAI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
🤖claude🌐universal
1.2k
190
View
agentscope-java
Coding & DevelopmentExpert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications.
🌐universal
6.0k
1.5k
View
ospec
Coding & DevelopmentDocument-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
✨gemini🤖claude💬gpt🌐universal
524
34
View
misakanet-failure-memory
Coding & Development📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org
🤖claude⌨️cursor🌐universal
424
158
View