Skip to content

Fields

AI agents Latest

AI agents that break a task down, call tools and finish the job: Claude Code, Manus and peers, plus agent frameworks and evaluations.

105 picked73 in the last 30 days847 collected

November 18 04:01 updated

AI agents · Picks · page 6

February 25WednesdayItems 101–105 of 105
  1. OpenAI Developers Blog62

    OpenAI publishes Codex prompting guide for gpt-5.3-codex

    OpenAI released a Codex prompting guide for developers calling the Codex-tuned gpt-5.3-codex model directly through the API, recommending medium reasoning effort for interactive coding and high or xhigh for the hardest tasks. The guide covers migrating an existing harness to the open-source codex-cli, including the standard Codex-Max prompt, the apply_patch, shell_command and update_plan tools, and first-class compaction via /compact in the Responses API for multi-hour sessions. It also describes the new phase field, supported only on gpt-5.3-codex, which marks assistant items as commentary or final_answer and must be preserved in history to avoid performance degradation.

    Why it matters: OpenAI's official guide details how to tune prompts, tools and compaction for gpt-5.3-codex, giving teams a concrete migration path for their own coding agents.

February 11Wednesday
  1. Modal Blog78

    Modal launches free GLM-5 endpoint and publishes self-deployment and frontend integration guides

    Modal has launched a free OpenAI API-compatible endpoint for GLM-5, available through the end of April, limited to a single concurrent request, and has also released reproducible code for deploying it with SGLang on a single node with 8 B200 GPUs.

    Why it matters: Modal provides a free OpenAI-compatible endpoint for Z.ai's GLM-5 and gives specific configurations for integrating it in OpenCode, OpenClaw, Claude Code, and the Vercel AI SDK.

February 2Monday
  1. OpenAI Developers Blog62

    OpenAI introduces the Codex app

    OpenAI introduced the Codex app, a dedicated app for its Codex coding agent, in an official developers blog post. The post is an intro walkthrough covering the app and its core workflows, with the full video hosted on YouTube.

    Why it matters: OpenAI's official walkthrough shows how the Codex app structures core coding workflows, useful for developers weighing it against existing coding agents.

December 23, 2025Tuesday
  1. Replit Blog70

    Replit launches in-ChatGPT app building via @replit and Replit Agent

    Replit is now available inside ChatGPT, letting users tag @replit in any message to have Replit Agent create, update and deploy Replit Apps directly in the conversation. Build progress and an interactive preview appear in-chat, and each request such as adding dark mode or a payment form updates the app instantly, with apps stored in the user's Replit account for later publishing. The integration requires a ChatGPT account (Free, Plus, Pro or Teams) and a Replit account, works where the ChatGPT App Store is available, and consumes Replit Agent credits.

    Why it matters: Replit's ChatGPT integration lets users describe an app in chat and have Replit Agent build, preview and deploy it without leaving the conversation.

August 23, 2024Friday
  1. Cursor Changelog62

    Cursor raises $60M Series A from Andreessen Horowitz, Thrive Capital and OpenAI

    Cursor raised a $60M Series A from Andreessen Horowitz, Thrive Capital, OpenAI, Jeff Dean, Noam Brown, and founders of Stripe, GitHub, Ramp, Perplexity and OpenAI. The AI coding tool says it has grown to more than 40,000 users, including startups, research institutions and large enterprises, and describes internal systems for next-edit prediction, retrieval across billions of files and speculative-inference code rewriting.

    Why it matters: Cursor's $60M Series A announcement also discloses its user base has grown past 40,000 and names the investors backing its AI coding tool.