Self-hosted · Latin: girded, encircled, contained

Your agents keep doing their job.

Nothing else.

You handed a program your keys, your files and an open socket. Cinctus is a self-hosted control plane that runs OpenClaw, Hermes, Claude Code — any MCP client — inside a sandbox that is locked down before you touch a single setting. Your keys, your files, your machine.

No account. No telemetry. One email when it ships, then we leave you alone.

AGPL core · Runs on a Pi or a €4 VPS · No vendor account

cinctus.local/agents/openclaw
CINCTUS
yourbox.lan · self-hosted
Overview
Agents 3
Egress
Vault
Approvals 1
Audit
Settings
perimeter · enforcing
egress · deny-all
vault · 0 keys in plaintext
Agents / openclaw
perimeter enforcing
egress deny-all
14:32
SANDBOX · ROOTLESS CONTAINER
openclaw running · 2 h 14 m
34 skills scanned · 2 flagged & quarantined · keys injected per call
cpu 2.0 · capped mem 512 MiB / 1 GiB mounts read-only wall-clock 4 h
Egress deny-all · 2 hosts allowed
live
14:31:52 api.anthropic.com:443 POST /v1/messages allowed
14:31:12
185.66.90.14:8080 unknown host
not on openclaw's allowlist · dropped, written to audit
blocked
14:31:07 api.telegram.org:443 approval notification allowed
14:29:41 api.anthropic.com:443 POST /v1/messages allowed
14:28:33 api.anthropic.com:443 POST /v1/messages allowed
everything else: dropped by default
Waiting for you 1 pending
send email — waiting for your approval
openclaw · requested 14:31 · via Telegram
Approve Deny
Audit today · spend $0.19
14:31 egress blocked → 185.66.90.14
14:31 approval requested · send email
14:29 model call · api.anthropic.com $0.0041
14:12 skill scan · 34 checked · 2 flagged
13:58 read /data/mail · read-only

01 — THE PROBLEM

You handed a program your keys, your files and an open socket.

Personal agents went mainstream in 2026 faster than any self-hosted tool before them. The security did not come along for the ride. These are the numbers from the last few months. None of them required an attacker to be clever.

1 click

Remote code execution

CVE-2026-25253. One link, and the agent's host is not yours any more.

NVD · CVSS 8.8

341

Malicious skills shipped

Found in one marketplace audit, installed by one click, running with your agent's full rights. Later scans found hundreds more.

Koi Security, Feb 2026

40,000+

Instances facing the internet

40,214 found in one scan, still rising. Most belong to someone who thinks they are on a LAN.

SecurityScorecard, Feb 2026

chmod 644

Where your API keys live

Plaintext, in a config file, next to the code that reads your email.

The tooling that fixes this exists — agent firewalls, MCP gateways, policy engines. All of it assumes you are a security engineer with a spare afternoon. Cinctus is the same primitives, assembled, with the safe setting already on.

02 — WHAT IT DOES

Six things, and it does them from the first boot.

No hardening guide, no policy language to learn. The defaults are the product; the settings are for loosening them on purpose.

$ docker compose up -d
▸ perimeter   up
▸ vault       up · 0 keys in plaintext
▸ egress     deny-all
$ cinctus adopt openclaw
scanning 34 skills … 2 flagged
agent openclaw is now cinctus

Per-agent sandbox

Rootless container, read-only mounts, hard wall-clock and memory limits. An agent that gets owned takes its own box down with it and nothing else.

Egress allowlist

Deny by default. The agent reaches the hosts you named and no others, and every outbound request is inspected and written down before it leaves.

Credential vault

Keys never enter an agent's config. They are injected for the call that needs them and revoked from one place when something smells wrong.

Skill & MCP scanner

Every skill and MCP server is checked against a reputation feed before it is allowed to run once. The feed gets better every time an install reports back.

Human approval

Spending money, sending mail, touching a repo — the actions you mark wait for your yes on Telegram, or whatever channel you already read.

Audit timeline

What ran, what it read, where it called, what it cost. One timeline you can scroll at 2am, and export when somebody asks you to prove it.

03 — THE CAVEATS

What Cinctus does not do.

You are going to run this on the machine that holds your life. You deserve the caveats before the pitch, not in a changelog eight months in.

It does not stop prompt injection.

Nobody's product does. Cinctus assumes the agent will eventually be talked into something stupid and makes that survivable.

It does not police what the agent is allowed to think.

Inside the permissions you granted, an agent can still do a bad job. That is your call to make, not ours.

It is not a managed service.

Nothing runs in our cloud. If your box is down, Cinctus is down, and that is the trade you came here for.

It does not exist yet.

This is a waitlist, not a download. First build lands [LAUNCH WINDOW] — and if it slips, you get the email that says so.

04 — PRICING

Free for a person. Paid for an organisation.

The line does not move. Everything one human needs to secure their own agents is free forever and stays in the open-source core — not a trial, not a seat count that shrinks next year.

CORE

AGPL
Freeforever
  • The whole cockpit, self-hosted
  • Sandbox, egress control, vault, approvals
  • Audit timeline and cost dashboard
  • One user, one instance

Open source. Fork it if we let you down.

PRO

€9/ month
  • Live reputation feed and rule updates
  • Secure remote access to your panel
  • Config backups and restore
  • Alerts when an agent trips a rule

Everything in Core, still on your box.

BUSINESS

€99/ month and up
  • Multiple users, SSO, roles
  • Central policy per agent
  • Exportable audit and log retention
  • Compliance reports

Priced per managed agent. Card, not a sales call.

Get one email when it ships.

We are building this in the open, alone, fast. The waitlist is how we decide whether to keep going — and it is where the first install instructions land.

Stored on our own box in Germany. Unsubscribe link in every mail. Never sold, never shared.