Sign in

Augment Code

@augmentcode.com
338 followers 261 following 344 posts

The Developer AI that deeply understands your codebase and how your team builds software. Augment puts your team’s collective knowledge at your fingertips.

PostsRepliesMedia
Augment Code @augmentcode.com · 29/09/2025
Claude Sonnet 4.5 from Anthropic is now the default model for Augment Code. We’re rolling it out to all customers over the next 24 hours, where it will be available alongside Sonnet 4 (for a limited time) and GPT-5 in the model picker.
130
Augment Code @augmentcode.com · 28/08/2025
The Auggie CLI is now available for everyone. Auggie brings Augment’s industry-leading context engine to every part of your stack—terminal, CI, and beyond. Getting started is simple: npm install -g @augmentcode/auggie www.augmentcode.com/product/CLI
100
Augment Code @augmentcode.com · 09/07/2025
Every project, team, and workflow is unique. Augment Rules empower you to specify exactly how your agent should behave. Simply add instruction files to .augment/rules/ and your agent will adapt.
100
Augment Code @augmentcode.com · 09/07/2025
With Augment Rules, your software agent can build just like your team does.
120
Augment Code @augmentcode.com · 03/07/2025
PS: That’s why we built Prompt Enhancer —it auto-pulls context from your codebase and rewrites your prompt for clarity. Available now in VS Code & JetBrains: just click ✨ and ship better prompts, faster.
010
Augment Code @augmentcode.com · 02/07/2025
Guess now we can predict Asia's lunch time 💀
000
Augment Code @augmentcode.com · 29/05/2025
🆕 Mermaid diagrams in Augment Agent Agent reads your codebase, understands structure, and renders a Mermaid diagram—directly from your prompt.
100
Augment Code @augmentcode.com · 16/05/2025
But it’s not just about question quality. We needed a benchmark that could evolve with the product. So we designed AugmentQA as a loop — not a static test. The cycle looks like this:
100
Augment Code @augmentcode.com · 14/05/2025
❌ “Write better prompts.” ✅ Just click Enhance ✨
120
Augment Code @augmentcode.com · 01/05/2025
Is left vs right panel chat placement the new tabs vs spaces? Drop your take in the comments
100
Augment Code @augmentcode.com · 18/04/2025
UI’s broken. It’s obvious on screen. But tracking down the cause? Hours of inspecting styles and guessing at layout logic. Drag the bug into our agent. It analyzes the UI, finds the root cause, and proposes a fix — with context.
000
Augment Code @augmentcode.com · 15/04/2025
𝐆𝐏𝐓-𝟒.𝟏 𝐚𝐥𝐦𝐨𝐬𝐭 𝐭𝐨𝐩𝐬 𝐂𝐥𝐚𝐮𝐝𝐞 𝟑.𝟕 𝐨𝐧 𝐜𝐨𝐝𝐢𝐧𝐠?! New eval dropping using our #1 SWE-bench coding agent! - GPT-4.1 beats Gemini 2.5 Pro and almost tops Claude 3.7 Sonnet! - Even GPT-4.1 mini matches Claude 3.5 Sonnet V2 performance. It was the top model just 2mo ago!
100
Augment Code @augmentcode.com · 10/04/2025
LLaMa 4 beats Deepseek-R1 and V3 on coding?! Fresh evaluation using our #1 SWE-bench coding agent and >200,000,000 tokens of production-grade code: Claude 3.7 Sonnet > Gemini 2.5 Pro > LLaMA 4 Maverick > DeepSeek-V3 > Deepseek-R1
000
Augment Code @augmentcode.com · 04/04/2025
9/ While Agent is running… - Skill grows over time. - Beginners: observe and approve - Intermediates: multitask Power users: collaborate + course-correct in real time
100
Augment Code @augmentcode.com · 04/04/2025
7/ What if it messes up? - If it's totally off: start a new session - If it's slightly off: nudge it back Bonus: Use checkpoints to undo mistakes.
100
Augment Code @augmentcode.com · 04/04/2025
2/ How should I prompt? Don't under-specify. More details → better results.
100
Augment Code @augmentcode.com · 03/04/2025
Unlimited Agent, for a limited time. We want to hear from our community and see how you use agents, because pricing should be fair and predictable. Try it out now. We’ll update to usage pricing in the future.
200
Augment Code @augmentcode.com · 03/04/2025
Built on our Context Engine and extended via MCP: - Supabase, Figma, Vercel, Cloudflare, Sentry, and more - Connect your stack in seconds - Add your own tools to the agent's context Don’t just write code, build software.
110
Augment Code @augmentcode.com · 03/04/2025
🛡️ Code Checkpoints Every step is logged. Every edit is reversible. Agent creates checkpoints before running actions — giving you full control without slowing you down. Like version control for your AI.
100
Augment Code @augmentcode.com · 03/04/2025
🐛Visual debugging. - Drag in a screenshot. - Agent identifies the UI issue (CSS, layout, logic). - Suggests a fix. - Runs only the relevant tests. Debugging becomes: drop, fix, confirm.
100
Augment Code @augmentcode.com · 03/04/2025
⚙️ Integrated Dev Workflows Use Agent to go from ticket → code → PR without switching tools: - GitHub: branch, commit, PR - Linear: issue detection + resolution - Notion, JIRA, Confluence: context → implementation AI becomes part of your actual workflow.
100
Augment Code @augmentcode.com · 03/04/2025
🧩 Persistent Memory Agent adapts to how you work: - Learns your coding style - Remembers previous refactors - Adjusts to your infra and conventions Memory builds over time. You don’t have to re-teach it on every session.
100
Augment Code @augmentcode.com · 01/04/2025
For the love of code.
030
Augment Code @augmentcode.com · 31/03/2025
🧵 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/... Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇
120
Augment Code @augmentcode.com · 25/03/2025
When tested against leading open-source models from the CoIR leaderboard, Augment's retrieval system significantly outperformed them on real tasks—even though those models ranked higher on synthetic tests. This demonstrates a critical gap between benchmark performance and practical utility.
110
Augment Code @augmentcode.com · 25/03/2025
What makes AugmentQA special is that it evolves over time. By continually collecting new failure cases from actual use, the benchmark gets tougher and more reflective of real-world engineering complexity.
100
Augment Code @augmentcode.com · 25/03/2025
Most code retrieval benchmarks optimize for synthetic problems. But professional software engineers don't solve artificial puzzles--they navigate large, often messy codebases.
110
Augment Code @augmentcode.com · 25/03/2025
The morning routine.
020
Augment Code @augmentcode.com · 17/03/2025
Use Instructions in VS Code to write or modify blocks of code using natural language. Refactor a function, write unit tests, or craft any prompt to transform your code. 👉 Hit ⌘I and get started.
030
Augment Code @augmentcode.com · 11/03/2025
Context aware code completions in Vim 🩶 Get started here: hjkl.ai
041
Augment Code @augmentcode.com · 08/03/2025
Fun fact: the #3 IDE on Augment Code? Cursor.
130
Augment Code @augmentcode.com · 05/03/2025
Vim and Neovim developers can now get Augment’s powerful code completions and chat–yes, chat!–right in their editors. Get started: hjkl.ai
030
Augment Code @augmentcode.com · 25/02/2025
Sonnet 3.7 yields step-size improvements in the quality of our agents (to be released soon!!) across many tasks like bug fixing and implementing medium-sized features. We believe it will play a key role in the evolution of AI coding agents in 2025 and tested it extensively in preview.
110
Augment Code @augmentcode.com · 25/02/2025
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 👀
261
Augment Code @augmentcode.com · 19/02/2025
No more manual updates. No more missed references. Just write code and let AI handle the ripple effects.
120
Augment Code @augmentcode.com · 19/02/2025
💡 Show of hands: Who's spent hours updating their codebase after a "simple" field change? We built Next Edit at Augment to eliminate this type of toil. Next Edit understands your code's dependencies and automatically propagates changes across your workspace.
110
Augment Code @augmentcode.com · 06/02/2025
Now available in @jetbrains.com IDEs: Use smart apply to add code directly from chat and see the changes Augment helps you make.
031
Augment Code @augmentcode.com · 09/12/2024
Imagine building software with an AI that deeply understands your complex codebase. Join a live demo of Augment Code to see how it helps with onboarding, testing, and refactoring that fit your stack. Register here: get.augmentcode.com/augment-code...
010
Augment Code @augmentcode.com · 04/12/2024
Augment is free for open source contributors and maintainers. 🎉 Augment’s deep codebase understanding tears down some of the biggest pains for working on open-source projects– the context you need to contribute and the help you need to make quality PRs. Sign up at augmentcode.com/opensource
053
Augment Code @augmentcode.com · 03/12/2024
Discover how Augment's lightning-fast responses transformed the coding experience for AMP, a leader in AI-powered recycling solutions. Read the story: augmentcode.com/blog/amp-str...
000
Augment Code @augmentcode.com · 26/11/2024
Here's a real example: Traditional AI gets stuck on incomplete functions, repeating suggestions. RLDB understands the context and provides meaningful completions.
100
Augment Code @augmentcode.com · 26/11/2024
🚨🧵Major breakthrough in AI code completion Our code completion model just got as smart as one 2x larger. The secret? Learning from how developers actually write code, not just finished repos. Check out these gains:
Accuracy of code completion models on our internal benchmark. The boost our model gets from RLDB is similar in size to doubling the model size, or doubling the amount of training data.
141
Augment Code @augmentcode.com · 22/11/2024
Outdated legacy code vs Augment 🔥 👀
010