#codexcli — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #codexcli, aggregated by home.social.
-
Codex CLI vs Claude Code 🚀
Codex CLI (OpenAI) brilla por su velocidad (hecho en Rust) y su integración total con tu cuenta de ChatGPT para gestionar entornos en la nube y subagentes.
Claude Code (Anthropic) es el rey del razonamiento profundo en bases de código enormes, ideal para refactorizaciones masivas y flujos Git complejos de forma autónoma.
¿Cuál prefieres? 🛠️
-
Codex CLI vs Claude Code 🚀
Codex CLI (OpenAI) brilla por su velocidad (hecho en Rust) y su integración total con tu cuenta de ChatGPT para gestionar entornos en la nube y subagentes.
Claude Code (Anthropic) es el rey del razonamiento profundo en bases de código enormes, ideal para refactorizaciones masivas y flujos Git complejos de forma autónoma.
¿Cuál prefieres? 🛠️
-
From the Leanpub Blog: The Leanpub Podcast 🎙 Feat. Daniel Vaughan, Author of Codex CLI: Agentic Engineering from First Principles
#books #leanpublishing #selfpublishing #codexcli #ai #programming
-
From the Leanpub Blog: The Leanpub Podcast 🎙 Feat. Daniel Vaughan, Author of Codex CLI: Agentic Engineering from First Principles
#books #leanpublishing #selfpublishing #codexcli #ai #programming
-
Check out the Leanpub Podcast 🎙 Feat. Daniel Vaughan, Author of Codex CLI: Agentic Engineering from First Principles
#books #leanpublishing #selfpublishing #codexcli #ai #programming
-
Check out the Leanpub Podcast 🎙 Feat. Daniel Vaughan, Author of Codex CLI: Agentic Engineering from First Principles
#books #leanpublishing #selfpublishing #codexcli #ai #programming
-
터미널 AI 3대장, 뭐가 다를까?
AI 채팅창이 아닌 터미널에서 직접 코딩하는 시대가 열렸습니다. Anthropic·OpenAI·Google이 내놓은 터미널 AI 도구 3가지를 비교하고, 각각의 강점과 나에게 맞는 선택법을 알려드립니다.
-
"Description technique détaillée du fonctionnement interne de l'agent de codage d' #OpenAI #CodexCLI, un outil de codage #IA qui écrit du code, exécute des tests et corrige des bogues"
Intéressant de voir un peu la technique derrière les belles paroles.
Et bien je ne suis pas près de laisser les rênes de mon PC à ce genre de programme!!!
-
"Description technique détaillée du fonctionnement interne de l'agent de codage d' #OpenAI #CodexCLI, un outil de codage #IA qui écrit du code, exécute des tests et corrige des bogues"
Intéressant de voir un peu la technique derrière les belles paroles.
Et bien je ne suis pas près de laisser les rênes de mon PC à ce genre de programme!!!
-
AI 에이전트의 엔진룸, OpenAI가 공개한 Agent Loop의 비밀
OpenAI가 Codex CLI의 핵심 작동 원리인 agent loop를 공개했습니다. AI 에이전트가 어떻게 대화하고 작업하는지, 프롬프트 캐싱과 컨텍스트 관리 전략을 실제 코드와 함께 설명합니다. -
AI 에이전트의 엔진룸, OpenAI가 공개한 Agent Loop의 비밀
OpenAI가 Codex CLI의 핵심 작동 원리인 agent loop를 공개했습니다. AI 에이전트가 어떻게 대화하고 작업하는지, 프롬프트 캐싱과 컨텍스트 관리 전략을 실제 코드와 함께 설명합니다. -
"Codex CLI is our cross-platform local software agent, designed to produce high-quality, reliable software changes while operating safely and efficiently on your machine. We’ve learned a tremendous amount about how to build a world-class software agent since we first launched the CLI in April. To unpack those insights, this is the first post in an ongoing series where we’ll explore various aspects of how Codex works, as well as hard-earned lessons. (For an even more granular view on how the Codex CLI is built, check out our open source repository at https://github.com/openai/codex. Many of the finer details of our design decisions are memorialized in GitHub issues and pull requests if you’d like to learn more.)
To kick off, we’ll focus on the agent loop, which is the core logic in Codex CLI that is responsible for orchestrating the interaction between the user, the model, and the tools the model invokes to perform meaningful software work. We hope this post gives you a good view into the role our agent (or “harness”) plays in making use of an LLM.
