OpenAI Codex Can Now Ship Live Shareable Websites

2026-01-05 · Source: unwind ai · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Robotics & Autonomous Systems · Depth: Intermediate, medium

Summary

This brief, dated June 03, 2026, highlights several advancements in AI development and tools. OpenAI's Codex now features "Sites," enabling users to publish interactive, shareable websites directly from their sessions, complete with collaborative canvases and AI-powered inline annotations. This is part of a broader push to support non-technical knowledge workers, evidenced by six new open-source, role-specific plugins bundling 62 apps and 110 skills for functions like Data Analytics and Sales. Concurrently, Hermes Agent released a native desktop app for macOS and Windows, making its multi-agent orchestration more accessible. TinyFish introduced BigSet, an open-source tool that generates structured, auto-refreshing datasets from natural language prompts using parallel AI agents. Microsoft also launched its MAI family of 7 in-house models, including MAI-Code-1-Flash for coding, aiming for cost-effective alternatives to existing frontier models.

Key takeaway

For AI Engineers and technical professionals evaluating development workflows, these advancements signal a shift towards more integrated, accessible, and cost-optimized AI tooling. You should explore Codex's new "Sites" for direct web publishing and its role-specific plugins to streamline non-developer collaboration. Consider adopting Hermes Desktop for simplified agent orchestration and investigate BigSet for automated, refreshable dataset generation. Additionally, assess Microsoft's new MAI models and Factory Router for potential cost savings and optimized model selection in your agentic systems.

Key insights

AI tools are rapidly evolving to empower non-developers with direct, integrated, and automated capabilities for complex tasks.

Principles

• AI agents increasingly handle end-to-end workflows.
• Accessibility drives broader AI adoption.
• Cost-efficiency guides model selection.

Method

BigSet's method involves describing a desired dataset in natural language, which AI agents then use to infer schema, research in parallel, verify, deduplicate, and deliver a structured, refreshable output.

In practice

• Use Codex "Sites" for live project dashboards.
• Deploy Hermes Desktop for agent orchestration.
• Utilize BigSet for automated data collection.

Topics

• AI Agents
• OpenAI Codex
• Hermes Agent
• Low-Code Development
• Data Automation
• Microsoft MAI Models
• Model Routing

Code references

• openai/role-based-plugins
• tinyfish-io/bigset
• nesquena/hermes-webui
• Shubhamsaboo/awesome-llm-apps

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• OpenAI's Codex update lets agents build interactive enterprise workspaces via Sites and role-specific plugins — Codex's update transforms it into an agentic AI operating environment for business, enabling precise automation and interactive app creation.
• OpenAI Codex Can Now Use Your Computer! (Full Breakdown + Testing) — OpenAI's Codex is an evolving AI agent designed for non-technical users, excelling in browser and computer control.
• 😺 New Codex, Copilot, Hermes, and Microsoft Build 2026 AI updates — The AI industry is rapidly shifting towards agent-centric computing, emphasizing local execution, integrated workflows, and robust security.
• OpenAI says Codex is coming to your phone — OpenAI's Codex now offers mobile and desktop control, intensifying competition in agentic coding tools.
• [AINews] AI vs SaaS: The Unreasonable Effectiveness of Centralizing the AI Heartbeat — OpenAI's Codex 5.3 enhances coding with speed and mid-turn interaction, shifting focus to agent orchestration and user tools.
• OpenAI Codex App: death of the VSCode fork, multitasking worktrees, Skills Automations — Agent-native coding interfaces and specialized open models are rapidly advancing, shifting developer workflows and evaluation paradigms.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by unwind ai.