Build AI teammates that watch and act

Open-source infrastructure for AI teammates that watch, remember, and act. Connectors and webhooks build a live org knowledge graph; agents look it up and branch into a sandbox to do work.

Paste into your coding agent to scaffold a project.

Or start it yourself:

1

Connect your data

Pick the systems it can read. Lobu turns those updates into live customer memory.

NotionGoogle DriveGmail50+ more
Reuse a prebuilt connector, or point Lobu at any database you use.
Your agent writes code to read memos and minutes.
2

Define the goal

Tell it what to watch for and when to ask before acting.

“Summarize new board memos: what was approved, what is blocked, and who owns each next action.”

Runs unattended · posts to #exec-digest.Watchers
3

Lobu works autonomously

It scans memory on schedule, spots the account at risk, and keeps the evidence attached.

Live decision memory · 11 memosdecision
Board memo Q4
Owner · Priya
action needed
approved Series A bridgeblocked Frankfurt lease
Derived from recent events:
Board memo Q4 posted to the exec workspace
1h ago · Notion
Bridge approved, hiring freeze reaffirmed
1h ago · Board notes
Frankfurt lease counter due Apr 25
55m ago · Slack
Board memo Q3closed
Offsite planapproved
+ 9 more memosMemory & entities
4

You review and approve

You can edit the draft, send it, or leave it.

C
Chief of staff
online
Board approved the $4M Series A bridge and the Q1 hiring freeze. Blocked: the Frankfurt lease, pending legal diligence. Want the exec digest with owners?12:01
Yes, and flag Priya's deadline.12:01
Drafted. Priya owns the Frankfurt counter, due Fri Apr 25. Posted to #exec-digest.12:01
Replies in your team's chat, or your own app over the API:
For engineers

The whole agent, in code.

One project defines it end to end: the agent, its connectors, the memory schema, watchers, and skills. Write it yourself, or let your coding agent generate it. Pick a piece to read the code.

lobu.config.tslobu.config.ts
import {
  connectorFromFile,
  defineAgent,
  defineConfig,
  defineEntityType,
  defineRelationshipType,
  defineWatcher,
  secret,
} from "@lobu/cli/config";
import type LinearCyclesConnector from "./linear-cycles.connector.ts";

const leadership = defineAgent({
  id: "leadership",
  name: "leadership",
  description:
    "Help leadership teams turn memos, decisions, and board materials into reusable operating context",
  dir: ".",
  providers: [
    {
      id: "anthropic",
      model: "claude/sonnet-4-5",
      key: secret("ANTHROPIC_API_KEY"),
    },
  ],
  network: {
    allowed: [
      "github.com",
      ".github.com",
      ".githubusercontent.com",
      "registry.npmjs.org",
      ".npmjs.org",
    ],
  },
});

// entity types and relationships defined here…

const boardActionTracker = defineWatcher({
  agent: leadership,
  slug: "board-action-tracker",
  name: "Board action tracker",
  schedule: "0 8 * * *",
  notification: { priority: "high", channel: "both" },
  tags: ["leadership", "daily", "board"],
  agentKind: "notifier",
  prompt:
    "Track board action items: check task delivery status, blocker resolution progress, and approaching deadlines for the next board packet.\n",
});

export default defineConfig({
  connectors: [
    connectorFromFile<typeof LinearCyclesConnector>(
      "./linear-cycles.connector.ts"
    ),
  ],
  org: "leadership",
  orgName: "Leadership",
  orgDescription:
    "Turn memos, decisions, and board materials into reusable operating context",
  agents: [leadership],
  entities: [decision, document, region, risk, task],
  relationships: [approved, assigned, blockedBy],
  watchers: [boardActionTracker],
});
Examples

Explore agent workflows.

Each example shows the sources, memory, and actions for one AI teammate.

Run anywhere

Local, self-hosted, or managed.

Local

Run on your laptop.

Boot the gateway, workers, memory, and embeddings with one command.

Self-host

Run in your cloud.

Docker, cloud VM, or Kubernetes when data and controls need to stay with you.

Lobu Cloud

Let Lobu run it.

Use the same project with managed isolation, secrets, and upgrades.

Build your first
multi-user agent.