Codex bundles LibreOffice
- ID
- 20346
- Status
- summarized
- Published
- 02 Sep 2026, 3:03 AM
- Fetched
- 02 Sep 2026, 3:11 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Sep/1/codex-libreoffice/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 6.5
- Created
- 02 Sep 2026, 3:11 AM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Simon Willison discovered that the OpenAI Codex desktop app (now rebranded as ChatGPT) caches 1.7GB of runtimes in ~/.cache/codex-runtimes/codex-primary-runtime/, including full Python, Node.js, Poppler, git, and LibreOffice installations. A skills folder instructs Codex on how to locate and use these bundled binaries for document processing.
Why it matters
If you're building AI agent tooling, this reveals how OpenAI approaches local document handling—bundling heavyweight runtimes like LibreOffice directly into the desktop app rather than relying on server-side conversion. Builders shipping desktop AI agents should consider whether similar local-runtime bundling is necessary for reliable document parsing, and check their own cache directories for unexpected disk usage from AI tooling.
Discussion angle
What does bundling LibreOffice locally tell us about the limits of server-side document processing for AI agents, and should Malaysian builders working on agent tooling adopt similar local-runtime strategies?