Your Company is a Filesystem

Eli Mernit makes a compelling case: if an AI agent’s architecture boils down to “filesystem as state + LLM as orchestrator,” then modeling an entire company as a filesystem gives agents the unified namespace they need to actually solve business problems.

As someone who uses AI tools daily to run an e-commerce business, this resonates — so much of my workflow is essentially moving data between siloed systems. A shared filesystem would be a game changer.

Original source: Eli Mernit (@mernit)

One of the reasons OpenClaw is so good is because its entire context is a filesystem on your computer.

OpenClaw runs on a computer and lets you talk to it via a chat app like Telegram or iMessage. When you ask it to run a task, it calls the Claude API and uses context from files on your machine. Your conversation with OpenClaw is represented as a file on the computer. When you run a task, OpenClaw writes to that file. The filesystem is the state.

As you add more data to those files, OpenClaw becomes more powerful and useful. When you connect your Gmail, OpenClaw has emails as files on your computer. When you connect your Eight Sleep bed, OpenClaw adds your sleep data to a file on the computer.

But if OpenClaw is useful for our personal lives, how powerful would OpenClaw (or other AI agents) actually be if an entire company was represented as a filesystem it could work in?

Take a law firm as an example. The entire back office operation is just a state machine — new cases go to /cases, time entries to /billing/time-sheet. Permissions naturally map to seniority: associates get read/write on their cases, partners access everyone’s. The governance structure is just Unix file permissions.

One reason that rolling out agents at enterprises is complicated is because data is siloed across many different systems. Invoices are in Quickbooks, emails are in Outlook, proposals live in Sharepoint, contracts live in Netsuite. There is no shared namespace to access all this data across the business. By modeling a company like a filesystem, agents can access nearly all the data they need to get the right context and make decisions.

There’s obviously nuance to all businesses, and many work streams are codified in people’s heads — not in JSON files. But the power of OpenClaw and the underlying architecture points to a future where the filesystem becomes the source of truth for the agents that are the most useful.

The past year has been explosive for AI agents. But when you tear away the noise, the architecture of an AI agent can be reduced to two components: the filesystem as state, and Claude as the orchestrator. By modeling the company as a filesystem, an agent is able to solve business problems by simply reading and writing files.