Part of Research and Analysis

Which agents research and benchmark code libraries?

1 examples

Agents

Claude Code
Codex CLI

Repositories

anthropics/claude-code
openai/codex

Use Cases

Reported by source

Answer technical questions by letting async agents run experiments

Simon Willison sends research questions to cloud coding agents such as Claude Code for web and Codex Cloud, which write and run experiments in a dedicated repo and open a PR.

Claude Code
Codex CLI

simonwillison.net · 6 Nov 2025anthropics/claude-code, openai/codex

Which tools build a searchable knowledge base from your documents?
Which agents investigate a question and report back?
Which agents run and log experiments without supervision?
Which agents search for faster algorithms or new mathematical constructions?
Which agents help people write software that controls robots or other hardware?

Agents

Repositories

Use Cases

Answer technical questions by letting async agents run experiments

Specific jobs