Codex CLI 0.130.0 release
TL;DR
Codex CLI 0.130.0 introduces plugin hook details, a new 'codex remote-control' command for headless app-server management, thread pagination, and improved Bedrock authentication using AWS login profiles.
What changed
Codex CLI 0.130.0 adds explicit documentation for plugin hooks. A new codex remote-control command appears for managing the app server without a terminal interface. Thread pagination arrives to handle longer sessions cleanly. Improved Bedrock authentication now accepts standard AWS login profiles instead of separate keys.
Why it matters
Solo operators gain a path to run Codex agents on remote machines without constant SSH sessions. The remote-control addition signals OpenAI is betting on headless and scripted deployments rather than only local interactive use. Thread pagination reduces memory spikes during extended agent runs.
AWS profile support lowers friction for teams already inside AWS environments. This move pressures competing CLI tools that still require custom auth wrappers.
How to use it
Run npm install -g @openai/codex@0.130.0 to pull the release. Invoke codex remote-control with the required flags to start a daemon-managed session. Point Bedrock calls at an existing AWS named profile in your config file.
Full command reference lives at developers.openai.com/codex/cli/reference. Test pagination by starting a long thread and scrolling with the new controls.
Watch for
Stable daemon uptime over several days will confirm the remote-control bet. Crashes during pagination on threads above 50k tokens would break it. Expect an adjacent move toward managed remote environments listed in the registry next quarter.
Who this matters for
- Vibe Builders: Use the remote-control command to run persistent agents on servers without keeping a terminal open.
- Developers: Simplify AWS Bedrock integration by using standard login profiles instead of managing separate API keys.
Harsh’s take
The addition of a remote-control command is the standout feature here. It signals a shift from local CLI experimentation toward production-grade headless deployments. By allowing the app server to run as a daemon, OpenAI is making it easier for operators to host their own persistent agent infrastructure on remote VPS instances.
This reduces the friction of maintaining active SSH tunnels just to keep a process alive. Improved Bedrock authentication and thread pagination are necessary hygiene updates. Standardizing on AWS login profiles removes a common security headache for teams already deep in the Amazon ecosystem.
Pagination is a practical fix for the memory bloat that usually kills long-running agent sessions. This release is less about new AI capabilities and more about the boring, essential plumbing required to move agents out of the sandbox and into reliable server environments.
by Harsh Desai
About OpenAI Codex
View the full OpenAI Codex page →All OpenAI Codex updatesGo deeper
More AI news
- Daily RoundupGLM 5.3 and Vercel agent tools land, Gemini SAT practice, plus fresh models on Hugging Face
Google and Vercel released new agent and model features while Hugging Face and Replicate added trending models; OpenAI tightened safety after agent issues.
- Daily RoundupVercel-Origin beta and GPT-5.6 Sol discount, plus agent tools for builders
Vercel rolled out Origin repository deployments and a month-long GPT-5.6 Sol discount on AI Gateway while Product Hunt featured new agent layers and Hugging Face highlighted an uncensored Qwen model, with industry moves around data use and automation exits.
- Weekly DigestHermes Agent v0.20 voice and A2A protocol, OpenClaw mobile updates, and multi-agent tools to test now
Hermes Agent rolled out v0.20 releases with voice streaming, A2A interoperability, desktop artifacts, and self-recovery tools while OpenClaw added Android switching, iOS caching, and plugin provenance checks across the week.