What’s new in Playcode

You can now invite friends to Playcode and both of you get credits. Your friend receives 10 welcome credits the moment they sign up with your link, and you receive 40 credits when they subscribe.

Find your personal invite link in the project menu, right under your credits meter. You have 3 invite passes; every time an invited friend subscribes, one pass comes back, so your best invites never run out.

The invite dialog shows who joined and what you have earned, with friends' emails masked for privacy.

Usage History now shows where every AI credit goes. Click the info icon on any row for a full breakdown: input, output, and cache tokens, each with its own credit cost.

It answers the question we hear most: why did a short message still cost credits? The first message in a chat saves your whole prompt and tools to cache once (that is the big number), and every later message reuses it at a large discount. Now you can see exactly that.

The activity list also got a proper Load more button and a running count of how many records you are viewing, so you can browse your full history.

Until today, the AI agent could fetch a webpage's text (article-style, cleaned via Markdown) but not its raw HTML. That was a real gap when you'd say "redesign this site" - the agent needed the actual DOM, classes, and layout, not a flattened text version.

Now there's a dedicated WebFetchHtml tool. Give the agent a URL, it downloads the page's raw HTML (up to 5 MB), saves it as a file inside your project under temp/, and reads it back chunk by chunk - the same way it reads any other file in your project.

Practical example: "Fetch https://stripe.com/pricing and redesign our pricing page in that style." The agent now actually sees Stripe's grid, their semantic landmarks, their spacing patterns - not just the text on the page.

Safety: same SSRF protections as the existing fetcher - localhost, private IPs, cloud metadata endpoints are all blocked. The HTML is never inlined into the conversation (that would blow the context budget); it's only ever read on demand from the project file.

The chat attach menu (the paperclip) now accepts zip and tar.gz archives, on top of images, videos, and PDFs. Drop one in chat, the agent gets the URL, and you can ask it to do something with the contents.

Where this really shines: Cloud projects. The agent has a real shell, so it can curl the archive into your workspace and unzip it directly. Practical uses:

• Import an existing site - drag its source zip in, ask the agent to extract it and use it as a starting point.
• Hand the agent an asset bundle - a folder of images, fonts, or design exports, packaged once, dropped in chat.
• Move work between projects - export from one, drop into another.

On Browser projects the agent sees the archive's URL but can't extract it in-browser (no shell). For full unzip-and-use behavior, drop archives into a Cloud project.

Up to 150 MB per file. The archive contents are never sent to the AI model directly - only the URL is referenced in the conversation, which keeps your costs predictable and avoids hitting model file-size limits.

Projects with long chat histories and lots of files now load significantly faster. Instead of downloading every message on login, chats now load on demand - only when you open them.

• Instant project loading - Login and project switching no longer wait for chat history to download. You get to your code immediately.
• Smart message loading - Chat messages load when you open a conversation, with older messages fetched as you scroll up.
• Lower memory usage - Only active chats consume memory, so even projects with hundreds of AI conversations stay snappy.

Improvements

• Import from AI - Redesigned - The "Import from AI" popover now clearly explains what it's for: importing code from ChatGPT, Gemini, Grok, or any AI assistant. Each step has a help tooltip explaining exactly what to do.
• 90%+ Success Rate - Smart content detection now works almost perfectly. Paste any code and Playcode figures out if it's HTML, CSS, JavaScript, Python, C, C++, Go, or SQL and puts it in the right file automatically.

Improvements

• AI Now Understands All Languages - The built-in AI assistant now fully understands Python, C, C++, Go, and SQL projects. It knows how each language works in Playcode, including entry points, package management, and execution modes.
• Import from AI - Multi-Language - The Import from AI feature now detects Python, C, C++, Go, and SQL code automatically. Paste code from ChatGPT or Claude and it goes to the right file (main.py, main.c, main.cpp, main.go, or main.sql).
• Smarter Code Detection - Improved detection patterns for all supported languages. Python imports, C/C++ includes, Go packages, and SQL queries are now recognized instantly.

Improvements

• Go Runtime Now Works Everywhere - Rebuilt the Go interpreter with self-hosted WebAssembly. No more CDN dependencies that were blocked in some regions. Go code execution is now reliable worldwide.
• Python Runtime Self-Hosted - Core Python runtime (Pyodide 0.29.1) now loads from our servers instead of external CDN. Faster initial load and works in regions where jsdelivr was blocked.

Improvements

• Redesigned AI Mode Selector - The mode selector now explains exactly how to work with AI. Each mode is color-coded: Plan (blue) for planning, Agent (green) for building, and Ask (orange) for questions only.
• Recommended Workflow Guide - The menu now shows "Plan → Agent → Ask" as the recommended workflow, with step numbers (1, 2, 3) and clear descriptions for each mode. Perfect for non-programmers!
• Mode Badges - Each mode has a helpful badge: "Start here" for Plan, "Default" for Agent, and "Read-only" for Ask.
• Learn More Link - Quick access to detailed documentation about how each mode works.

Changes

• Free tier adjustments - To keep Playcode sustainable and continue offering a great experience, we've had to reintroduce some coding limits for free accounts. Pro users continue to enjoy unlimited lines of code, along with all other premium features. We appreciate your understanding and support!

Improvements

• HTML Page Selector: Click the URL bar in the preview toolbar to see all HTML pages in your project. Quickly switch between pages without typing URLs manually.

Improvements

• Click to Open Files - When AI reads a file, click the tool message to open that file in the editor with the exact lines highlighted.
• Accurate Line Range - Read tool now shows the precise line range (e.g., "Read index.html:1-78") so you know exactly what the AI saw.
• Clickable File Lists - In "List files" results, click any file path to open it directly in the editor.
• Cleaner Visual Hierarchy - Read and list operations now use muted text styling to keep focus on the code changes.

Improvements

• Refined Visual Design - The interface now features a cleaner, more borderless appearance with improved color themes and subtle shadows that create depth without clutter
• Better Contrast - Enhanced visibility across all themes (Dark, Blue, Gray) with optimized borders and backgrounds for a more polished look