cedric (@cedric_chee)

OpenAI의 Codex CLI 저장소 PR에서 GPT-5.4가 포착되었으며, 'fast mode'라는 새 옵션이 등장해 우선순위 티어(priority tier) 사용을 가능하게 보인다는 내용입니다. 해당 변경은 클라이언트/도구 레벨의 성능·요금 우선순위와 관련된 업데이트로 해석됩니다. 링크는 GitHub PR로 구체 구현을 확인할 수 있습니다.

https://x.com/cedric_chee/status/2028334870557290956

#openai #gpt5.4 #codex #codexcli #github

cedric (@cedric_chee) on X

GPT-5.4 spotted in Codex CLI PR, and a new fast mode that seems to enable use of the priority tier. https://t.co/2Hf7nroJi8

X (formerly Twitter)

🤖Learn how to easily add MCP servers (like the essential Context7) to Claude Code, Gemini CLI & Codex CLI.

I wrote a quick guide showing the commands and where all the hidden config files live. 👇
https://elguerre.com/2026/02/28/tip-how-to-add-mcp-servers-to-claude-code-and-gemini-cli-on-windows/

#AI #Developers #MCP #ClaudeCode #GeminiCLI #CodexCLI

Numman Ali (@nummanali)

NousResearch의 신규 Hermes Agent에 Kimi_Moonshot, Zai_org, MiniMax_AI의 코딩 플랜 지원을 추가하는 PR을 넣었다는 개발 업데이트입니다. Pi Agent provider 시스템으로 참조되었고, badlogicgames와 연계된 흐름이며 Codex CLI 기반 멀티 에이전트 시스템으로 구현되어 개발자가 바로 빌드할 수 있게 됐다는 내용입니다.

https://x.com/nummanali/status/2026814113028993341

#hermes #codexcli #multiagent #pullrequest

Numman Ali (@nummanali) on X

Added a PR for support for @Kimi_Moonshot, @Zai_org and @MiniMax_AI coding plans to the new Hermes Agent from @NousResearch The feature was referenced through Pi Agent provider system from @badlogicgames Done with Codex CLI multi agent system You can just build things

X (formerly Twitter)

Numman Ali (@nummanali)

Hermes Agent에 Kimi_Moonshot, Zai_org, MiniMax_AI의 코딩 플랜 지원을 추가하는 PR이 제출되었다고 보고합니다. 이 기능은 badlogicgames의 Pi Agent provider 시스템을 통해 참조되었고, Codex CLI 기반의 멀티에이전트 시스템으로 구현되어 개발자가 바로 빌드할 수 있도록 했다는 내용입니다.

https://x.com/nummanali/status/2026814113028993341

#hermes #nousresearch #codexcli #multiagent #agents

Numman Ali (@nummanali) on X

Added a PR for support for @Kimi_Moonshot, @Zai_org and @MiniMax_AI coding plans to the new Hermes Agent from @NousResearch The feature was referenced through Pi Agent provider system from @badlogicgames Done with Codex CLI multi agent system You can just build things

X (formerly Twitter)

"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!!! 

https://intelligence-artificielle.developpez.com/actu/379965/Description-technique-detaillee-du-fonctionnement-interne-de-l-agent-de-codage-d-OpenAI-Codex-CLI-un-outil-de-codage-IA-qui-ecrit-du-code-execute-des-tests-et-corrige-des-bogues/

Codex | TyfloPodcast

Michał Dziwisz demonstruje narzędzie Codex CLI — interfejs pozwalający na pisanie kodu z wykorzystaniem modeli językowych dostarczanych przez OpenAI. W audy ...

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.

https://aisparkup.com/posts/8645

"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

GitHub - openai/codex: Lightweight coding agent that runs in your terminal

Lightweight coding agent that runs in your terminal - openai/codex

GitHub

↳ continue
↳ continue
↳ continue
↳ continue

#codex #CodexCLI

Công cụ CLI aichat giúp tìm kiếm toàn văn nhanh và tiếp tục phiên làm việc với Claude-Code/Codex mà không cần nén nội dung. Hỗ trợ tìm kiếm bằng giao diện TUI siêu nhanh (Rust/Tantivy), sao chép phiên, cắt bỏ thông minh hoặc chuyển tiếp sang phiên mới có tích hợp lịch sử (lineage). Dễ dàng tìm lại ngữ cảnh cũ qua lệnh `>resume` hoặc `aichat search`. Hữu ích cho phát triển AI agent và làm việc dài hạn. #aichat #ClaudeCode #CodexCLI #AI #Productivity #công_cụ #trí_tuệ_nhân_tạo #hiệu_suất

https://