Before we dive in, a quick note on terminology: at OpenAI, “Codex” encompasses a suite of software agent offerings, including Codex CLI, Codex Cloud, and the Codex VS Code extension. This post focuses on the Codex harness, which provides the core agent loop and execution logic that underlies all Codex experiences and is surfaced through the Codex CLI. For ease here, we’ll use the terms “Codex” and “Codex CLI” interchangeably."
https://openai.com/index/unrolling-the-codex-agent-loop/
#AI #GenerativeAI #LLMs #OpenAI #CodexCLI #Codex #AIAgents #AgenticAI #Programming #SoftwareDevelopment
-
"Codex CLI is our cross-platform local software agent, designed to produce high-quality, reliable software changes while operating safely and efficiently on your machine. We’ve learned a tremendous amount about how to build a world-class software agent since we first launched the CLI in April. To unpack those insights, this is the first post in an ongoing series where we’ll explore various aspects of how Codex works, as well as hard-earned lessons. (For an even more granular view on how the Codex CLI is built, check out our open source repository at https://github.com/openai/codex. Many of the finer details of our design decisions are memorialized in GitHub issues and pull requests if you’d like to learn more.)
To kick off, we’ll focus on the agent loop, which is the core logic in Codex CLI that is responsible for orchestrating the interaction between the user, the model, and the tools the model invokes to perform meaningful software work. We hope this post gives you a good view into the role our agent (or “harness”) plays in making use of an LLM.
Before we dive in, a quick note on terminology: at OpenAI, “Codex” encompasses a suite of software agent offerings, including Codex CLI, Codex Cloud, and the Codex VS Code extension. This post focuses on the Codex harness, which provides the core agent loop and execution logic that underlies all Codex experiences and is surfaced through the Codex CLI. For ease here, we’ll use the terms “Codex” and “Codex CLI” interchangeably."
https://openai.com/index/unrolling-the-codex-agent-loop/
#AI #GenerativeAI #LLMs #OpenAI #CodexCLI #Codex #AIAgents #AgenticAI #Programming #SoftwareDevelopment
-
OpenAI Adds ‘Skills’ Framework to ChatGPT and Codex CLI, Mirroring Anthropic’s Agent Standard
#AI #OpenAI #ChatGPT #CodexCLI #AIAgents #DeveloperTools #SoftwareEngineering #Anthropic #MCP #Programming #GPT52 #GenAI
-
OpenAI Adds ‘Skills’ Framework to ChatGPT and Codex CLI, Mirroring Anthropic’s Agent Standard
#AI #OpenAI #ChatGPT #CodexCLI #AIAgents #DeveloperTools #SoftwareEngineering #Anthropic #MCP #Programming #GPT52 #GenAI
-
#OpenAI has quietly implemented #skills support in both #ChatGPT and #CodexCLI. The skills, similar to #Anthropic’s implementation, are #folders containing a #Markdownfile and optional resources. This allows users to create #customfunctionalities, such as generating PDFs or writing Datasette plugins, by leveraging existing skills or creating their own. https://simonwillison.net/2025/Dec/12/openai-skills/?eicker.news #tech #media #news
-
#OpenAI has quietly implemented #skills support in both #ChatGPT and #CodexCLI. The skills, similar to #Anthropic’s implementation, are #folders containing a #Markdownfile and optional resources. This allows users to create #customfunctionalities, such as generating PDFs or writing Datasette plugins, by leveraging existing skills or creating their own. https://simonwillison.net/2025/Dec/12/openai-skills/?eicker.news #tech #media #news
-
Codex CLI Silent RCE Flaw (CVE-2025-61260)
https://www.technadu.com/codex-cli-flaw-allowed-silent-remote-code-execution-through-malicious-repository-configurations/614994/• Repo configs auto-executed MCP commands
• Backdoors via commit/PR access
• CI & developer endpoints at risk
• Root cause: trusted repo-level config execution
• Patched in v0.23.0A critical reminder that AI-powered developer tools must adopt strict zero-trust defaults.
