Simon Willison Terminal Agents Stack
Uses Claude Code, Codex CLI, and Gemini CLI as 'terminal agents' for async code research. Fires off 2-3 research projects daily, checks back 10 minutes later. Coined the term 'terminal agents' for this category.
3
Skills
2025-06
Verified
Persona
Skills in this bundle
Claude Code
Anthropic's official agentic coding CLI. Terminal-native, tool-use-driven, with deep file system and shell access. #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue (fastest enterprise SaaS to $1B ARR). 8M+ npm weekly downloads. Opus 4.6 with 1M context.
★ 80K+
Codex CLI
OpenAI's open-source coding agent built in Rust. Terminal-Bench 77.3% (GPT-5.3-Codex), SWE-bench Pro standardized 41.04%. 3-4x more token-efficient than Claude Code, 60-75% cheaper per task. Free with ChatGPT subscription, sandbox-first execution, 619 releases in 10 months.
★ 66K+
Gemini CLI
Google's open-source terminal agent with Gemini 3 models, 1M token context, built-in Google Search grounding, and the best free tier in the category (1K req/day). 97.9K stars, 444 contributors. SWE-bench Pro standardized 43.30% (#2 behind Claude Code).
★ 98K+
Build your own stack.
See all ranked skills and find the best fit for your workflow.
Source
X post: 'Claude Code, OpenAI Codex (CLI) and now Gemini CLI — we need a name for this category'
View source →Last verified: 2025-06