devang

⌛️Countdown: 4 days till Launch Week. What are we shipping? Wrong answers only. Worst guesses get 4 months of Max.

Remote Agent is live in VS Code (v0.472.1). Early users are already shipping while they sleep. One dev launched 3 agents before logging off - woke up to a PR, docs, and a fixed flaky test. We’re celebrating wins like that by giving 5 devs 4 months of Augment Max ($1K in value…

Announcing Sim v0.3 Templates, knowledge bases, realtime collaboration, and more just dropped 🔻

Me and the boys discussing the windsurf acquisition rn

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…

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…

🚀 Claude Sonnet 4 is rolling out in Augment Code! @AnthropicAI's best model now powers every autocomplete, edit, and chat—no extra cost.

The team at @augmentcode gave me early access to their new feature called remote agent. It allows your AI agents to code even while you are not at your computer. It's absolutely incredible. Not only that but you can also run multiple agents in parallel. This has wider…

"while these `guy`s work, let me tell you a little bit more..." 😵‍💫😵‍💫😵‍💫

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

AI coding tools can expose your IP. Before integrating one, ask these 4 questions 👇

People have been liking the super simple open-source coding agent repo we released that got us to #1 on swebench-verified github.com/augmentcode/au…

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.

For the love of code.

the only non-embarassing response i have when someone asks me what my bench is

🧵We just released the #1 open-source agent on the SWE-bench Verified leaderboard by assembling the best of Claude Sonnet 3.7 and O1. Open-source repo here: github.com/augmentcode/au… Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇

Just bumped into @jyangballin on Stanford campus and discussed future of coding agents and swebench/sweagent. Very happy such smart and kind folks are working on this important problem with an open-source POV. The future is bright ☀️ Strongly believe open source is critical…

Simple benchmarks can still tell you a lot. @augmentcode uses a modified CCEval benchmark to measure the quality of context-aware, inline code completions — and it correlates well with actual user acceptance rates. augmentcode.com/blog/augment-l…

A simple idea to build the @UCBerkeley startup alumni network has grown beyond my wildest dreams into #AccelScholars, a tight-knit community of the most ambitious, talented, kind-hearted people, whose individual stories we’ve been fortunate to support for the past eight years

Want to use Claude Sonnet 3.7? Great news: it's now live in Augment, no credit card or pro plan required. Here's why Sonnet 3.7 is more than just hype. Sonnet 3.7 crushed one of our internal benchmarks by almost 10% over 3.5 👀