> ## Documentation Index
> Fetch the complete documentation index at: https://docs.replit.com/llms.txt
> Use this file to discover all available pages before exploring further.

# January 09, 2026

> 2 min read

## What's new

* [Automation preview for Agent users](#automation-preview-for-agent-users)
* [Private apps for free accounts](#private-apps-for-free-accounts)
* [Made with Replit badge](#made-with-replit-badge)
* [AI command in Shell](#ai-command-in-shell)
* [New AI models in Integrations](#new-ai-models-in-integrations)

## Platform

### Automation preview for Agent users

<Frame>
  <video src="https://cdn.replit.com/sanity/changelog-01-09-2026.mp4" controls />
</Frame>

Automation preview is now available to all Agent builders. Get a preview of the automation step graph in seconds, instead of waiting minutes to see visual progress.

### Private apps for free accounts

Builders on free accounts can now create private apps. Free tier limits still apply on how many apps you can create.

### Made with Replit badge

<Frame>
  <img src="https://replit.com/badge?caption=Made%20with%20Replit" alt="Made with Replit badge" noZoom />
</Frame>

A "Made with Replit" badge now appears on free published apps. Remove it by upgrading to Replit Core. Select the badge to learn more about Replit.

### AI command in Shell

<Frame>
  <img src="https://mintcdn.com/replit/kUWF7BqlJ2NZzoTt/images/changelog/2026-01-09/screenshot-2026-01-08-at-18-12-51_c5b98b748839.png?fit=max&auto=format&n=kUWF7BqlJ2NZzoTt&q=85&s=9e7072b22a38b8d48022cf41ee0ee07e" alt="Shell showing the replit ai command output" width="1244" height="412" data-path="images/changelog/2026-01-09/screenshot-2026-01-08-at-18-12-51_c5b98b748839.png" />
</Frame>

Interact with LLMs in Shell using the `replit ai` command. This works for both direct Shell access and Agent workflows.

### New AI models in Integrations

Support for newly-launched AI models is now available in AI Integrations:

| Model                        | Description                                                                                                                 |
| ---------------------------- | --------------------------------------------------------------------------------------------------------------------------- |
| `gpt-5.2`                    | OpenAI's most capable model for professional knowledge work. First model above 90% on ARC-AGI-1 with a 400K context window. |
| `claude-opus-4.5`            | Anthropic's flagship model optimized for coding, agents, and computer use. Achieves 80.9% on SWE-bench Verified.            |
| `gemini-3-flash-preview`     | Google's high-speed model for agentic workflows with 1M token context. Near Pro-level reasoning at lower latency and cost.  |
| `gemini-3-pro-preview`       | Google's advanced multimodal model with state-of-the-art reasoning and real-world knowledge.                                |
| `gemini-3-pro-image-preview` | Google's Nano Banana Pro model for high-quality image generation and editing with accurate text rendering.                  |