Codex CLI 0.130.0 Adds `remote-control`, Richer Plugin Sharing Metadata, and Better App-Server Thread Paging
OpenAI shipped Codex CLI 0.130.0 in May 2026. The release adds a new `codex remote-control` command for starting a headless, remotely controllable app-server, improves app-server clients with paging options for large threads (unloaded/summary/full turn items), expands plugin sharing with link metadata and discoverability controls, adds Bedrock auth support for AWS console-login credentials from `aws login` profiles, and fixes several app-server/thread reliability issues.
OpenAI published Codex CLI 0.130.0 in the May 2026 section of the official Codex changelog, positioning it as the next step after 0.129.0's TUI-focused improvements. The headline is a new codex remote-control command for starting a headless, remotely controllable app-server, plus concrete improvements to plugin sharing metadata and app-server client behavior for large threads.
Key Takeaways
- New headless entrypoint:
codex remote-controlis a simpler way to start a headless, remotely controllable app-server. - Large-thread paging controls: app-server clients can page large threads with unloaded, summary, or full turn item views.
- Richer plugin sharing: plugin details now show bundled hooks, and plugin sharing exposes link metadata plus discoverability controls.
- Better Bedrock auth ergonomics: Bedrock auth can use AWS console-login credentials from
aws loginprofiles. - Reliability fixes: live app-server threads now pick up config changes without a restart, and several thread/diff operations behave more predictably.
What Changed: New Features (from the official changelog)
| Area | What changed | Why it matters |
|---|---|---|
| App-server | Added codex remote-control as a simpler entrypoint for starting a headless, remotely controllable app-server. | Makes it easier to run Codex as a service or integrate it into other automation where the UI is not the primary surface. |
| App-server clients | Clients can page large threads with unloaded, summary, or full turn item views. | Large histories are a reality for multi-day agent workflows; paging reduces client overhead and makes “resume where I left off” feel snappier. |
| Plugins | Plugin details now show bundled hooks; plugin sharing exposes link metadata plus discoverability controls. | Improves the ergonomics of distributing plugins and understanding what a shared plugin actually includes. |
| Auth (Bedrock) | Bedrock auth can use AWS console-login credentials from aws login profiles. | Reduces friction for teams authenticating to Bedrock via AWS SSO/console login flows. |
| Multi-environment sessions | view_image can resolve files through the selected environment for multi-environment sessions. | Helps when the file you want to inspect exists only inside the active environment (remote/container/sandbox). |
Bug Fixes Worth Noting
0.130.0 also includes several fixes that are specifically relevant if you rely on Codex's app-server and long-lived threads:
- Live app-server threads pick up config changes without requiring a restart.
- Turn diffs stay accurate across apply-patch operations, including partial failures that still mutated files.
- Thread summaries/renames/resume/fork paths work better through
ThreadStore, including threads without local rollout paths.
Sources
- Codex changelog: https://developers.openai.com/codex/changelog
Read next
Keep building the workspace playbookCodex CLI 0.129.0 Adds Modal Vim Composer, Redesigned Resume/Fork Picker, and a `/hooks` Browser
OpenAI shipped Codex CLI 0.129.0 on May 7, 2026. The release brings modal Vim editing to the TUI composer via `/vim`, a redesigned resume/fork picker with raw scrollback and workspace-aware `/diff`, a new `/hooks` browser with before/after compaction support, expanded plugin management with workspace sharing and access controls, theme-aware status lines, and Codex Apps auth surfaced through Guardian. Plus a long bug-fix list across Linux/Windows sandboxes, MCP, and TUI input handling.
Codex CLI vs Claude Code vs Cursor: 2026 Architecture Deep-Dive (Sandboxing, Context, Plugins, Scheduling)
Codex CLI, Claude Code, and Cursor all reach for the same outcome -- an AI agent that ships code -- with three different architectures. Codex enforces safety at the OS kernel layer. Claude Code uses application-layer hooks for programmable governance. Cursor builds the agent into a visual IDE with a marketplace of plugins. The right one depends less on which model you prefer and more on which architecture matches your security posture, your composition needs, and your team shape.
Frequently Asked Questions
What shipped in Codex CLI 0.130.0?
Per the official Codex changelog, Codex CLI 0.130.0 adds a `codex remote-control` entrypoint for starting a headless app-server, lets app-server clients page large threads using unloaded/summary/full turn item views, expands plugin sharing metadata (including link metadata and discoverability controls), adds Bedrock auth support for AWS console-login credentials from `aws login` profiles, and fixes several app-server and thread reliability issues.
What is `codex remote-control`?
`codex remote-control` is a new top-level command that starts Codex's app-server in a headless mode designed to be remotely controlled. Compared to launching the app-server indirectly, it is a simpler, explicit entrypoint for teams that run Codex as a service or integrate it into other tooling.
Why does app-server thread paging matter?
If you run Codex for long sessions, threads can become large. 0.130.0 adds client-side paging options so the client can request unloaded, summary, or full turn item views, which is a practical improvement for performance and UX when browsing big histories.