Amp

You can now send feedback to Amp directly from your website. Enable the feedback widget in the settings for your project and add one script to your website. Then visit the site with ?amp appended, and the annotation widget is displayed. Click on any part of the page and write instructions for Amp. Once you are done, send the feedback to Amp. The first time, you sign in with Amp. Then Amp starts a new thread in your project and makes the change. You ship it from the thread like any other change.

Today we're launching spaces, a new way to interact with agents and your team in Amp. A space is a conversation with a single agent whose job is to spawn and coordinate agents for you. You no longer have to create and organize threads yourself; the agent in a space will do it for you. It's a new, higher-level way to work with many agents. After using spaces for the past few weeks, we think this might be the future of interacting with agents. There's something special about this way of working. You operate with a bird's-eye view but can still dive into the weeds when necessary.

Amp now integrates with GitLab, on gitlab.com and on self-managed instances. Connect your GitLab account and you can start projects from your GitLab repositories. Orbs clone and push as you and come with glab signed in, so the agent can open merge requests, comment on them, and read issues and pipelines. Amp can also subscribe to comments and CI for a merge request it opens. A reviewer's request or a failed pipeline lands in the thread that wrote the code, so Amp already has the context. Ask Amp to start a new orb for every new merge request or issue in a project.

Agents in Amp can now collaborate with you in Artifacts. These are documents that belong to a single thread and that the agent, you, and your teammates can all edit. Here are two examples from our real threads. This one is from Nicolay's thread, where he asked whether Amp wastes model calls while it waits on a long shell command. The agent went through 60 of our threads and wrote up what it found: how much the waiting costs, why, and a plan to fix it in two steps.

Amp now has a Mac: ask it to work on your iOS or Mac app and watch it build, test, and run the app. Your thread still runs on a Linux orb, next to your dev server and toolchain. The Mac is a second machine attached to that orb. Amp can automatically start a Mac, run commands on it, and read and write files, so it decides on its own when the work needs a Mac. When it does, our server boots a fresh Mac in the cloud with Xcode and the simulators installed, in about 30 seconds.

You can now ask Amp to visualize or build something for you and it will do it, right in the thread: charts, timelines, diagrams, and mockups you can click through. Here are some examples, from our real threads. Go ahead, hover and click through them: Here, for example, is an excerpt from Quinn's thread, where he asked for ways to fit a diff stat into a small button: And here's what went into building this feature:

You no longer need to be in a workspace to self-host orbs. Up until now, only workspace admins could manage self-hosted orb providers. Now, you can add a provider in your personal Settings → Orbs and set it up the same way as a workspace provider. When you create a thread, it shows up under Self-Hosted, marked Personal.

We now have an Android app: Download and install from ampcode.com/app, or scan this QR code:

Amp is now an agent in Linear. Assigning an issue to Amp starts a new Agent Session in Linear and spawns a new orb. You can also mention @Amp to kick off a session. Amp sends its response back to the same session and replies to messages sent along the way. The Agent Session also appears in your Amp sidebar and is fully viewable in Amp. Assign Amp an issue in Linear. Follow its progress in the Agent Session. Then open the same conversation in Amp. To get started, install the Amp agent in your Linear workspace and connect your Amp account to the Linear MCP in Settings → MCP & Integrations. Read the docs to learn more.

You can now see and control your macOS or Linux runner's desktop. This is nice for trying native apps that Amp builds for you, such as iOS apps: Turn on Share This Mac's Display under Settings › Runner in the macOS app, or start your runner with amp --no-tui --desktop. Your Amp client connects directly to the runner, so it's nearly instant when the runner is on your local network or nearby. Read See and Control the Runner's Desktop for more details.

You can now talk to Puck from ChatGPT, Claude, and other agents via MCP. After developing an idea with ChatGPT's voice mode on a walk, send it directly to Puck for implementation. Puck knows your projects in Amp and routes it to the right orb. In the same conversation, you can check in on your work in Amp directly from ChatGPT. Puck MCP offers two tools: puck for interacting with your Puck in Amp, and orbs for showing an interactive view of your running orbs with links to their portals. You're talking to the same Puck you use in Amp. It can look through your threads, find earlier work, and coordinate your agents. To connect, open Settings > Puck. Click Add to Claude, or copy ampcode.com/mcp into ChatGPT or another MCP client, then sign in with your Amp account. See Use Puck in Other Apps for details.

The Changes pane now automatically puts files in an intelligent order. Amp reads the diff, identifies the files that are essential to the change, and puts them first. If the diff changes, Amp computes an updated order without rearranging the files while you’re reviewing them. Instead, a blue dot will appear over the intelligent ordering button, which you can click to apply the updated order. The new automatic intelligent ordering is computed much more rapidly. Here is a comparison of the same diff ordered by both the old and new method: You can optionally go back to alphabetical file ordering by clicking the ordering button.

Amp now follows up on GitHub pull requests it opens. Comments, reviews, and CI results show up in the same thread. When Amp opens a PR, the agent can now subscribe to the PR's comments, reviews, and CI for its latest commit. A failing check or a reviewer's question shows up in the same thread, and Amp already has the context to deal with it. This is enabled by our new first-class support for GitHub Webhooks.

You can now use your Claude Subscription in Amp. It's free and available for everyone now. When creating a new thread, just pick Mode > Claude Code. It'll ask to link your Claude sub if you haven't already done that. Under the hood, this mode uses the Claude Agent SDK instead of Amp's own agent. But we made it all work: orbs and runners, thread sharing, portals, multiplayer, thread-to-thread messaging and orchestration, etc. See the Claude sub docs for more information.

You can now have multiple separate conversations with Puck. We know you love Puck. We also know you've been asking Puck about your recent orbs, a bug fix, and dinner plans, all in the same conversation. Now each of those can be its own conversation, and each one gets its own Puck. Press + to start a new conversation. Click the conversation's name at the top to switch between them. Conversations you haven't touched in three days move into Inactive so the list stays short. Read more about Puck conversations in the docs.

Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token. Open the mode picker in the new thread dialog, choose a mode that uses GPT-6 Astra (e.g., the default High mode), and move the speed switch past Fast to Plaid. Plaid currently works with Amp-provided inference only, as OpenAI does not yet support ultrafast for linked ChatGPT subscriptions. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast or standard speed. Like fast mode, Plaid can be toggled on or off for an existing thread.

Amp now collapses your agent's step-by-step work even more, since you care about what the agent did, not how it got there. (You can still expand the steps when needed.) A year ago, watching your agent's every step sometimes helped, and you probably were only running one agent. Now? You have lots of agents. You should be giving them harder, deeper work and verification demands. They should run for longer on their own, without you watching them from up close. If you have the patience to watch your agents work, you're giving them too short a leash.

You can now share a runner with your workspace. Start it with --share and everyone in your workspace can start threads on that machine from ampcode.com. If you have a machine with GPUs, a Mac that's used to build and sign the iOS app, or a dev box in a specific network, you can now set it up and the whole team can spawn agents on it: Everyone in your workspace now sees it in the picker under Shared Runners. With --amp-env, a shared runner gets the workspace and project Secrets & Env Vars, but never your personal ones. That applies to your own threads on it too.

The Amp app for macOS now starts a runner for you. You no longer need amp --no-tui open in a terminal to run threads on your Mac. Open App Settings… (⌘⇧,), go to Runner, and click + to add a folder or one of your projects. Start a thread and your Mac is right there in the picker, marked This Mac. You can also pick it when you start a thread from ampcode.com, your phone, or Puck. Keep This Mac Awake stops your Mac from going to sleep while the runner is on and the Mac is plugged in, so you can still start threads on it after you walk away. The screen still turns off and locks. On battery, or when you close the lid, your Mac sleeps as usual. Read more in the runner docs.

A runner can now create Git worktrees. Pick a repository the runner serves, hit Tab, name the branch, and the thread starts in a fresh checkout. Your main checkout stays untouched. In the directory picker, every Git checkout on the runner gets a New Worktree option next to it. Choose it and you get a small form: The name you chose becomes the branch name and the folder name. The runner then creates the worktree as a sibling of the repository: ~/code/amp gets ~/code/amp-fix-flaky-login-test, checked out on a new branch fix-flaky-login-test off the current HEAD.

A runner can now serve many directories, not just the one it was started in. You can point it at specific projects and directories or let it find your Git repositories. Start a runner and tell it which directories to serve with --dir. Repeat the flag for each one: Or start it in the directory that holds your checkouts and let it find them: --discover-dirs serves every Git checkout up to two levels beneath the current directory and picks up new ones as you clone them. Checkouts somewhere else, or deeper than two levels?

We've added a Restack button that organizes all of your thread's changes into a cleaner set of commits. Use it to split a large diff into logical pieces for review, clean up an agent's intermediate commits before merging, or combine small related commits. The final file contents stay the same. Read how to restack and review your changes in the docs.

Update (2026-10-23): Tune Modes now has one role per mode, Main Agent. You can no longer pin a model for the Oracle or for subagents, so the Oracle and Subagents rows in the screenshot below are gone. Task and Read Thread subagents run the same model and reasoning effort as the thread that started them. See Tune the Modes for how it works today. You can now choose the models behind Amp's builtin modes and put your own agents on the Dial. There are two tabs in Settings → Mode Dial. At launch, Tune Modes had three roles per mode. Today it has only Main Agent; see the update above.

When you send a message while the agent is working, it's now delivered at the next possible opportunity, instead of being queued until the agent finishes its turn. This means the agent acts on your feedback sooner and doesn't waste time on unnecessary verification steps. Most people won't need to change how they use Amp. If you do find Amp steering too abruptly, we've found that it works well to phrase your prompts like "When done, then ..." instead of "Now, ...". Ship, Review, and other builtin actions still queue, because usually you want to wait until the agent is done before shipping or getting a review. If needed, you can still queue from Amp or queue in the Amp CLI.

Your orb now has a desktop you can see and control. Use the Desktop tab in any orb thread to get a high-resolution interactive Linux desktop. It's useful for verifying the agent's work when developing for Linux, Android, or the Chrome extension API, or when working with file formats that need to be opened in desktop applications. It's also useful for computer use, CAD, and anytime you just want a desktop in the cloud. Modibo Sissoko, an Amp user, sent in a video of how he tests .docx files exported by his application in LibreOffice to make sure they look right: And if you're curious what Puck does for fun when not helping you, turn on Fun Games in Desktop: