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.

GitHubLinkedInNotion50+ more
Reuse a prebuilt connector, or point Lobu at any database you use.
Your agent writes code to pull profiles and launches.
2

Define the goal

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

“Match community members to new launches and posts in their space, and draft intro messages for the best two matches.”

Runs unattended · posts to #community-matches.Watchers
3

Lobu works autonomously

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

Live member memory · 315 membersmember
Sarah
Needs · embeddings, MCP
wants intros
topics embeddings · MCPmatches Devon · Mira
Derived from recent events:
Asked for two intros in embeddings infra
15m ago · Sarah
Devon shipped an embeddings eval harness
9m ago · GitHub
Mira posted an MCP auth breakdown
3m ago · Community feed
Devon Linopen to intros
Mira Satoactive
+ 312 more membersMemory & entities
4

You review and approve

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

C
Community agent
online
Top matches for Sarah this week: Devon Lin (shipped a similar embeddings eval harness) and Mira Sato (deep MCP work). Want me to draft intros to both?12:01
Yes, reference Devon's repo.12:01
Drafted both, referencing Devon's repo and Mira's post. Queued in your outbox.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,
  reactionFromFile,
  secret,
} from "@lobu/cli/config";
import type DiscoursePostsConnector from "./discourse-posts.connector.ts";
import type opportunityMatcherReaction from "./opportunity-matcher.reaction.ts";

const agentCommunity = defineAgent({
  id: "agent-community",
  name: "agent-community",
  description:
    "Discover aligned members, explain why they should meet, and draft warm introductions",
  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 opportunityMatcher = defineWatcher({
  agent: agentCommunity,
  slug: "opportunity-matcher",
  name: "Opportunity matcher",
  schedule: "0 */12 * * *",
  notification: { priority: "normal" },
  tags: ["community", "matching"],
  minCooldownSeconds: 300,
  reaction: reactionFromFile<typeof opportunityMatcherReaction>(
    "./opportunity-matcher.reaction.ts"
  ),
  prompt:
    "Monitor connected profiles, newsletters, websites, and member updates for new launches, posts, hiring signals, funding news, and project changes. Identify which members are likely to care, explain why, and queue approved intro or outreach drafts.\n",
});

export default defineConfig({
  connectors: [
    connectorFromFile<typeof DiscoursePostsConnector>(
      "./discourse-posts.connector.ts"
    ),
  ],
  org: "agent-community",
  orgName: "Agent Community",
  orgDescription:
    "Discover aligned members, explain why they should meet, and draft warm introductions",
  agents: [agentCommunity],
  entities: [match, post, topic],
  relationships: [interestedIn, introducedTo, matchesWith, writesAbout],
  watchers: [opportunityMatcher],
});
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.