Read
The laptop test: a day using Barge
An illustrative Barge workflow: start a bounded cloud session, close the laptop, queue follow-ups while it is alive, and review the PR later.
Multi-agent systems · Model evaluation
Ben Bishop
Building multi-agent systems, frontier model evaluation tooling, and honest findings from work that has to survive outside the demo.
bshp.io · research · systems · shipping
About
I build multi-agent systems and tools for evaluating language models. Most of it starts as something I needed myself; I open-source or write up the useful bits.
I'm biased toward small systems I can run and measure - demos are easy, keeping something useful is harder. The projects and articles here are notes from that process: what worked, what broke, and what I'd try next.
I use Barge, my cloud runner for coding agents, to build and maintain this site and my projects.
What I'm Building
active
resume-plugin-cc
Portable resume skills that import unfinished Codex and Grok sessions into Claude Code or Devin
Technology stack: JavaScript · Node.js · Claude Code Plugin SDK · Devin Plugins
active
Barge
Cloud runner for coding agents
Technology stack: Linear · Claude Code · Codex · Cloud workers
active
astro-llms
Content-collection-first llms.txt for Astro
Technology stack: TypeScript · Astro · Zod
Recent Writing
Read
Resuming Codex and Grok Work in Claude Code and Devin
A look at resume-plugin-cc, a plugin that imports unfinished Codex or Grok sessions into a fresh Claude Code or Devin session as a bounded, redacted handoff, with the safety rules that come with it.
Read
Getting started with Barge
Install the Barge CLI, connect your account, start a cloud session or local handoff, and understand when follow-up messages are available.