Agor Cloud - Opening a Private Beta

Agor is BSL-licensed and vastly open source. You’re free to run it however you want—you just can’t commercialize it. It has all the building blocks for anyone without commercial intent to build next-gen, multi-agent, multiplayer servers that can really change how you build software.

So why Agor Cloud?

The Gap Between “Works for Me” and “Works for Production”

Here’s what we learned productionizing Agor at Preset for our own use:

When you’re excited about shared dev environments, worktrees, and AI sessions, you quickly realize the scale of what it takes to run this safely in production:

A stateful database that needs backups and migrations
API keys for multiple agent providers (Claude, Gemini, Codex)
Prompt injection risks when agents have filesystem access
User isolation so one developer’s session doesn’t stomp another’s
Docker resource containment—when people can fire up dev environments at the click of a button, you need resource isolation to ensure core services remain healthy while people go to town on the shared box
Observability across a fleet of dev environments
Analytics to understand usage patterns and costs
Policies to prevent runaway token spend

The insight: The best people to operate any given piece of software are the people building that software.

We’re building Agor. We’re running it in production for ourselves. And as a SaaS company offering Preset Cloud, we had all the infrastructure expertise in place to do this right—for us and for anyone else who wants it.

What Agor Cloud Offers

Agor Cloud is a fully managed service, turnkey. Up in minutes, reliable, always running the latest fully secured version of Agor with all the bells and whistles.

Unix-Level User Isolation

We’re bringing back shared, fat servers—the right way.

If you’re going to share and collaborate on dev environments, there’s no way around this: each user needs real isolation. Not just process separation, not just containers, but Unix-level user isolation.

Every developer gets their own Unix user on the Agor server. Worktrees, sessions, and dev environments run as that user. Filesystem permissions enforce boundaries. No accidental cross-contamination, no leaky abstractions.

This is how multi-user systems were designed to work. Agor Cloud makes it seamless.

Always Up

Managing a large box running all sorts of dev environments is challenging:

Docker containers that need health checks
Background processes that hang
Disk space that fills up
Network ports that collide
SSH tunnels that disconnect

Agor Cloud ensures the infrastructure stays healthy. Monitoring, auto-recovery, capacity management—handled.

You focus on building. We focus on keeping the lights on.

Analytics Dashboards

Want to see who’s using AI? How much? Who’s ramping slowly? Where the token spend is going?

Agor Cloud comes with embedded, rich, interactive reporting through Preset Portals.

Every Agor Cloud instance includes a fully-loaded Preset (managed Apache Superset) workspace. Pre-built dashboards show:

Token usage by user, worktree, and repo
Cost breakdown by agent type (Claude, Codex, Gemini)
Session duration and completion rates
Worktree lifecycle metrics
Agent performance and error rates

You get full SQL access to your Agor database through Superset, so you can build custom reports for your team’s workflow.

All your PDLC (Product Development Life Cycle) and AI development data in one place. Explore it however you want.

Usage Policies

AI is powerful. It’s also expensive. You want to enable usage, but you probably want guardrails:

Token quotas per user or team
Rate limits to prevent chain reactions
Max concurrent sessions to manage compute load
Approval workflows for high-cost operations
Spending caps to avoid surprise bills

Agor Cloud lets you configure policies that fit your team’s needs. Enable the productivity boost, contain the blast radius.

CI-Ready: Agents That Don’t Disappear

Being able to @claude and @codex in GitHub issues and pull requests has made GitHub a better place for all of us and our agents. But there are clear limitations:

The problem with ephemeral CI agents:

You hope the agent will one-shot the solution in CI
Things remain opaque—you can’t see what the agent actually did
Sessions are ephemeral—once the job finishes, the context vanishes
You can’t reuse the context window that was built up
No way to say “that was close, but can you also check X?”
Missing context about how the branch got built in the first place

How nice would it be if agents in CI could:

Work with live dev environments instead of cold checkouts
Access the full context of how the branch was built
Persist their sessions so you can go in and ask for a few more things
Appear on your board alongside your other work, not in a black box

That’s exactly what Agor Cloud enables.

With Agor Cloud, you can allow your agents in CI to benefit from everything across the Agor platform:

See CI-triggered sessions spawn in your Agor environment in real-time
Watch agents work with full visibility into tool use, file reads, and reasoning
Resume sessions after CI completes—“Thanks for the review, now can you fix the issues you found?”
Reuse context from the session that created the branch
Connect to live dev environments instead of starting from scratch
Track genealogy from issue → PR → review → fixes—all as a session tree

Getting something like that to work securely can be quite complex—API authentication, user isolation, secret management, network access controls. Agor Cloud handles all of it.