Follow us for ongoing security coverage.#Cybersecurity #CodexCLI #RCE #AIThreats #SupplyChainSecurity #DevSecOps #InfoSec
-
Vulnerability in OpenAI Coding Agent Could Facilitate Attacks on Developers https://www.securityweek.com/vulnerability-in-openai-coding-agent-could-facilitate-attacks-on-developers/ #ArtificialIntelligence #vulnerability #CodexCLI #OpenAI #AI
-
Vulnerability in OpenAI Coding Agent Could Facilitate Attacks on Developers https://www.securityweek.com/vulnerability-in-openai-coding-agent-could-facilitate-attacks-on-developers/ #ArtificialIntelligence #vulnerability #CodexCLI #OpenAI #AI
-
OpenAI just rolled out GPT‑5.1‑Codex‑Max, a new Codex CLI that finishes a 24‑hour coding sprint on its own. With “thinking tokens” and autonomous debugging, it pushes LLM‑driven development to a new level. Curious how it works and what it means for open‑source tooling? Dive into the details. #GPT5_1CodexMax #CodexCLI #ThinkingTokens #AutonomousDebugging
🔗 https://aidailypost.com/news/openai-launches-gpt51codexmax-completes-24hour-coding-task-internally
-
OpenAI just released a Codex CLI that works with any ChatGPT plan and integrates into VS Code via an extension. It taps the OpenAI Developer API, supports GLM and Minimax models, and enables agentic coding workflows. Curious how this can boost your open‑source projects? Read the full breakdown. #OpenAI #CodexCLI #ChatGPTPlan #VSCodeExtension
🔗 https://aidailypost.com/news/openai-codex-cli-works-chatgpt-plan-vs-code-extension
-
OpenAI just released a Codex CLI that works with any ChatGPT plan and integrates into VS Code via an extension. It taps the OpenAI Developer API, supports GLM and Minimax models, and enables agentic coding workflows. Curious how this can boost your open‑source projects? Read the full breakdown. #OpenAI #CodexCLI #ChatGPTPlan #VSCodeExtension
🔗 https://aidailypost.com/news/openai-codex-cli-works-chatgpt-plan-vs-code-extension
-
Reverse engineering Codex CLI to get GPT-5-Codex-Mini to draw me a pelican
https://simonwillison.net/2025/Nov/9/gpt-5-codex-mini/
#HackerNews #ReverseEngineering #CodexCLI #GPT5 #CodexMini #Pelican #AIArt
-
Reverse engineering Codex CLI to get GPT-5-Codex-Mini to draw me a pelican
https://simonwillison.net/2025/Nov/9/gpt-5-codex-mini/
#HackerNews #ReverseEngineering #CodexCLI #GPT5 #CodexMini #Pelican #AIArt
-
"For a while now I’ve been hearing from engineers who run multiple coding agents at once—firing up several Claude Code or Codex CLI instances at the same time, sometimes in the same repo, sometimes against multiple checkouts or git worktrees.
I was pretty skeptical about this at first. AI-generated code needs to be reviewed, which means the natural bottleneck on all of this is how fast I can review the results. It’s tough keeping up with just a single LLM given how fast they can churn things out, where’s the benefit from running more than one at a time if it just leaves me further behind?
Despite my misgivings, over the past few weeks I’ve noticed myself quietly starting to embrace the parallel coding agent lifestyle.
I can only focus on reviewing and landing one significant change at a time, but I’m finding an increasing number of tasks that can still be fired off in parallel without adding too much cognitive overhead to my primary work.
Here are some patterns I’ve found for applying parallel agents effectively."
https://simonwillison.net/2025/Oct/5/parallel-coding-agents/
#AI #GenerativeAI #AIAgents #AgenticAI #LLMs #ClaudeCode #CodexCLI
-
"For a while now I’ve been hearing from engineers who run multiple coding agents at once—firing up several Claude Code or Codex CLI instances at the same time, sometimes in the same repo, sometimes against multiple checkouts or git worktrees.
I was pretty skeptical about this at first. AI-generated code needs to be reviewed, which means the natural bottleneck on all of this is how fast I can review the results. It’s tough keeping up with just a single LLM given how fast they can churn things out, where’s the benefit from running more than one at a time if it just leaves me further behind?
Despite my misgivings, over the past few weeks I’ve noticed myself quietly starting to embrace the parallel coding agent lifestyle.
I can only focus on reviewing and landing one significant change at a time, but I’m finding an increasing number of tasks that can still be fired off in parallel without adding too much cognitive overhead to my primary work.
