Bring your agents
Connect ChatGPT, Claude, Codex, OpenClaw, or any MCP client to the same company context, scoped to each user.
Connect an agent →Reconcile payment sources against the ledger, explain any variances, and prep the reconciliation note.
See how ledger history, transactions, reconciliations, and sign-off connect without rebuilding context each run.
Connectors stream your databases, SaaS tools, files, devices, and internal APIs into context. Your systems of record stay where they are. Models, sandboxes, and devices are independent layers, credentials gateway-side. Flip the tabs to wire each one.
Connectors ↗Raw events resolve into people, customers, projects, policies, and goals, with the relationships between them. Every fact from the connectors above converges on the right record, carries its provenance, and is read under the caller's permissions.
Memory ↗A trigger — a schedule, or reactive to connector events — plus a plain-language prompt. Once defined it runs unprompted: scans memory, matches the trigger, and surfaces the work with the evidence attached.
Automations ↗“Each morning, reconcile every against and . When a explains a variance, attach it and ping the before close.”
ChatGPT, Claude, and Codex connect over MCP; Slack, Teams, and WhatsApp over chat; your own apps over the API. Same context, same permissions, whoever's asking. Consequential work arrives as a proposal you review, edit, and approve.
Platforms ↗Variance flagged · Account 4100
Drafted the month-end recon note for Maya. Review before I post it:
Use the agents your team already trusts. Managed agents are optional.
Connect ChatGPT, Claude, Codex, OpenClaw, or any MCP client to the same company context, scoped to each user.
Connect an agent →Run repeatable work from live events or schedules under the same approval policy.
Build a managed agent →Share context, permissions, approvals, and connected actions with any agent. Add Lobu's runtime only when you need it.







The use case above is one project: connections, entity types, automations, and agent configuration. Inspect each piece or let your coding agent generate it.
import {
connectorFromFile,
defineAgent,
defineConfig,
defineSkill,
defineEntityType,
defineRelationshipType,
defineAutomation,
every,
secret,
field,
} from "@lobu/cli/config";
import type QuickBooksTransactionsConnector from "./quickbooks-transactions.connector.ts";
const reconciliationMonitorSkill = defineSkill({
name: "reconciliation-monitor",
content:
'Check accounts for unreconciled transactions, new variances, and approaching reporting deadlines. Return actionable exceptions in `alerts` as standard observation event drafts. Put the readable exception in `content` and counts/details in `metadata` with `kind: "reconciliation_alert"`. Return an empty array when there is nothing to review.\n',
});
const finance = defineAgent({
id: "finance",
skills: [reconciliationMonitorSkill],
name: "finance",
description:
"Help finance teams reconcile data, explain variance, and prepare reporting runs",
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 reconciliationMonitor = defineAutomation({
agent: finance,
slug: "reconciliation-monitor",
name: "Reconciliation monitor",
triggers: [every("0 6 * * 1-5")],
tags: ["finance", "reconciliation", "daily"],
minCooldownSeconds: 3600,
outputs: { alerts: { event: "observation" } },
skills: ["reconciliation-monitor"],
});
export default defineConfig({
connectors: [
connectorFromFile<typeof QuickBooksTransactionsConnector>(
"./quickbooks-transactions.connector.ts"
),
],
org: "finance",
orgName: "Finance",
orgDescription:
"Help finance teams reconcile data, explain variance, and prepare reporting runs",
agents: [finance],
entities: [account, report, transaction, variance],
relationships: [createsVariance, reconcilesTo, summarizedIn],
automations: [reconciliationMonitor],
});Connect any agent to shared context and keep consequential actions under approval.