All work

OpenClaw

A self-hosted AI gateway. One Node.js service owns the model connection and serves the same assistant to Discord and Telegram.

Role
Solo build
Stack
Node.js, LLM APIs, Discord, Telegram
Status
In daily use

The problem

An assistant spread across a browser tab, a phone app and a chat window is really three assistants. I wanted one service that owns the model connection and the configuration, runs on hardware I control, and answers wherever I already am.

What I built

  • The gateway. A Node.js service that holds the provider connection and reads one JSON config file.
  • Jarvis on Discord. The main interface, because Discord is where I already spend my time.
  • A Telegram adapter. Added second, to prove a new surface doesn't touch the core.
  • Readable failures. When something breaks, the log says what and where.

How it works

Tried firstGroq

Fast, but rate limits made it unreliable for something always on.

Tried secondCerebras

Hit the same wall from a different direction.

CurrentNVIDIA

Nemotron through NVIDIA's hosted API. Stable enough to forget about.

EvaluatingOpenRouter

Pay-per-use access to Claude, so cost follows actual use.

Two providers failing the same way told me reliability was the real design constraint, not model quality. The provider sits behind a boundary, so every switch was a config change and neither bot needed rewriting.

Next up: separate Dev and Biz agents as their own Discord bots, GitHub integration so the assistant can act on repositories, and finishing the OpenRouter cost comparison.

What I learned

  • Rate limits and provider reliability shaped the architecture more than model choice did.
  • Draw the boundary before the first migration and the second one is cheap.
  • Self-hosting trades convenience for control. Make that trade on purpose.
  • Tool use, streaming and prompt structure came straight from the Anthropic Claude API course.
Next project Websites