Agents × Infrastructure

Orchestrate AI agents on
your own VPS and your own terms..

Scroll
[ Dashboard Preview ] Built on OpenClaw
Cortex — AI agent orchestration dashboard powered by OpenClaw
Agent orchestration workflows, skills, monitoring
[ The problem ]

Running
AI agents
is still chaos.

01 Operations
  • No control plane

    Your agents run on scattered machines with no unified way to dispatch, monitor, or stop them.

  • Blind execution

    No visibility into what agents are doing in real-time. Failures are discovered hours later in logs.

  • Manual everything

    Task dispatch, approvals, retries, escalations — all requires SSH-ing into machines.

02 Engineering
  • Disposable prompts

    Prompts and agent instructions are copy-pasted, never versioned. No skill reuse across agents.

  • No pipelines

    Complex tasks require multi-step coordination. Without a workflow engine, you chain scripts and pray.

  • Infra is an afterthought

    Security, networking, container isolation — bolted on later instead of built in from day one.

[ What we're building ]

One platform
to orchestrate them all.

01 /04
01 WORKFLOWS

Deterministic pipelines

YAML-defined DAG workflows with parallel step execution, dependency resolution, context propagation between steps, and automatic retry with configurable fallback strategies.

YAML + DAG
02 SKILLS

Portable agent capabilities

SKILL.md files synced natively to agent workspaces. Import from the marketplace, create your own, or version them in Git. Agents load skills automatically.

SKILL.md
03 AUTOPILOT

Scheduled autonomous scanning

Cron-based repo scanning with multi-agent parallel analysis. Auto-generates structured proposals with risk assessment. Approve or let it execute.

Cron + proposals
04 OBSERVABILITY

Real-time operational dashboard

Live task feeds via Convex real-time subscriptions. Workflow step-by-step progress, agent status, cost tracking per task. Two UIs: Dashboard and Mission Control.

Real-time
[ Under the hood ]

Your infrastructure.
Our orchestration.

Cortex runs on your own servers. Here is what powers it.

VPS

Hetzner / AWS / Any Linux host

Your agents run on your own machines. Full control over CPU, memory, and storage. No shared infrastructure.

NETWORK

Tailscale mesh VPN

Zero-trust networking between your VPS and Cortex. No public ports. Encrypted WireGuard tunnels. Agents unreachable from the internet.

RUNTIME

OpenClaw in Docker containers

Each agent runs in its own isolated container with the OpenClaw runtime. WebSocket protocol v3 for bidirectional communication. Workspace-level file isolation.

BRIDGE

Gateway (Express + WebSocket)

Push-based architecture: Convex dispatches tasks to the gateway, which routes them to the right agent via OpenClaw. No polling. Real-time response streaming.

BACKEND

Convex real-time database

Serverless functions, real-time subscriptions, and transactional consistency. Dashboard and Mission Control get instant updates without refresh.

[ Product in action ]

DASHBOARD & MISSION CONTROL

Configure agents, launch workflows, and monitor everything in real-time. Powered by Convex subscriptions.

CHANNELS
LIVE CH.01 — Dashboard --:--:--
Cortex dashboard - overviewCortex dashboard - workflowsCortex dashboard - skills libraryCortex dashboard - agent configCortex dashboard - proposalsCortex dashboard - autopilot
MISSION CONTROL
Cortex mission control - kanban
Kanban
Cortex mission control - activity
Activity
Cortex mission control - costs
Costs
Cortex mission control - tasks
Tasks
Cortex mission control - docs
Docs
[ Why now ]

Built on OpenClaw,
launched as Cortex.

Open
core

Cortex is built on OpenClaw, an open-source AI agent runtime. Your agents, your infra, your data. No vendor lock-in.

No vendor lock-in.

Shape
the roadmap

Early adopters get direct access to the founding team. Your feedback drives what we build next.

Your feedback drives what we build next.

First-mover
advantage

Production-ready agent orchestration before the market catches up. Skills, workflows, and infrastructure — ready now.

Ready now.

[ How it works ]

Simple. Powerful.

1
2
3
4
01 5 min

Provision your VPS

Deploy on Hetzner, AWS, or any Linux host. One Docker Compose file brings up OpenClaw agents, the WebSocket gateway, and the reverse proxy.

02 10 min

Secure the network

Tailscale mesh VPN connects your VPS to Cortex. Agents run in isolated Docker containers. No public ports exposed except the gateway.

03 15 min

Configure from the dashboard

Define agent roles, assign skills, create YAML workflows. Everything is managed from the Cortex dashboard — no SSH needed after initial setup.

04 Ongoing

Monitor and scale

Tasks flow through the gateway in real-time. Review proposals, approve workflows, track costs. Add agents as you grow — same infrastructure, more capacity.

[ Pricing ]

THREE PLANS,
one mission.

All prices in EUR. No hidden fees. Cancel anytime.

Starter

For solo developers shipping with one agent.

29 EUR
/mo
Agents 1
Runs / day 5
Autopilot
Skills 10
Support Community
Recommended
Pro

For teams automating their development workflow.

79 EUR
/mo
Agents 4
Runs / day 50
Autopilot
Skills 50
Support Priority
Team

For organizations that need full control at scale.

149 EUR
/mo
Agents 4
Runs / day
Autopilot
Skills
Support Dedicated
[ Get started ]

Ready to deploy your agents?

Start with a Hetzner VPS and a Docker Compose file. Full orchestration in minutes.

Free tier available. No credit card required.