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,
secret,
} from "@lobu/cli/config";
import type DocuSignEnvelopesConnector from "./docusign-envelopes.connector.ts";
const legalReview = defineAgent({
id: "legal-review",
name: "legal-review",
description:
"Review contracts, summarize risk, and surface missing protections",
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 contractReviewTracker = defineWatcher({
agent: legalReview,
slug: "contract-review-tracker",
name: "Contract review tracker",
schedule: "0 8 * * 1-5",
notification: { priority: "high" },
tags: ["legal", "contract", "daily"],
minCooldownSeconds: 1800,
reactionsGuidance:
"For any contract with `status: needs_counsel`, route an entity-scoped event\nto the assigned reviewer. For contracts >90 days unsigned, escalate to the\ncounterparty owner; never auto-resolve risk items.\n",
prompt:
"Review active contracts for approaching deadlines, unsigned agreements, and unresolved risk items. Flag any clauses that still need counsel approval.\n",
extractionSchema: {
type: "object",
required: [
"pending_contracts",
"unresolved_risks",
"approaching_deadlines",
],
properties: {
pending_contracts: { type: "array", items: { type: "string" } },
unresolved_risks: { type: "array", items: { type: "string" } },
approaching_deadlines: { type: "array", items: { type: "string" } },
flagged_clauses: { type: "array", items: { type: "string" } },
},
},
});
export default defineConfig({
connectors: [
connectorFromFile<typeof DocuSignEnvelopesConnector>(
"./docusign-envelopes.connector.ts"
),
],
org: "legal-review",
orgName: "Legal",
orgDescription:
"Review contracts, summarize risk, and surface missing protections",
agents: [legalReview],
entities: [clause, contract, counterparty, risk],
relationships: [belongsToCounterparty, containsClause, createsRisk],
watchers: [contractReviewTracker],
});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.