Framer Release Notes

Introducing Skills, a new way to teach the Framer agent how you work.

Save instructions for your design system, writing style, or CMS workflow and reuse them across tasks.

Reference @pages, @components, and @styles in your project to help the agent follow your design direction, while you keep control of the result on the canvas.

To get started, use /skills to ask the agent to create or update a skill.

After a conversation where you’ve refined a page or a piece of copy, ask the agent to capture the decisions you want to reuse next time.

Skills stay with a project when someone remixes it, so template creators can now include guidance for adding new pages and content with their template while staying true to their design.

Learn more about Skills.

You can now better manage repeating content like FAQs, product features, tutorial steps, and cases studies with the new List field in the Framer’s CMS. Rather than duplicating fields like Title 1, Description 1, Title 2, Description 2, you can group items in a single list and add or reorder rows as you would in a CMS table. Your content editors can spend less time juggling fields and more time keeping your site fresh. To migrate existing content, ask the Framer Agent to convert repeated CMS fields into a List. The Agent will also take care of reconnecting the CMS data on the Canvas. If you have a list that is not shown on the Canvas yet, you can easily add it from the Insert panel. Alternatively, select a card you’ve designed and use the newly added Repeat property to repeat it for each list item. Watch the video to learn more. We’ve also added features, fixed bugs, and made improvements across the CMS. See a complete list below.

Added

• Added the List field in the CMS, including API and Agent support
• Added a new video component to insert in CMS rich text fields
• Added support for reordering the Status field in the panel
• Added support for editing content inline for content editors
• Added support for duplicating multiple CMS items at once
• Added support for finding CMS fields in the Insert panel

Fixed

• Fixed a cropping issue when embedding vertical videos in rich text
• Fixed managed collections creating duplicate items in branches
• Fixed monochrome and duotone icons rendering in CMS tables
• Fixed loading errors when refreshing paginated CMS pages
• Fixed Agent date changes drifting to yesterday or tomorrow
• Fixed duplicate titles producing conflicting automatic slugs
• Fixed undo history after inserting links and pasting images
• Fixed CMS detail page previews failing after reloading
• Fixed case-sensitive slug filtering on published sites

Improved

• Improved block selection for images and embeds in rich text
• Improved scrolling performance in large CMS collections
• Improved selection and context sharing with the Agent
• Improved opening items from the Canvas breadcrumb
• Improved handling of invalid fields when adding items
• Improved the toolbar UI of CMS formatted text fields
• Improved the UI of field warnings in the table view
• Improved the link popout UI in the table view
• Improved the filter menu UI in the CMS view

Branching

• Added createBranch to create and switch to a new branch
• Added the Branch class to switch, merge, and delete branches
• Added getBranch and getBranches to look up branches by ID
• Added subscribeToBranches to react to branch changes live

Publishing

• Added publish to ship a project’s changes from a plugin
• Added deploy to push a published version to a custom domain
• Added getUnpublishedPageChanges to list changes since publish
• Added getDeployment and getDeploymentIssues to track deploys

Plugins

• Added a url property to Font for its source file
• Added PathNode and ShapeGroupNode for imported vectors
• Added createdAt and updatedAt timestamps to collection items
• Added ShapeContainerNode and BooleanShapeNode node types
• Notion: Relation fields now support up to 100 references
• Notion: Added faster, clearer sync error reports
• Notion: Improved the sync progress interface
• Tidy Up: Added vertical layout and name sorting
• ASCII: Can now be launched from the image picker
• Google Sheets: Added support for the alt-text field
• Google Sheets: Added support for the option field

Agent

• Added support for Page Effects editing
• Added support for A11Y layer attributes
• Added support for Text Shadow properties
• Added support for draggable layer properties
• Added support for Tap Highlight Color
• Added support for hiding layer Scrollbars
• Added CMS Rich Text Video insertion
• Added Enter and Exit Backdrop transitions
• Added safe areas to floating Overlays
• Added overflow linting for Ticker layers
• Added viewport height validation
• Added restrictions for No Index values
• Added out-of-scope Variable warnings
• Added detached Components to summaries
• Added billed Token usage to Stats
• Added File Downloads to Agent Chat
• Added Code File changes to summaries
• Added Redirect changes to summary views
• Added CMS Item links to summaries
• Improved Claude compaction thresholds
• Improved context ceiling reliability
• Improved boolean handling in Computed Values
• Improved parent and child layer validation
• Improved trust handling for Script URLs
• Fixed invalid Control Reference assignments
• Fixed incorrect names for Vector Sets
• Fixed summaries when viewing another scope
• Fixed Tracking IDs using Link Variables
• Fixed failed summary compaction
• Fixed Skills menu positioning between Chats
• Fixed Link 404s in Code Components
• Fixed Link 404s for Draft Pages

