Your content,
operated by AI.

LumiBase is the Content Operating System — agents do the operational work, you set the intent and hold the veto.

AI Harness

Agents operate your content. You set the intent — and hold the veto.

Goals, runs & real skills

The first-class API is a goal, not a click. Agents pursue it through governed skills — every run inspectable, replayable, and attributed.

✓Draft 12 release notesL2 · auto

⏸Rewrite pricing pageawaiting approval

✓Translate docs → vi + enL3 · veto window

•Reconcile SEO titlesrunning

Trust gradient · L0–L4

Autonomy is earned, not granted. Promotion is data — clean runs and passing evaluations. Demotion on incident is automatic.

Currently at L3 — Veto window. A dangerous action executes into a staged revision and auto-commits after the window. Silence commits; the kill switch stays armed.

Human-in-the-loop

schema:write and delete always route through approval — at every autonomy level, with no exceptions.

Provenance-first

Every revision records agent, run, model, references, and approver — served on the Delivery API with ?provenance=true.

agent:writer-2drafted body · run #482

human:maiapproved · constitution ✓

agent:translatorlocalized vi → en

Content OS

Declare the desired state. LumiBase reconciles content toward it, continuously.

Read the vision

Intent-driven, not click-driven

The unit of work is an intent with an SLO. Content that violates its SLO is an incident — detected, raised as a goal, fixed within a write budget.

Every product: ≥1 image · 50–200 words · vi+enSet intent

desired

82% converged

Reconciliation loop

Content drifts; a control loop pulls it back. Live state, not last-edit state — the Kubernetes idea, applied to content.

Tenant Constitution

Versioned, hashed publish gates encode your taste and policy. What fails the constitution never ships — at any autonomy level.

Multi-agent newsroom

Writer, reviewer, translator, SEO — narrow per-role grants, cross-review between agents, and a hard self-review ban.

✍Writer

✦Reviewer

⟳Translator

◎SEO

Studio

Mission control — humans supervise the system instead of hand-editing every item.

Tour the Studio

No-code Collection Builder

Model any content shape without migrations or code — drag-drop UI and live JSON schema, kept in sync both ways.

titlestring

slugstring

authorm2o → users

bodyrichtext · encrypted

Field-level permissions

RBAC down to the individual field via a JSON policy engine — plus per-field AES-GCM encryption for the data that matters.

Security

Exception inbox & trust ledger

Approvals, veto windows, incidents, and the kill switch in one queue. You review exceptions — not everything.

Mission Control

Realtime collaboration

Presence, live subscriptions, and per-field pin badges over WebSocket — humans and agents on the same content.

Runtime

Edge-native, never locked in — Cloudflare Workers or self-hosted Docker, one abstraction.

Read the docs

Typegen + SDK

Your schema becomes TypeScript types, and a full JS/TS SDK covers auth, items, files, and realtime.

import { createClient } from '@lumibase/sdk'
const db = createClient<Schema>(url)
const posts = await db.items('posts').read()

Runtime abstraction

@lumibase/runtime swaps cache, storage, DB, search, and queues per deployment target. Business logic never touches a vendor binding.

MCP server

Your content becomes tools any AI assistant can call — the API and MCP are the front door, the UI is a projection.

⌘

@lumibase/mcp-server

ClickHouse CDC + materialized reads

Stream every change out; materialize hot read paths for the edge. Analytics without touching the write path.

Postgres→CDC→ClickHouse

Questions, answered

What is a Content Operating System?

A traditional CMS is a tool humans use to manipulate content one operation at a time. A Content Operating System inverts that: you declare the desired state of your content (its SLOs), and a control loop of governed AI agents continuously reconciles content toward that state — with full provenance and human veto. LumiBase is that runtime.

How is this different from an AI plugin bolted onto a CMS?

Autonomy in LumiBase is earned, not granted. Every (site, agent, capability) sits on a trust ladder from L0 (shadow) to L4 (autopilot). Agents are promoted by passing evaluations and auto-demoted on incidents. Every action is gated by a versioned tenant constitution and recorded with provenance.

Do humans lose control?

No. Humans set intent, taste, and policy, and hold the veto. The L3 veto window stages dangerous changes and commits them only if no human objects within a time budget. A four-scope kill switch can halt agents instantly. Nothing publishes that fails the constitution.

Is it open source?

Yes. The core LumiBase is free forever under the Apache 2.0 license. It runs edge-native on Cloudflare Workers and can also be self-hosted with Docker via a shared runtime abstraction.

Run your content like a system.

Declare the desired state. Let governed agents converge it. Keep the veto. Free forever under Apache 2.0.

Start building Documentation

Your content,operated by AI.