Tom Wiltzius 737f4fe3aa Unify thread metadata updates above store
Make the ThreadStore contract coherent: append_items is now a raw canonical
history append, and update_thread_metadata is the single metadata write API.
ThreadStore implementations no longer infer metadata by inspecting appended
rollout items.

LiveThread now owns the live append flow. It applies the rollout persistence
policy before writing JSONL history, observes the canonical items with a small
ThreadMetadataSync helper, and sends the derived facts back through
update_thread_metadata. ThreadManager becomes the single app-facing metadata
entrypoint, routing loaded threads through LiveThread and cold threads directly
to the store.

LocalThreadStore preserves the local compatibility requirements inside the
local implementation. SQLite, when available, receives explicit metadata
updates. JSONL and name-index compatibility are still maintained for explicit
metadata mutations such as rename, memory-mode, and git changes, so old rollout
files and SQLite-less local storage remain readable.

RolloutRecorder is reduced to local JSONL writing for thread-store appends.
The shared rollout persistence policy remains in codex-rollout, but recorder no
longer owns live metadata synthesis. The added thread-store README captures the
new ownership boundaries for future remote and local implementations.
2026-05-12 13:17:13 -07:00
2026-04-24 17:49:29 -07:00
2025-04-16 12:56:08 -04:00
2025-04-16 12:56:08 -04:00
2026-04-24 17:49:29 -07:00
2026-04-07 10:55:58 -07:00

npm i -g @openai/codex
or brew install --cask codex

Codex CLI is a coding agent from OpenAI that runs locally on your computer.

Codex CLI splash


If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.
If you want the desktop app experience, run codex app or visit the Codex App page.
If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.


Quickstart

Installing and running Codex CLI

Install globally with your preferred package manager:

# Install using npm
npm install -g @openai/codex
# Install using Homebrew
brew install --cask codex

Then simply run codex to get started.

You can also go to the latest GitHub Release and download the appropriate binary for your platform.

Each GitHub Release contains many executables, but in practice, you likely want one of these:

  • macOS
    • Apple Silicon/arm64: codex-aarch64-apple-darwin.tar.gz
    • x86_64 (older Mac hardware): codex-x86_64-apple-darwin.tar.gz
  • Linux
    • x86_64: codex-x86_64-unknown-linux-musl.tar.gz
    • arm64: codex-aarch64-unknown-linux-musl.tar.gz

Each archive contains a single entry with the platform baked into the name (e.g., codex-x86_64-unknown-linux-musl), so you likely want to rename it to codex after extracting it.

Using Codex with your ChatGPT plan

Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan. Learn more about what's included in your ChatGPT plan.

You can also use Codex with an API key, but this requires additional setup.

Docs

This repository is licensed under the Apache-2.0 License.

S
Description
pinned at tag rust-v0.124.0 by vibe-kanban crates/executors
Readme Apache-2.0
1.6 GiB
Languages
Rust 96.8%
Python 2.4%
Starlark 0.2%
Shell 0.2%
TypeScript 0.1%
Other 0.1%