Openai open-sourced codex harness, the runtime that actually runs codex — sessions, context, tool…
openai open-sourced codex harness, the runtime that actually runs codex — sessions, context, tool wiring — so anyone can build their own coding agent on it. the agent business is splitting into model, harness, and everything else.
the harness is where the moats are being redrawn.
Context
OpenAI's developer blog on Codex as a platform, with a metadata date of 19 August 2026, says the open-source Codex harness powers its experiences, helping models gather context, reason, use tools, operate within configured boundaries, request approval and carry work forward. It reports that retained reasoning and context compaction raised GPT-5.6 Sol on ARC-AGI-3 from 13.3% to 38.3% with sixfold fewer output tokens, an OpenAI-reported result. The github.com/openai/codex repository is Apache 2.0 licensed, and an OpenAI post of 4 February 2026 says the harness and the Codex App Server, a JSON-RPC API, power the web app, CLI, IDE extension and macOS app.
A dated announcement of open-sourcing the harness, as distinct from the long-running public Codex CLI repository, was not found, and the August post treats it as already open, so the note's implied recent event is unverified. Whether the repository contains the full runtime or only the CLI and App Server was not examined. Anyone can build an agent on it is supported in spirit by the platform post; the moat framing is the author's opinion.
Related work
Watch next
- Repository release notes and the App Server docs.
Sources
- Codex as a platform (OpenAI developers)developers.openai.com
- openai/codex (GitHub)github.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 09:24 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →