Now

Stacked pull requests are now displayed in Linear Diffs. Move through a stack and see review, CI, and merge status at a glance. Related PRs are grouped into a single collapsible row in Reviews, alongside their issue and project context.

For GitHub-native stacks, you can preview every affected PR before merging the current PR and those below from Linear.

Learn more in our documentation.

View code changes as the agent works⁠

Diffs now update in realtime throughout a Linear coding session, including uncommitted changes from follow-up prompts. You can follow the code as it evolves, catch wrong turns earlier, and steer the agent before or after a pull request is opened.

AI credit usage explorer and spend limits⁠

Admins can now see what’s driving AI credit usage and set limits to manage spend.

The new usage explorer breaks down spend by team, feature, user, or loop across any time period. Compare total spend, session count, and average spend per session, then select a group in the chart or table for a closer look.

You can also set spend limits at the workspace, user, or loop level to keep usage within the bounds you choose. When a limit is reached, additional AI credit usage is paused until the limit resets or an admin increases it.

Billing admins and owners can access both features in Usage & Limits. Learn more about AI credits in our documentation.

Guided Reviews on Basic⁠

Guides walk you through the most important changes in a pull request. They’re now available on Basic plans.

Coding sessions are the shortest path from issue to diff. Assign a task to Linear Agent, and it works in a secure cloud environment to write and test the code before opening a pull request for review.

We’re adding more control over how each session runs, from its environment to the models behind it.

Adaptive routing⁠

Save time and tokens by automatically routing simpler tasks to a faster model while using the default reasoning model for more complex work. If a task needs more capability than expected, you can restart the session on the default model while keeping the original pull request for reference.

Environment secrets⁠

Coding sessions can now access environment secrets during setup to securely fetch private dependencies and other environment config.

Open-weight models⁠

Coding sessions now support open-weight models, starting with GLM-powered sessions. Workspace admins and owners can choose which models are available from Coding sessions settings.

Visit the docs for more details.

Team organization at scale⁠

As companies grow, it can become challenging to accommodate every team’s workflow within a single workspace-wide system. A Product team may track discovery and development, while Marketing organizes work around campaign stages. Both need workflows that reflect how they operate, without fragmenting the company-wide view.

We’re giving teams more freedom to own and organize project work, without losing sight of the bigger picture.

Team project labels and statuses⁠

Teams can now define their own project labels and statuses to reflect how they work, and extend those workflows across their sub-teams for consistency. Team project labels and statuses are available on Business and Enterprise plans.

Project lead teams⁠

You can now define a lead team for a project to clarify ownership when multiple teams contribute. Filter by lead team to create focused views of the projects each team owns.

Team loops triggers⁠

Loops can now run when a team is created, someone joins or leaves a team, or an issue is assigned to a team. This makes it possible to automate recurring coordination, such as sending onboarding information to new teammates or reassigning open issues when someone leaves.

Project and initiative IDs⁠

Projects and initiatives now have durable, human-legible IDs. Reference work reliably in agent workflows and external tools, even when names change.

Loops are recurring agent workflows for teams. They now respond to more workspace activity, including changes to initiatives, projects, and cycles. They can also edit Linear documents and post updates to Slack.

Teams change project plans all the time. It’s not the change itself that’s hard, but the follow-through: updating docs, creating issues, and keeping everyone informed. That’s where information falls out of sync and handoffs get missed. Loops can now handle that coordination for you.

For example, when a project’s target date changes, a loop can automatically update the launch plan and post a Slack message explaining what changed, why, and who needs to act.

Trigger from across your workspace⁠

New triggers include:

• Project and initiative changes to status, ownership, target dates, milestones, membership, and labels, plus new updates and comments
• Cycles being created, started, or completed
• Issue changes to status, priority, assignee, cycle, project, or labels

Edit documents⁠

In addition to creating issues and updating projects and initiatives, Loops can now edit documents. When scope or timing changes, a loop can update the relevant Linear document so plans stay aligned.

Share updates in Slack⁠

A loop can now also draft and post tailored Slack updates using context from Linear and connected tools. Keep the right people informed about what changed and what happens next.

Continue any run⁠

Each loop run starts a conversation with Linear Agent. Once it finishes, you can continue that conversation like any other agent session to review the work, add context, or direct what happens next.

Loops credits available until end of year⁠

We’ve extended introductory Loops credits through December 31, giving teams more time to test Loops on their own workflows. See the docs for more details.

Callout components⁠

Use callout components to draw attention to important information in issue and project descriptions, as well as documents. Choose any color, icon, or emoji to match the context.

In PR descriptions, Linear converts callouts to the closest matching GitHub callout type, so the emphasis carries over.

Type /callout to get started.

An active workspace can create a significant amount of notifications each day, and until now your inbox treated them all the same. The new Priority tab separates what needs your attention from what can wait, so something like a review blocking a release never gets buried.

Linear selects what appears in Priority by default, with the option to customize it by choosing notification sources or creating a filter. You can also continue using the inbox just as you do today.

To get started, open the inbox display options or read the docs.

Draft projects with Linear Agent⁠

The new project composer lets you develop ideas with Linear Agent before creating a live project. Inside the composer, Linear can pull in relevant context from your workspace and connected tools to sharpen the brief and build out a plan.

Drafts save automatically as you work, so you can return to the draft without losing progress.

Select Create with Agent in the project creation page to get started.

Document editing on mobile⁠

Document creation and editing are now available in Linear’s iOS and Android apps. Start a doc while the context is fresh, update a plan as it changes, or fix a detail before it sends someone in the wrong direction, without waiting until you’re back at your desk.

Rich previews in diffs⁠

Images, fonts, Markdown, and PDFs now render directly inside Linear diffs. Reviewers can see the output alongside the code and understand what changed without leaving the pull request.

Symlinks are also now supported, shown as file-based changes.

Third-party app approvals⁠

As more apps and agents connect to your workspace, admins need control over which ones can access company data. Third-party app approvals are now available on paid Linear plans, allowing admins to review and approve apps before they’re installed.

Learn more in the docs.

Linear Agent can now set up, run, and test your code before returning its work. That means fewer handoffs and changes that are further along when they come back to you.

We’re also introducing lower, more transparent pricing, making AI credit usage easier to understand and control.

Configurable environments⁠

Coding sessions now automatically adapt to each codebase’s configuration, with broader out-of-the-box support for Python, Ruby, Go, and more.

During a session, Linear detects and installs the toolchains and dependencies it needs to complete the task. Teams can go further by pinning runtime versions, adding setup scripts, and defining environment variables.

To get started, create an environment in settings. Visit the docs for more details.

Browser testing⁠

Once the application is running, Linear Agent tests its work where users experience it: in the browser.

The agent opens the app, navigates through a flow, and verifies its implementation. It also captures before-and-after screenshots, making visual changes easier to review alongside the code.

Browser testing can catch broken interactions and visual regressions that code review alone might miss. If the agent finds a problem, it can make a fix, rerun the test, and return the work with that validation complete.

Transparent pricing⁠

As coding sessions take on more work, costs need to be easy to understand and easy to control.

Starting today, coding sessions use a lower-cost pricing model with two components:

• Model usage: Tokens are charged at the provider’s published rates, with no markup
• Sandbox runtime: Charged at $0.25 per 20-minute block

Together, model usage and runtime determine the AI credit cost of a session. The usage dashboard shows the breakdown, along with token usage and cost by model.

Admins can also set workspace-wide and per-user spend limits that reset daily, weekly, or monthly. When a limit is reached, additional AI credit usage is paused until the limit resets or an admin increases it.

Learn more about AI credits in the docs.

Initiatives are Linear’s way to manage product strategy and high-level planning across projects. Strategy may start at the company level, but teams carry it forward. You can now assign a team to lead an initiative, making it clear who is responsible for driving the work and how it contributes to the broader direction.

For work that requires tighter access, initiatives led by private teams are only visible to team members. This creates a secure place for confidential planning, regulated projects, audits, and other restricted work.

Learn more about initiatives in the docs.

Enterprise-managed authorization for MCP⁠

Linear’s MCP now supports managing employee access through your existing Okta-managed identity.

When employees connect from a supported Anthropic agent, Linear verifies their identity through Okta and applies their existing Linear permissions. Admins can manage access centrally, without requiring employees to sign in or authorize Linear individually.

Available to Enterprise workspaces with Okta SAML configured. Learn more in the docs.

Your coding session doesn’t have to stop when you leave your desk. Use the Linear mobile app to review code changes, comment on specific lines, and iterate with Linear Agent.

Open any diff and switch to the Changes tab to inspect the code. When you spot something to change, tap the relevant line to add it to your message to steer the coding session in the direction you want.

We’ve also added section under My Issues → Assigned for your delegated issues. It shows the status of each coding session, and gives you a quick way back into active work.

Download the Linear mobile app for iOS and Android.

Guided Reviews are now generally available⁠

Guided Reviews break diffs into focused sections with explainers on what changed and why. As part of general availability, they are now generated for larger pull requests, with a bigger context window and better latency.

Guided Reviews are available on Business and Enterprise plans at no additional cost.

Support for GitHub teams in reviews⁠

You can now assign reviews to GitHub teams. Review requests assigned to your GitHub teams appear in a dedicated section of the Reviews inbox. Learn more in the docs.

Signed commits for coding sessions⁠

Coding sessions now support signed commits. Add your SSH or GPG key in Settings to enable signing.

Workspace admins can also require users to upload a signing key before using coding sessions.

GitHub Copilot for Linear⁠

GitHub Copilot users can assign issues directly to Copilot’s cloud agent from Linear. Copilot uses the issue context to work in its own development environment, open draft pull requests, and update the issue as it makes progress.

Choose model and agent settings, set the base and working branches, then steer ongoing work through comments in Linear. To get started, install GitHub Copilot for Linear, or read the GitHub announcement for more details.

Documents and project descriptions are critical context for your teams and agents.

You can now edit text with Linear Agent, and use Loops to keep docs and project descriptions up-to-date. Author name indicators let you check if text was written by a colleague or added by a loop.

When editing, changes you make through Linear Agent highlight separately so they’re easy to review. If you need to revert to an earlier version, restore to any previous checkpoint from version history.

Show author names or open version history from the ⌘/Ctrl + K menu, or in document display options. Learn more in our documentation.

Refreshed issue sidebar⁠

The issue sidebar now closely integrates issue properties with the main content. We’ve pinned Diffs to the top of this panel so you can access the issue’s pull requests from anywhere on the page.

Loops are a new way for Linear Agent to take on recurring work for your team.

Describe the job in plain language and then choose whether it should run on a schedule or in response to an event. From there, Loops use context from your workspace and connected tools to decide on the next best action.

For example:

• Review incoming issues, research root causes, and dispatch to coding agents
• Create and coordinate follow-up work based on unstructured notes, like meeting transcripts or incident reports
• Keep launch plans and project specifications up-to-date
• See more ways to use Loops in the docs

Loops run at the team and workspace level, with shared visibility and control. Anyone with access can review their instructions, see how they are configured, and inspect what happened during each run.

Loops are available today on Business and Enterprise plans and use AI credits. To help you get started and understand usage, we’re giving your workspace $20 per seat in promotional credits. These credits are applied automatically to runs, and expire on August 20, 2026.

Read the blog post to learn more.

Initiatives define your company’s high-level goals and organize the projects that contribute to them. To help you manage initiatives as your roadmap grows, we’ve added a new set of focused initiative properties:

• Proposed and canceled statuses make it clear when an initiative is under consideration or has been intentionally set aside
• Priority communicates which initiatives are most important
• Labels group initiatives by product line, region, or other meaningful categories

Use these properties to group and filter initiatives on any plan, or build custom initiative views on Enterprise plans. Learn more about initiative properties in the docs.

Centrally manage access to Linear’s MCP server in Claude⁠

Give employees secure access to Linear and other MCP servers in Claude, without requiring them to authenticate with each server individually.

Enterprise-managed Authorization lets Okta administrators manage access and permissions centrally, and users automatically get access to the MCP servers they’re authorized to use when they sign in to Claude.

Enterprise-Managed Authorization is available to Enterprise workspaces using Okta as an identity provider and Claude as an MCP client. Learn more in the docs or in the MCP specification.

Share filtered views⁠

You can now share any filtered view by copying its URL from your browser, or by pressing ⌘/Ctrl Shift C on desktop.

Share filtered views to discuss a subset of an existing view with someone else — like an issue view filtered by an assignee, or project or initiative view filtered by a label.