Canvas

• Added Reset Override to Vector Icons
• Added external Icon Sets to Actions
• Added EM type to Decoration Thickness
• Improved Stack inference on Design Pages
• Improved Component loading after Code edits
• Improved persistence of Vector Icon previews
• Improved Alpha handling for Image Shaders
• Improved Shader dragging performance
• Improved Figma imports with Overflow: Clip
• Improved grouped Shape SVG size 50%
• Fixed replacement priority for Custom Fonts
• Fixed relative Imports in Code Files
• Fixed shallow-scope Localization imports
• Fixed broken Images aborting Rich Text

Framer Agents now use far fewer credits on larger, multi-step builds, giving you more room to create pages, make site-wide updates, and refine your work within the same credit budget. We worked directly with OpenAI to improve model efficiency in Framer, resulting in OpenAI models using around 25% fewer credits on multi-step builds. Alongside that work, we improved all models to complete tasks in 15–30% fewer steps, use 30–40% fewer tokens, and save another 10–15% through better caching. Agents now also catch and resolve more unintended side effects.

We’ve also made GPT-5.6 Terra the default model in Framer. In our testing, it is more capable than GPT-5.5, twice as fast, and uses 37.5% fewer credits. Combined with the broader efficiency improvements, multi-step builds with Terra use 60–67% fewer credits than GPT-5.5 did when Framer Agents launched. Sonnet 5 and Opus 4.8 benefit from the same improvements, using 48% fewer credits. These improvements are now live across Framer Agents and External Agents.

We’re introducing mouse interaction to two more Shaders: Liquid Gradient and Logo Gradient. Liquid Gradient creates animated color fields that move across your screen, while the Logo Gradient adds shifting gradient effects to SVGs and PNGs. Both respond to your cursor with smooth, spring-based tracking, combining motion-style interaction with WebGL effects. Tweak the colors, motion, intensity, and more to create endless variations of these shaders. To add the new interactions, simply click + on the new Mouse property while having your shader selected.

Adding new CMS items is now faster. A new empty row appears at the bottom of every collection, allowing you to create items directly from the table. To quickly add an item, focus the empty row, fill in one or more fields and hit Return to quickly add it and move to the next one. It’s especially useful for rapid creation of simple entries like categories, labels or tags. We’ve also shipped a number of additions, improvements, and fixes, with a particular focus on the Agent experience in the CMS. Additionally, we made formatted text fields behave more reliably. See the full list below.

Added

• Added a bottom empty row to quickly create new items
• Added Agent support for adding CMS rows as context
• Added Agent support for working with field dividers
• Added Agent support for collections via Select tool
• Added Agent support for previous and next pages
• Added support to delete multiple items with ⌫
• Added tooltips to the formatted text toolbar
• Added ability to force delete fields in use
• Added support for searching collections
• Added support for filtering by date field

Improved

• Improved Agent single-cell selection and editing
• Improved Agent duplicating synced collections
• Improved Agent awareness of selected rows
• Improved Agent awareness of draft statuses
• Improved Agent highlighting status changes
• Improved Agent handling of required slugs
• Improved Agent selected row highlights
• Improved Agent Select tool behaviour
• Improved selection of links in rich text
• Improved contrast in the item overlay
• Improved the / menu in rich text
• Improved the menu to filter items

Fixed

• Fixed inline editing of formatted text with components
• Fixed an issue with CSV exports and tags
• Fixed undo when pasting images in formatted text
• Fixed a font issue when inline editing code blocks
• Fixed undo after adding a link in formatted text
• Fixed scrolling when reselecting cell groups
• Fixed an issue with scrollbars in embeds
• Fixed the Fields header not being sticky
• Fixed Add to Agent button behaviour

OpenAI’s next generation of models is now available in Framer: GPT 5.6 Sol, GPT 5.6 Terra, and GPT 5.6 Luna.

Together, they give you more control over how you spend credits, whether you need the highest-quality creative output, balanced intelligence at lower cost, or maximum speed for large updates.

GPT 5.6 Sol is our strongest creative model yet.

In testing, it produced refined designs with minimal guidance and became the first model to score 100% on our hardest internal benchmark, a major step up from GPT 5.5 at the same credit cost.

GPT 5.6 Terra is built for balance.

It delivers GPT 5.5-level results while using only 0.6× the credits, making it ideal for large audits, redesigns, and consistency passes.

GPT 5.6 Luna is our fastest model in Framer, running 2× faster than any previous option while using only 0.4× the credits compared to GPT 5.5.

It is especially well suited for large CMS updates and complex cross-site find-and-replace tasks.

Fable 5 is now available in Framer. It’s the most proactive model we’ve tested. It goes beyond the brief, setting up styles and reusing elements across your site. When designing from scratch, first results are polished, with thoughtful finishing touches. It handles creative work like shaders and subtle animations noticeably better than models like Opus or Sonnet. In our latest evals, Fable 5 scored 83% overall, clearing Opus 4.8 at 77%, and led every model on design at 81%. At 2× the credit usage of GPT 5.5, Fable lands around 3.3× Sonnet 5. Now live in the agent model picker.