What is Hezo?
Hezo is an open source 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 hold the real value of a secret you store, everything sensitive is encrypted behind a
master key, and every project runs sandboxed in its own container.
Quickstart
Agents always run inside a container, so this machine needs a Docker-compatible runtime
(or point Hezo at a managed sandbox service and it
needs none). Everything else is in the binary.
1. Install. One self-contained binary, nothing to compile.
curl -fsSL https://hezo.ai/install.sh | sh
Windows (PowerShell):
irm https://hezo.ai/install.ps1 | iex
2. Start the server.
hezo
3. Open http://localhost:3100. Follow the
first-run setup to create your master key and
connect a model, then build your first project.
Docker, Colima, Rancher Desktop, OrbStack and Lima all work, and Hezo finds the socket
itself (see Container runtimes). Switch between
local and managed containers at any time from Settings > Containers; see
Containers. Prefer a manual download? Grab the binary from
GitHub Releases, with full per-platform
steps in Installation.
Two ways to run it
Self-host it. Free and open source under GPL-3.0. One binary, your machine, your
data, your model keys - start at Quickstart above. Want it always-on
rather than on your laptop? These provision a server in a couple of minutes, with
Docker, the binary, automatic HTTPS (a real cert via <ip>.sslip.io, no domain
needed), systemd and a locked-down firewall:
Google Cloud and AWS are one-click today - Google Cloud opens Cloud
Shell and runs the deploy, and AWS opens a CloudFormation Launch Stack.
DigitalOcean opens a short guide until its
Marketplace image is listed.
Any provider that takes cloud-init works too, and
One-click deploy covers which kind of
machine to pick and why.
Hezo Cloud. We run your instance at you.app.hezo.ai, agents run on
managed sandboxes, and you still bring your own model keys. Starts with a 7-day free
trial, and we don't ask for a card - see
hezo.ai/pricing, or
the docs.
How it works
- Create a project and pick a team. Launch a ready-made team from the
marketplace - App Team, Social Media Marketing or
Investment Portfolio - start from a
template, or ask the
CEO to assemble one for the work.
- Set the direction. Specify the project plan, shape the
team's structure, hire or customize
agents, and give any agent
its own model.
- The team gets to work. Agents pick up tasks and work
autonomously, asking for your approval
when needed. The project dashboard tells you where things
stand without your having to read the board.
Features
- Agents organised like a company. A global CEO and Coach
above per-team Captains and workers, with org charts
you reshape while a project runs.
- Tasks that run themselves. A task board with nested
sub-tasks, heartbeat wake-ups, approval gates, and long runs that resume on their own.
- Works on your real repositories. Agents clone, commit and push over your connected
GitHub account, and the signing key never enters the container,
so commits land verified.
- One platform layer over every model. The meta-harness
runs each model in its own first-party CLI, then levels the differences: the same tools,
skills, memory and sandbox whichever you pick, plus a completeness check that will not let
a run end on failing tests or an "out of scope" dodge. It runs on Claude Code, Codex and
Kimi Code. Grok Build and OpenCode cannot block a turn, and Hezo does not check Antigravity
runs yet, so runs on those three fail open.
- Agents never hold your secrets. Every credential is a
placeholder. The egress proxy swaps in the real
value only for the hosts you allowed.
- Your models, your spend. Bring your own provider accounts, give
any agent its own model, set budget caps, and see
cost per run.
- Container hours, not just tokens. A ledger of how long every container was up, with a
monthly allowance that stops new containers once
it is spent.
- Structure the team to the work - compose the roster, the reporting lines, and what each role is, change it while a project runs, and carry a structure you've tuned forward to the next one.
- Teams & projects - one team per project, launch a ready-made team from the marketplace or start from a template, hire and customize agents, snapshot a team to reuse, export one to share.
- Know where a project stands - a project dashboard leading with a summary the Captain keeps current on its own, with optional high-level goals and scheduled re-checks layered on top.
- Choose where containers run - on your own machine or a managed sandbox service, switchable either way at any time, with containers started on demand and a memory budget shared across every project.
Agents never hold your secrets
This is a big reason Hezo exists. Agents reference every credential by a placeholder -
never the real value:
Authorization: Bearer __HEZO_SECRET_STRIPE__
The real key lives encrypted in Hezo's vault. When the request leaves the container, the
egress proxy checks the destination against that secret's allowed hosts and swaps in
the real value only if it matches - say, api.stripe.com. Send it anywhere else and the
proxy blocks the request; the substitution never happens.
So a buggy, jailbroken, or outright malicious agent cannot leak what it never sees. It
can only use a secret against the hosts you scoped it to, and the value is never written to
a log line or to disk - diagnostics record the placeholder instead. One credential is the
exception: the model-provider key the agent's own CLI authenticates with, which reaches the
container in readable form because that traffic does not go through the proxy. The same posture runs end
to end: encrypted at rest behind your master key, every project sandboxed in its own
container, and an append-only audit trail of what people and agents did. See the security documentation
for the full picture.
Self-host it and the models you connect, the
machine, the data and the master key are all yours. On
Hezo Cloud we run the box and include AI inference on the
Base AI model, and any model account you connect is still billed to you by its
provider.
Works with your models
Bring your own provider accounts - connect as many as you like, and give any individual
agent its own model. Each provider is
driven through a first-party agentic command-line runtime inside the container.
Anthropic, OpenAI, Google and xAI each run on their own CLI; the
Anthropic-compatible providers run through Claude Code, and OpenRouter through
OpenCode. Hezo's meta-harness levels the differences, so
the tooling, memory and sandbox stay the same underneath whichever model you pick.
| Provider | Models | Runtime | Auth |
|---|
| Anthropic | Claude | Claude Code | API key or subscription |
| OpenAI | ChatGPT / GPT | Codex | API key or subscription |
| Google | Gemini | Antigravity | API key |
| xAI | Grok | Grok Build | API key |
| Kimi (Moonshot) | Kimi | Claude Code or Kimi Code | API key |
| DeepSeek | DeepSeek | Claude Code | API key |
| Z.ai | GLM | Claude Code | API key |
| OpenRouter | Many, via one account | OpenCode | API key |
| Ollama | Whatever you run locally | Claude Code | Server URL (key optional) |
| LM Studio | Whatever you run locally | Claude Code | Server URL (key optional) |
Where the Runtime column lists more than one, that credential chooses which CLI it runs on;
the first is the default, so adding a key without touching the setting works. You can
change it later, or rotate the stored key in place, without re-adding the connection.
Ollama and LM Studio run agents entirely on your own hardware at no per-token cost -
point Hezo at your server URL and leave the key blank.
Full details (subscriptions vs. API keys, mixing providers, per-agent overrides) in
AI model support.
Development
Contributor setup, scripts, and the testing guide live in
.github/CONTRIBUTING.md and AGENTS.md.
You'll need Bun v1.3.14+ and a Docker-compatible runtime.
git clone https://github.com/hezo-ai/hezo.git
cd hezo
bun install
bun run dev # server on :3100, web UI on http://localhost:5173
bun run test # the full test suite
Community & license
⭐ If Hezo is useful to you, a star helps other people find it. It is the main way an
open source project gets discovered, and it costs you one click.
Questions and bug reports are welcome via
GitHub Issues.
Copyright (C) 2026 Ramesh Nair.
Hezo is licensed under the GNU General Public License v3.0 or later.
X: @hezo_ai