Your CI agents become first-class citizens in your Agor environment, not ephemeral scripts that run and disappear.

Full Observability

If you’re using Agor to spin up dev environments—likely through Docker, Kubernetes, or local processes—you need visibility into what’s running and how it’s performing.

Agor Cloud provides:

Multi-cast observability - logs and metrics flow to both your tools and ours
Integration with your existing stack - StatsD, Datadog, CloudWatch, Prometheus
Built-in dashboards - CPU, memory, disk, network for every environment
Alerting - get notified when environments spike, disk space runs low, or processes hang

You maintain full observability on a system that’s quickly becoming critical to your PDLC. We ensure our internal monitoring doesn’t interfere with yours—multi-cast means both systems see the same data stream.

Agor becomes the heart of your development process. You need visibility into it just like you need visibility into production.

Who Agor Cloud Is For

Teams that want shared dev environments without the ops burden
Engineering orgs exploring AI-assisted development at scale
Companies with security and compliance requirements that rule out running open source locally
Teams that need analytics and cost controls around AI usage
Anyone who wants Agor’s capabilities without managing infrastructure

Signing Up for the Private Beta

We’re scaling this aggressively but cautiously. Agor Cloud is quickly becoming critical to team productivity, so we’re onboarding carefully to ensure every deployment is solid.

If you’re interested in a fully-loaded, hassle-free solution for you and your team, join our private beta.

Here’s how it works:

Fill out the interest form - Tell us about your team and use case
Quick discovery call - We’ll chat about fit and requirements (15 minutes)
Onboarding - Once we establish fit, you’ll be set up in minutes
Trial period - Use Agor Cloud, see if it delivers value for your workflow
Decide - If it’s solving real problems, stay on. If not, no hard feelings.

We’re not trying to sell you something you don’t need. We’re looking for teams where Agor Cloud makes a measurable difference—faster onboarding, better collaboration, cleaner development workflows, controlled AI spend.

Join the Private Beta →

What You Get

Dedicated Agor instance with your team’s repos and worktrees
Unix-level user isolation for secure multi-tenant development
Preset Cloud workspace with pre-built analytics dashboards
Policy controls for token quotas, rate limits, and spending caps
Full observability integrated with your existing monitoring stack
Managed infrastructure - backups, updates, monitoring, support
Direct access to the team building Agor - fast feedback loop, feature requests welcome

Pricing

We’re figuring this out during the private beta. Usage-based makes sense (token usage, active users, worktree count). We’ll work with early customers to find a model that’s fair and sustainable.

For now, focus is on fit and value. Pricing comes after we’ve proven this solves real problems.

Why Trust Us with This?

At Preset, we run Preset Cloud—a managed Apache Superset service used by thousands of teams. We know how to:

Operate multi-tenant SaaS infrastructure at scale
Handle security, compliance, and data isolation
Provide enterprise-grade observability and analytics
Support teams with mission-critical workflows

We’re building Agor Cloud because we’re running Agor ourselves. The features we’re adding are the ones we need. The operational experience we’re developing is the same rigor we apply to Preset Cloud.

You’re not getting a side project. You’re getting a fully supported service from a team that depends on it running flawlessly.

Open Source + Managed Service

Agor remains open source (BSL). You can still run it yourself if that fits your workflow better.

Agor Cloud is for teams that want the capabilities without the ops burden. No Docker config, no database migrations, no monitoring setup, no capacity planning. Just the platform, running reliably, with all the enterprise features baked in.

The open source project benefits too: production learnings at Preset feed back into Agor’s core. Better security, better performance, better defaults—everyone wins.

Let’s Get Cooking

AI-assisted development is changing how we build software. But the tooling around it—observability, cost controls, collaboration, security—hasn’t caught up.

Agor Cloud bridges that gap. Fully managed, secure, observable, built by the team using it every day.

If that sounds like what your team needs, we’d love to talk.

Join the Private Beta →

Questions? Reach out:

If you’re running Agor open source and want to share your experience, we’d love to hear about it. Open a discussion or drop us a note—your feedback shapes where this goes next.

Making of Agor Context Engineering