Codex CLI
OpenAITerminal coding agent from OpenAI, written in Rust. It reads a codebase, proposes a plan and executes multi-file changes with sandboxed command execution, and documents writable roots, permission profiles, agent approvals, auto-review, MCP connectors and skills. Desktop builds are offered for Linux and Windows.
Codex runs against either a ChatGPT plan or an API key. Verified 2026-08-13 via the OpenAI Codex CLI documentation.
Openness
5 high confidence- license
- Apache-2.0(OSI, the CLI agent)
- source
- public(GitHub)
- note
- agent is OSS but optimized for/defaults to OpenAI models (provider-leaning, not license-restricted)
- core-gated
- ungated(one Apache-2.0 LICENSE at the root governs the whole tree
Apache-2.0, an OSI-approved license, with public Rust source (96.1% Rust); OpenAI's own docs call it open source. The backing models are proprietary, but the orchestration agent scored here is fully open. A full recursive tree of openai/codex at main, untruncated, carries exactly one governing LICENSE - the root Apache-2.0 - and the only other license files cover vendored third-party dependencies (third_party/wezterm, codex-rs/vendor/bubblewrap) and sample skill assets. There is no enterprise or commercial directory, which is the test for whether a core has been carved out. What you pay for is model access: the README directs you to sign in with a ChatGPT Plus, Pro, Business, Edu or Enterprise plan, or with an API key. That is a hosted service sold alongside the published agent rather than a feature withheld from it, so nothing gates the core.
- https://github.com/openai/codex recorded 2026-06-04
Apache-2.0 license, public Rust source, v0.137.0 Jun 4 2026, 88.6k stars (verified)
- https://developers.openai.com/codex/cli recorded 2026-06-04
OpenAI describes Codex CLI as open source
- https://api.github.com/repos/openai/codex/git/trees/main?recursive=1 recorded 2026-08-11
Full untruncated recursive tree. The only LICENSE paths are the root `LICENSE`, `third_party/wezterm/LICENSE`, `codex-rs/vendor/bubblewrap/LICENSE`, `docs/license.md` and four sample-skill asset licenses. No enterprise/, ee/ or commercial/ directory anywhere in the tree.
- https://api.github.com/repos/openai/codex recorded 2026-08-11
Repo metadata: language Rust, license spdx_id Apache-2.0, size 549,758 KB, 105,340 stars, 'Lightweight coding agent that runs in your terminal'.
- https://raw.githubusercontent.com/openai/codex/main/README.md recorded 2026-08-11
'Using Codex with your ChatGPT plan - Run `codex` and select Sign in with ChatGPT ... to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.' and 'You can also use Codex with an API key'. The paid relationship is model access, not a withheld CLI feature.
Adoption
4 high confidenceOpenAI has disclosed that Codex passed 4 million weekly developers, and the Wikipedia article on the agent cites more than 6 million weekly active users - both firmly in the 1-10M band on disclosed developer count. The OpenAI announcement carrying the original figure is no longer fetchable, since openai.com answers 403 to a non-browser request, so the band rests on the larger Wikipedia-cited number instead. What is banded is a weekly active count rather than the monthly count the scale is written in, so if anything it understates a monthly reading.
- https://openai.com/index/scaling-codex-to-enterprises-worldwide/ recorded 2026-06-04
OpenAI: Codex surpassed 4M weekly developers (Apr 2026). Not re-fetchable - openai.com answers 403 to a non-browser request.
- https://en.wikipedia.org/wiki/OpenAI_Codex_(AI_agent) recorded 2026-08-13
tracks the disclosed figures with citations - more than 2 million weekly active users by March 2026, rising to 6 million weekly active users, with Cisco, Nvidia, Ramp, Rakuten and Harvey named as deployments
- https://github.com/openai/codex recorded 2026-08-13
105.7k stars, 16.0k forks, broad active install base (corroborating)
Capability
4 medium confidenceCapable, heavily-used coding agent backed by frontier OpenAI models, but no standalone agent SWE-bench placement published. Scored on feature matrix; high but not the open-agent benchmark frontier-definer (OpenHands 68.4%).
- https://developers.openai.com/codex/cli recorded 2026-08-13
autonomous terminal agent documented across sandboxing and writable roots, permissions and profiles, agent approvals and security, auto-review, MCP and connectors, skills and plugins, and Linux/Windows desktop apps; no benchmark figure published for the agent
Verified 2026-08-11