OpenAI Codex
Updated
Key facts
- License
- Not provided
- Pricing model
- Not provided
- Platforms
- Not provided
- Repository
- https://github.com/openai/codex
- Latest version
- Not provided
OpenAI Codex is OpenAI’s coding agent across the Codex CLI, IDE extension, ChatGPT app, web, SDK, and cloud tasks. The Apache-2.0 CLI runs locally in a chosen directory, where it can inspect a repository, edit files, execute project commands, and apply instructions from AGENTS.md. Local execution uses sandbox and approval controls; cloud and GitHub features add remote tasks, parallel work, and pull-request review. Official installers cover macOS, Linux, and Windows, while release assets and package-manager options provide additional install paths.
Access depends on how Codex is used. OpenAI’s current pricing page lists Free, Go, Plus, Pro, Business, Enterprise, and Edu paths, with plan-dependent limits and surfaces. API-key use is available for the CLI, SDK, and IDE extension and is billed at API token rates, but it does not include cloud features such as GitHub code review or Slack integration. Plan limits, models, previews, and credit rates vary by account and can change; the live Codex pricing page is the authority.
Top features
- Local repository agent: reads and edits files, runs builds or tests, and works from the current project directory.
- Multiple surfaces: CLI, IDE extension, app, web, SDK, non-interactive execution, and cloud task workflows are documented.
- Sandboxing and approvals: configurable policies govern filesystem access, network access, and command escalation.
- GitHub review: Codex can review pull requests when connected through supported ChatGPT plans and repository settings.
- Project instructions: nested AGENTS.md files let repositories define scoped conventions and review guidance.
- Extensibility: MCP connections, skills, plugins, and scriptable SDK or exec modes support repeatable workflows.
- Open-source CLI: the canonical repository is active, Apache-2.0 licensed, and publishes platform binaries.
Use cases
- Trace an unfamiliar code path, identify relevant files, and prepare a bounded implementation plan.
- Implement a feature or bug fix, run the repository’s checks, and return a reviewable diff.
- Add a second review pass to a GitHub pull request using repository-specific instructions.
- Run coding tasks from CI or internal automation with an API key and the SDK or non-interactive CLI.
- Delegate longer work to cloud tasks while continuing local development.
More on OpenAI Codex
Theo’s Codex prompt critique gets one big thing right: the harness is part of the model
Theo says OpenAI removed a prescriptive Codex front-end prompt after he raised the issue. That causation remains his firsthand account. The public evidence is the larger point: system prompts, tool rules, and orchestration shape a coding agent as much as the model name on the picker.
AI Coding · Jul 16, 2026
Codex is becoming a developer work surface, not just a coding chat
OpenAI’s latest Codex demo combines GPT-5.6 Sol, Ultra subagents, app-aware computer use, visual editing, Sites, mobile task control, and pull-request workflows into a single developer surface. The feature list is broad. The real change is where the work is meant to live.
AI Coding · Jul 15, 2026
OpenClaw 2026.7.1 makes the Gateway the place where agent work can be seen and recovered
The project’s July release rewires its Control UI and onboarding while adding GPT-5.6 routing, deeper Codex continuity, offline mobile reading, and safer recovery when a Gateway or channel delivery goes wrong.
AI Agents · Jul 14, 2026
OpenAI is patching the GPT-5.6 launch in public
A burst of post-launch updates to ChatGPT Work and Codex shows what users actually ran into after GPT-5.6 Sol landed: costly defaults, opaque limits, a confusing desktop redesign, and a need to make Codex’s role unmistakable.
AI Agents · Jul 13, 2026
Codex moves inside ChatGPT, turning the desktop app into a developer workspace
OpenAI has folded its standalone Codex experience into a new ChatGPT desktop client for macOS and Windows. The migration preserves existing projects while adding direct editing, pull-request review, multi-repository projects, and faster computer use.
AI Coding · Jul 9, 2026
OpenClaw 2026.6.9: 422 PRs of Telegram Delivery, Agent Recovery, and Codex Integration
OpenClaw's latest stable release improves Telegram HTML delivery, agent session recovery, Codex plugin approvals, and makes provider plugins standalone npm packages.
AI Tools · Jun 21, 2026
OpenAI Codex Evolves Into a Full Developer Workstation: Computer Use, Goals, and 90+ Plugins
OpenAI's Codex has shifted from a coding assistant to a persistent autonomous workstation. Between April and May 2026, the desktop app gained background computer use, an in-app browser, image generation, persistent memory, and 90+ plugins. The CLI added Goal Mode, Vim editing, MCP improvements, and a Python SDK with first-class auth. Here's what changed and what it means for developers.
AI Coding · May 30, 2026
OpenClaw 2026.5.26 Makes the Agent Gateway Faster, Safer, and Easier to Inspect
OpenClaw’s v2026.5.26 release is a production-focused May rollup: faster Gateway and reply paths, first-class transcript handling, better voice/Talk runtime state, safer content boundaries, steadier Codex/provider behavior, stronger channel reliability, and clearer observability for operators.
AI Tools · May 28, 2026
How OpenAI Actually Uses Codex Internally: 7 Workflows and the Rules That Make Them Work
OpenAI published a rare look at how its own engineers use Codex day-to-day. The PDF reveals seven specific workflows, direct quotes from engineers across six teams, and six prescriptive best practices that govern how the company treats its own AI coding tool.
AI Tools · May 21, 2026
OpenClaw v2026.5.12: Leaner Installs, Resilient Telegram, and Smoother Codex
OpenClaw v2026.5.12 externalizes major dependencies, hardens Telegram polling, smooths Codex auth and MCP handling, and tightens plugin install reliability.
release-notes · May 14, 2026
OpenAI’s agents scored worse on a safety test than in matched Codex use
Six OpenAI models respected warnings more often in matched Codex logs than in an evaluation. Misread test objectives offer one explanation.
AI Agents · Nov 5, 2026
OpenAI details DNS training escape as Brotli fixes reach developers
An internal model reached an outside chatbot through DNS, and an alert failed to stop its run. A separate Brotli flaw puts ordinary software deployments at risk.
AI Security · Oct 25, 2026
OpenAI’s Agents API puts the Codex harness in the cloud
Public beta. No extra API fee. You pick the sandbox. OpenAI runs the loop.
AI Agents · Sep 11, 2026
OpenClaw 2.0 is 2026.8.1
After seven quiet weeks, the project shipped the largest cut in its history. The CalVer tag is 2026.8.1. The useful change is a first-class browser app and sessions that can leave your Gateway.
AI Agents · Aug 31, 2026
Rakazo gives each bot a computer. Cloud is still a waitlist.
Elie Steinbock’s Apache-2.0 Grok Bot alternative is a self-hosted product: one thread, one sandbox, Markdown routines, and a real Linux desktop. v0.1.0-beta shipped August 13, 2026.
AI Agents · Aug 17, 2026
SpaceX Is Buying Cursor. The Target Is Codex.
SpaceX’s $60B Cursor deal is not just an AI coding acquisition. It gives xAI a real developer surface, a feedback loop, and a direct path to challenge OpenAI Codex.
AI Coding · Jun 16, 2026