# openai/codex

> A local coding agent from OpenAI that runs in the terminal: installed with one command and used as a CLI tool for working with code.

- Magnitude: 3.9 out of 10 — Steady
- Stars: 132,883 total · +144 stars measured 2026-11-02, 00:07–23:04 UTC
- Star trust: star growth looks organic
- Category: AI agents · Language: Rust · License: Apache-2.0 · Created: 2025-04-13 · Last push: 2026-11-02
- GitHub: https://github.com/openai/codex · Page: https://gitnova.dev/en/r/openai/codex

## Useful for

- Run codex in the terminal to automate edits in a project
- Install the agent via npm, Homebrew, or a standalone script on macOS, Linux, and Windows
- Sign in with a ChatGPT account to use Codex under a Plus or Pro plan

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 00:07–23:04: 132739 → 132883 stars (+144). This is the change over that interval.
- Hacker News: “Codex is EATING my Mac's disk space” — 176 points, 16 days ago.
- About 46 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 21,014
- Issues and pull requests: 57,419
- Watchers: 662
- Average over the last week: 284 per day
- Usual pace: 171 per day
- Stars in the last hour (measured): 4
- Latest release: rust-v0.167.0-alpha.3 (2026-11-01)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 116, 116, 137, 203, 203, 198, 147, 159, 208, 206, 194, 169, 129, 126, 162, 177, 212, 179, 170, 193, 124, 150, 163, 290, 158, 152, 612, 391, 239, 144

## Magnitude by day, last 14 days

10-20 5.4, 10-21 4.1, 10-22 4.3, 10-23 4.3, 10-24 4.1, 10-25 3.7, 10-26 3.9, 10-27 4.4, 10-28 4.3, 10-29 4.0, 10-30 4.4, 10-31 6.0, 11-01 5.1, 11-02 4.1

## Hacker News

- Codex CLI installs a persistent, self-updating background daemon by default — 609 points, 294 comments: https://news.ycombinator.com/item?id=50060694
- Codex is EATING my Mac's disk space — 176 points, 88 comments: https://news.ycombinator.com/item?id=50133231

## Similar by description

1. **xai-org/grok-build** — 2.0 · Steady · AI agents · Rust · +13 stars measured 2026-11-02, 00:12–23:08 UTC
   SpaceXAI's terminal-based AI coding agent: a fullscreen TUI that understands your codebase, edits files, runs shell commands, searches the web, and manages long-running tasks — interactively, headlessly, or via ACP in editors.
   Full card: https://gitnova.dev/en/r/xai-org/grok-build.md
2. **anomalyco/opencode** — 3.7 · Steady · AI agents · TypeScript · +251 stars measured 2026-11-02, 00:08–23:04 UTC
   Open source AI coding agent with terminal and desktop interfaces. Ships with a build agent (full edit and command access) and a read-only plan agent for code analysis.
   Full card: https://gitnova.dev/en/r/anomalyco/opencode.md
3. **openai/openai-cli** — 1.0 · Cooling · Developer tools · Go · +2 stars measured 2026-11-02, 00:16–23:13 UTC
   Official Go CLI for the OpenAI REST API: work with responses, files, images, and admin endpoints from the terminal. Simplifies API calls and scripted automation without writing code.
   Full card: https://gitnova.dev/en/r/openai/openai-cli.md
4. **MoonshotAI/kimi-code** — 2.2 · Steady · AI agents · TypeScript · +13 stars measured 2026-11-02, 00:12–23:08 UTC
   Kimi Code CLI is a terminal AI coding agent that reads and edits code, runs shell commands, searches files and fetches web pages, using Kimi models or other compatible providers.
   Full card: https://gitnova.dev/en/r/MoonshotAI/kimi-code.md
5. **QwenLM/qwen-code** — 2.3 · Steady · AI agents · TypeScript · +39 stars measured 2026-11-02, 00:12–23:07 UTC
   An open-source AI coding agent that runs in the terminal, editors, desktop, browser, and chat. Supports OpenAI, Anthropic, Gemini, Qwen and local models, plus MCP, SubAgents and headless mode.
   Full card: https://gitnova.dev/en/r/QwenLM/qwen-code.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 23:16 UTC, updated every 30 minutes.