Build proactive AI agents on a graph
that builds itself
Connect your company's data in real time, plug in your model, and let your agents act the moment something changes, as a bot, an API, or another agent.
Paste it into claude code, cursor, or opencode, and it scaffolds the project for you.
Or start it yourself:
Raw events in. Typed memory out. Agents act.
Connectors stream events into memory. Watchers derive typed entities. Agents read it, talk to users, and act.
One typed file wires it together.
Pick a piece to see the code for this use case. Click again to hide.
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",
extractionSchema: {
type: "object",
required: ["signals"],
properties: {
signals: {
type: "array",
items: {
type: "object",
properties: {
type: { type: "string" },
source: { type: "string" },
related_topics: { type: "array", items: { type: "string" } },
interested_members: { type: "array", items: { type: "string" } },
reason: { type: "string" },
suggested_action: { type: "string" },
},
},
},
},
},
});
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],
});Pick a use case to see it end to end.
Each page walks through the connectors, memory shape, and watchers for one team — and ships as a working example you can lobu apply.
Local, your cloud, or Lobu Cloud.
Same lobu.config.ts + *.connector.ts + agents/. One command to boot embedded; Docker + Helm for self-hosting; Lobu Cloud when you don't want to run it yourself.
Embedded, single process.
Gateway, workers, memory, embeddings, all in one Node process. Postgres is the only external.
$ lobu run → gateway :8787 → worker pid=<n> → memory N entities → watchers N armed
Docker. Helm. Your cloud.
Helm chart and Dockerfiles in the repo (charts/lobu/, docker/app/). Run on GCP, AWS, Fly, Render, or bare metal.
# Kubernetes $ helm install lobu ./charts/lobu # Docker $ docker build -f docker/app/Dockerfile .
Managed runtime.
Same code, run by Lobu. Per-user isolation, secret proxy, automatic upgrades.
$ lobu apply → org <your-org> → region <your-region> → agents N deployed → gateway <your-org>.lobu.run
Build your first
multi-user agent.
Latest blog posts
Shopify's Aquifer, in the Open
Shopify bet that an agent's corpus is the compounding asset. We made the same bet, with two differences: we keep the signal instead of the chat, and we built it for many companies instead of one.
Filesystem vs Database for Agent Memory
Agents need a workspace to think in and a warehouse to remember in. The filesystem is for ephemeral work. The memory layer is for durable organizational knowledge.
MCP Is Overengineered, Skills Are Too Primitive
MCP HTTP is great for external services. MCP stdio is redundant. And most skill systems are just prompt text with no reproducibility. Here's what we built instead.