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:
The graph notices. The agent acts.
Raw events stream in and build a typed record. When it crosses a line you set, an agent flags it on its own and proposes the next step. Chat is just one surface; the same loop fires over MCP or HTTP.
From your data to an agent that acts.
Three steps. No data pipeline to wire up, no glue code to maintain.
Connect your data, in real time
Stream company data the moment it happens: 50+ built-in connectors, any MCP server, or your own in TypeScript. On-device connectors even capture context no cloud agent can see.
Connecting data →It builds itself into memory
Watchers turn the raw stream into typed, queryable records, the moment events arrive or on a schedule. You describe what to track in plain language; there's no ETL to maintain.
Watchers & memory →Agents act where your team works
On the model you choose, agents respond and flag what matters the moment memory changes, right where your team already works, as a Slack bot, an API, or another agent.
Building agents →It's all one typed file. lobu apply deploys it.
Curious how Lobu stacks up against other agent runtimes? See the comparison →
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.