Openclawd From Scratch
Build Your Own OpenClaw From Scratch is a hands-on series where we rebuild an OpenClaw-style agent from first principles. Starting from a blank file, we'll implement the core agent loop, tool use, sandboxed execution on Modal. By the end, you'll have an agent that can install what it needs, run real workflows, and evolve over time.
The Lay of the Land
Breaking down OpenClaw-style agents and the roadmap for building one from scratch
Coding agents are no longer a novelty; they're quickly becoming the default interface for writing code, running workflows, and automating personal operations. Yet, most of the systems we use today…
It's alive!
Allowing an agent to modify itself with tools
The code for this article is available here. The difference between a chatbot and an agent is simple: agents can act. Think of this as our Frankenstein moment: it's alive, and it can use tools. For…
ET Phone Home
Deploying our agent on Telegram with ngrok so it can report back
Our agent can read, write and even extend itself - but right now it's stuck in a terminal. In this post, we'll fix that by allowing you to message it from your phone and watch it work in real time.…
Total Recall
Persisting conversations to a database and compacting context so our agent never forgets
Our agent can talk over Telegram, call tools, and even extend itself — but it has the memory of a goldfish. Every time the server restarts, the conversation vanishes. Send enough messages and the…