Chris Marty

From the start, one of our big bets at @augmentcode has been that the IDE won't be where Software Engineers of the future spend most of their time. That bet is only now becoming obvious to the rest of the world. If you're an AI-pilled Product Designer who wants to design the post-IDE future of building software, my DMs are open.

GPT-5.4 is now the default model in Augment, and it’s free for a limited time.

So what would you say....you do here?

Introducing Augment Code Review, powered by GPT 5.2. It's the #1-ranked AI code reviewer across precision, recall, and overall quality. Free for the first week for every paying customer, and free for open source projects.

Users love our Context Engine. Last week, we made it available to all agents as an MCP server. Today, we're sharing our 🚀Context Engine SDK🚀. What we do with context, you can do too. You can build agents and tools that retrieve from codebases, docs, configs (and more)! 📚 Quickstart: docs.augmentcode.com/context-servic… 💡 Examples: docs.augmentcode.com/context-servic… More to come in the next couple of weeks! Here's what you can build with it 🧵

Launch Week Day 1: Tasklist is here Eagle-eyed power users have already been putting Tasklist to work. Now, we’re showing you how to get the most out of it. With Tasklist, we’re making it way easier to take a big, vague task—and break it down step by step. So you can actually see what your Agent’s doing, monitor progress, and make changes as you go. It works the same way the most productive engineers do: - Define the ideal outcome - Break it into steps - Verify the plan makes sense That breakdown gives you confidence. Tasklist builds that into how the Agent works.

The top question we get: what's the difference between Augment Code and Cursor? Our answer: it's all about our Context Engine. We're built for pro software teams working in production-grade (read: large) codebases. We index your repository in real time, so we can feed the most relevant information to the underlying models. Result? Better suggestions. Better Agent outcomes. Better code. Of course there's more: security, privacy, no forks, no model picker (pro software engineers are too busy shipping). But, we know it's hard to understand the difference without seeing it for yourself. So, to help you cut through the hype, we're launching a special offer for Cursor Pro users: upload your invoice, and we'll give you an additional 600 user messages (on top of the 300 in our trial!) for free. We can tell you what the difference is, but it's better if you see it for yourself. New to Augment Code, but not to AI coding? Sign up here: app.augmentcode.com/promotions/cur…

This is what we solved at @augmentcode.

@augmentcode has been hands down the best AI editor I have used, and I am not saying it lightly, as I have been a very early user of @GitHubCopilot , then I switched over to @cursor_ai and use it for a long time, I also dabbled with @windsurf_ai . contd... 🙏🔁 RT/❤️Like

I did a side-by-side of Cursor (with Claude 4 & Gemini 2.5) vs AugmentCode on a medium-size codebase. Easy Task: make a sidebar collapsible. Cursor+Claude/Gemini failed—multiple back-and-forths, never got it working. AugmentCode nailed it on the first try. I find Cursor gets increasingly confused as codebases grow. Feels like more work than help—leaving me exasperated and thinking I should’ve just done it myself. Switching to @augmentcode @laserlikemike

I don’t think the next big leap in software productivity comes from “vibe coding.” It comes from removing the grind in real codebases.@AugmentCode’s new Remote Agent tackles flaky tests, stale docs & tedious refactors—with up to 10 autonomous agents. Learn more: augmentcode.com

Software development is changing faster than at any other time in the history of computing. We are introducing what we believe to be the next phase:

once you go background agent, you never go back. today our AI for code company @augmentcode launched remote agents. delegate coding tasks & walk away, come back when it’s done to review & approve.

Introducing Remote Agent - cloud-based dev agents with full-codebase context, deep IDE integration, and full toolchain access. Available in VS Code.

This is pretty cool. By implementing my sequential thinking MCP, Augment Code achieved the top SWE-bench score of 65.4%. Glad my opensource contribution is helping move the space forward.

Goodbye Cursor Augment Agent just dropped and it has taken coding to the next level. 7 Powerful features you don't want to miss:

Augment Agent is now live. Designed for large-scale codebases — with 200K context tokens, persistent memory, and deep tool integrations, Augment Agent is available in VS Code and JetBrains.

Augment Code debuts AI agent with 70% win rate over GitHub Copilot and record-breaking SWE-bench score venturebeat.com/ai/augment-cod…

My project has 39,205 lines of code, and Cursor can't answer questions about it. Cursor's context seems to be capped at around 10,000 tokens. Unfortunately, this is not enough for any decent-sized project. If you have a large codebase, check out @augmentcode. This thing is faaaast! I'm currently using their Visual Studio Code plugin, but you can also use them on JetBrains, Neovim, and even Vim. (I'm a Neovim fan, but Copilot's implementation for Neovim is nowhere as good as Augment Code.) Augment Code was gracious enough to sponsor this post. After you install their extension and run it for the first time, it will index your entire codebase. This is why it can answer questions as fast as it does, regardless of the size of your codebase. Augment Code supports chat and completions like every other AI coding assistant, but its killer feature is "Next Edit." When you make a change, two things happen: 1. The model analyzes the change to determine the ripple effects across your *entire* codebase. 2. The model suggests everything you need to update to ensure everything works correctly. This is pretty wild!