In private preview

Host the agents you already run,
right next to your app.

Lucity runs the agent from your terminal as it is, around the clock. It wakes on the events you choose, reaches only what you allow and keeps a record of every call. A cloud platform made in Switzerland and hosted in the EU.

Your apps can move in today. Agents arrive in your workspace the day they open, nothing to sign up for twice.

  1. CreateYou create an agent on the harness you already use, and tell it its job.
  2. Wake02:14. Your laptop is shut. A deploy fails, and the trigger wakes the agent.
  3. ThinkIt thinks with your model. Lucity adds the key at the wall, so the agent never holds it.
  4. ReadIt reads the build logs and the code. Reading is all you granted.
  5. AskThe fix is a rollback. That is a write, so the agent has to ask first.
  6. NotifyYour phone buzzes.
  7. ApproveYou tap Approve.
  8. ActThe rollback goes through. Every step of the night is on the record.
Always onIt runs on Lucity, not on a laptop. Asleep until something wakes it, at work seconds later.
Under your controlIt starts with nothing. You grant each model, tool and host, the keys stay with you, and every call is on record.
Built from partsTriggers, connectors, model providers and channels. Connect each once, combine them in plain words.

Works with the agents, models and tools you already use. No framework to adopt.

Always on,
long after you log off.

A hosted agent does not wait for your terminal. It sleeps until something happens, does the work, and tells your team in the chat they already use.

A failed deploy wakes it.

Lucity's own events are triggers: failed builds and deploys, crash loops, full disks, new vulnerabilities and expiring certificates.

Every trigger

Deploy doctor, yesterday

Awake for 11 minutes. Asleep, and nearly free, the rest of the day.

Deploysapi, release 214
Lucity

The deploy of api failed while building.

Deploy doctor

On it. Reading the build log and the last three commits.

Deploy doctor

The build needs STRIPE_WEBHOOK_SECRET since commit 4f2a91c, and it is not set at build time. The previous release still serves traffic. Should I add the variable from the shared group and redeploy?

Add and redeployNot now
Asleep when idleNo work, no bill worth mentioning. A trigger wakes it in seconds.
Picks up where it left offFiles, memory and conversations survive restarts, deploys and sleep.
A sandbox of its ownEach agent runs isolated, on infrastructure built for other people's code.
Answers where you talkTelegram, Mattermost, Slack, Teams or the dashboard, approvals included.

Under your control,
down to a single tool.

Every agent starts with nothing. You hand it each model, tool and host on purpose, the keys never go inside it, and you can read back everything it did.

Night watch · access

  • Model: Mistral Largeallowed
  • Lucity: logs, metrics, deploysallowed
  • Lucity: memory, instances, rollbacksasks Ops first
  • Lucity: delete anythinghidden
  • Sentry: read issuesallowed
  • Linear: create issuesasks first
  • Internet: status.mistral.aiallowed
  • Network: other services in productionoff
  • Model spend per day€20, then it stops

Shop on call · 03:13

Night watch wants to set the memory of web to 1 GB.

Changes to production need a yes from someone in Ops. The agent cannot answer for itself.

ApproveDeny
Grants, one by oneAllowed, asks first or hidden, down to a single tool of a single connector.
Keys stay outsideLucity adds the key as a call leaves. The agent never holds one, so it cannot leak one.
A yes from the right personRisky calls wait. You decide who may answer, and they answer from wherever they are.
A record of every callModel calls, tool calls and approvals, kept for a year, searchable and exportable.

Also included: a list of hosts each agent may reach, a daily spend limit, step by step replay of any run, and export of the record to your own bucket. How agent security works

Built from parts,
not from a framework.

An agent is a harness you know, instructions in plain words and four kinds of parts. Connect a part once, and every agent in the workspace can use it when you allow it.

Pick the agent you already run in your terminal and paste its instructions file. That is the whole move.

  • Open harnesses, pinned and kept up to date for you
  • One plain text file of instructions, the one you already have
  • Skills and subagents come along
  • Export an agent and run it anywhere a container runs

An event, a schedule or a message starts a conversation. Events about the same thing land in the same one, so a flapping service is one thread, not forty.

  • From Lucity: failed deploys, crash loops, full disks, new vulnerabilities
  • From your tools: alerts, new issues, new errors
  • Any schedule, in your time zone
  • A signed webhook, or an email to the agent's own address

Every trigger

Any remote MCP server becomes a connector, and so does your own API. The agent calls a tool, and Lucity adds the key on the way out.

  • Lucity itself: logs, metrics, deploys, rollbacks, variables
  • GitHub, Linear, Jira, Sentry, Grafana and Notion in one click
  • Your own API, from its OpenAPI file
  • Allowed, asks first or hidden, tool by tool

Every connector

Connect the providers you already pay for. Each conversation picks its model and how hard it thinks, and the bill stays with your provider.

  • No markup on tokens, ever
  • European providers for work that has to stay in Europe
  • Any OpenAI-compatible API, including models you host yourself
  • A daily spend limit per agent

Every model provider

An agent answers in the chats you add it to. Teammates link their account once, so it knows who is asking, and who said yes.

  • A thread or topic per conversation
  • Approvals as buttons, right in the chat
  • The dashboard and the API for everything else

Every channel

Claude Code
Codex
OpenCode
Pi
Yours next

Agents ship the way your apps do.

An agent lives in an environment, next to the services it looks after. Try a change in staging, promote it to production, roll it back when it misbehaves.

Right next to your appAn agent reaches the services of its environment by name, when you let it. No tunnels, no public endpoints.
Every change is a versionInstructions, grants and triggers are versioned together, with who changed what.
One click to productionPromote the agent you tried in staging, exactly as it was.

Night watch · versions

v14stagingAlso watch the worker queueNoa · 2 hours agoPromote
v13productionAsk Ops before any rollbackChristian · Tuesdaylive
v12earlierReport to Shop on callNoa · 2 NovemberRoll back

What it costs, and where it runs.

Billed while awakeAn agent is billed like a service, by the memory and CPU it uses while it works. Asleep, it costs next to nothing.
Models at costModel calls go on your own provider bill, at their price. We add no markup and resell no tokens.
In EuropeAgents run in the EU, operated from Switzerland. Pair one with a European model provider and its work stays in Europe.
Nothing of ours insideThe harness is open and the instructions are a text file. Export an agent and run it wherever a container runs.

Before you move an agent over

Still wondering about something? Ask about agents

No. Pick the harness you use locally, paste its instructions and connect the same tools. The agent behaves the way it did in your terminal, minus the terminal.

Claude Code, Codex, OpenCode and Pi today, and the list keeps growing. If it runs in a terminal and reads an instructions file, it is a candidate. Tell us which one you are missing.

No. A held call waits outside the sandbox, and only the people your rule names can answer it, from the chat or the dashboard. The agent sees the answer, never the button.

The agent sleeps and costs next to nothing. An event, a schedule or a message wakes it in seconds, with its files and conversations where it left them.

Yes. It drives Lucity through the plugin as before. Hosted agents take the work that should not wait until you are back at your desk.

Any provider your workspace connects, from Anthropic and OpenAI to Mistral, Infomaniak or a model you host yourself. Each conversation can pick its own model and effort.

In the EU, inside your workspace, operated by a Swiss company. Pair it with a European model provider and nothing the agent does leaves Europe.

Move one agent off your laptop.

1
Pick its harness

The one you run in your terminal today.

2
Paste its instructions

The instructions file you already have works as it is.

3
Tell it when to wake

A deploy fails, an alert fires, or every weekday at 06:00.