Here are some patterns I’ve found for applying parallel agents effectively."
https://simonwillison.net/2025/Oct/5/parallel-coding-agents/
#AI #GenerativeAI #AIAgents #AgenticAI #LLMs #ClaudeCode #CodexCLI
-
🚀 Multiple Execution Profiles: Configure different models (GPT-5, O3) with varying approval policies and sandbox modes for different agent roles
📊 Rich Agent Ecosystem: Ships with starter personas for code review, debugging, security auditing, performance analysis, documentation, and accessibility
🔄 Zero Fluff Philosophy: Single delegate tool with minimal attack surface, avoiding complex orchestrators while maintaining simplicity through #CodexCLI profiles
-
🚀 Multiple Execution Profiles: Configure different models (GPT-5, O3) with varying approval policies and sandbox modes for different agent roles
📊 Rich Agent Ecosystem: Ships with starter personas for code review, debugging, security auditing, performance analysis, documentation, and accessibility
🔄 Zero Fluff Philosophy: Single delegate tool with minimal attack surface, avoiding complex orchestrators while maintaining simplicity through #CodexCLI profiles
-
🤖 #CodexSubagentsMCP creates file-based sub-agents for #CodexCLI via a minimal #MCP server with just one tool and maximum auditability
⚡ Clean Architecture: Each call spins up isolated temp workdir contexts with persona injection via https://AGENTS.md files, preserving separated execution states
🔍 Auditable Design: All agents exist as reviewable files in PRs rather than buried code, enabling proper version control and team oversight
-
🤖 #CodexSubagentsMCP creates file-based sub-agents for #CodexCLI via a minimal #MCP server with just one tool and maximum auditability
⚡ Clean Architecture: Each call spins up isolated temp workdir contexts with persona injection via https://AGENTS.md files, preserving separated execution states
🔍 Auditable Design: All agents exist as reviewable files in PRs rather than buried code, enabling proper version control and team oversight
-
【10項目で比較】Claude Code vs Codex CLI どっちを選ぶべき？観点別にポイントを解説してみた
https://qiita.com/tomada/items/c369d5f28142a2599a36?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items -
Codex CLIでMCPサーバを設定する方法！config.toml またはコマンド一発で簡単
https://qiita.com/tomada/items/2eb8d5b5173a4d70b287?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items -
7시간 연속 코딩하는 AI가 나타났다 – OpenAI GPT-5-Codex 실무 활용 가이드
OpenAI의 새로운 GPT-5-Codex가 최대 7시간 연속으로 독립적인 코딩 작업을 수행하는 혁신적 기능과 실무 활용 방법을 소개하는 실용 가이드 -
今さらながら OpenAI の「Codex IDE extension」を VS Code で少し試してみる（公式情報なども見つつ）
https://qiita.com/youtoy/items/e5c8732340a483633257?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items -
Codex CLIのカスタムコマンドを完全攻略！よく使う指示を瞬時に呼び出す方法
https://qiita.com/tomada/items/37d260807c4324c9898d?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items -
OpenAI Codex CLI の使い方！ChatGPTサブスクで使えるAIコーディング入門
https://qiita.com/tomada/items/bcd0aef846c641ccbb9b?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items -
🚨BREAKING NEWS: Codex CLI is "going native"—because apparently, developers needed another reason to feel superior! 🥳 Now you can watch AI mumbo jumbo code in ways you didn't know were possible, while real engineers roll their eyes in unison. 🎉
https://github.com/openai/codex/discussions/1174 #CodexCLI #GoingNative #AIRevolution #DeveloperHumor #CodingTrends #TechNews #HackerNews #ngated -
OpenAI Codex 2025: Revolutioniert dein Coding-Game? 🤖💻
• KI-Agent fürs Terminal
• Code schreibt sich (fast) selbst
• CLI + Cloud = neue Power#ai #ki #artificialintelligence #OpenAICodex #CodexCLI #DevTools
Jetzt LIKEN, teilen, LESEN und FOLGEN! Schreib uns in den Kommentaren!
https://kinews24.de/openai-codex-codex-cli-ki-coding-agent-2025/
-
🚀 OpenAI’s Codex CLI is now open source—and it’s more than a dev toy. We’ve got ideas on how your business can actually use it, from writing code to keeping your employee handbook up to date with a single command. 🔗 Read the blog: https://mindcraftgroup.com/blog/codex-goes-open-source-how-businesses-can-actually-use-it #CodexCLI #OpenAI #DevOps #TechTools #Automation
-
OpenAI's New Codex CLI tool offers model-agnostic AI coding directly in the terminal
#AI #CodexCLI #OpenAI #AICoding #GPT4 #DeveloperTools #OpenSourceAI #MultimodalAI #CodingAgents #CLItools
