Top all-time · #1815
Augment Code Blog
Company blog · augmentcode.com/blogaiprogramming
Augment Code Blog is the company blog at augmentcode.com, writing about ai and programming. Since 2024, 41 different Hacker News readers have linked it 82 times, most often “Augment”. It is still writing: the last post was on 2026-10-08, and you can follow it by feed.
Too few sampled comments (15) to say how often HN recommends it.?
Why HN links it
Augment Code's blog posts on its funding, Context Lineage, AI model pickers and an AI code review benchmark. Commenters mostly mention the Augment product and link posts, without judging the writing.
Summarised by Claude from a sample of 15 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Your engineers have agents. Your organization doesn't. Cosmos is the platform that closes the gap.
Most-linked posts?
- Augment5 people · 5 mentions · first linked 2024-04-25
- A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all4 people · 4 mentions · first linked 2026-04-22
- Intent – The developer workspace for agent orchestration – Augment Code4 people · 4 mentions · first linked 2026-02-05
- Augment Raises $227M at $977M Valuation to Empower Software Teams with AI3 people · 3 mentions · first linked 2024-04-24
- /2 people · 3 mentions · first linked 2025-02-04
- #1 open-source agent on SWE-Bench Verified by combining Claude 3.7 and O12 people · 3 mentions · first linked 2025-03-31
- How I went AI-native in my terminal workflow2 people · 2 mentions · first linked 2026-03-27
- The end of linear work. What's beyond the IDE2 people · 2 mentions · first linked 2026-02-11
- What spec-driven development gets wrong2 people · 2 mentions · first linked 2026-02-24
- Building a Real-Time Context Engine for Our Code LLM: No More 10-Minute Delays2 people · 2 mentions · first linked 2025-01-30
What Hacker News says?
at Augment ( https://augmentcode.com ) we were one of the partner who tested 3.7 pre-launch. And it has been a pretty significant increase in quality and code understanding. Happy to answer some questions FYI, We use Claude 3.7 has part of the new features we are shipping around Code Agent & more.
Comment linking /
on “Claude 3.7 Sonnet and Claude Code”Submitted Developers are choosing older AI models as a story · 183 points
HN discussionIMHO, I would agree with you. I think chat is a nice intermediary evolution between the CLI (that we use every day) and whatever comes next. I work at Augment ( https://augmentcode.com ), which, surprise surprise, is an AI coding assistant. We think about the new modality required to interact with code and AI on a daily basis. Beside increase productivity (and happiness, as you don't have to do mundane tasks like te…
Comment linking /
on “Chat is a bad UI pattern for development tools”Submitted How We Optimize LLM Inference for AI Coding Assistant as a story · 30 points
HN discussionI wonder if Augment [1] are working on a Zed plugin. I've been using Augment for more than a year in Jetbrains IDEs, and been very impressed by it, both the autocomplete and the Cursor-style agent. I've looked at Cursor and couldn't figure out why anyone needed to use a dedicated IDE when Augment exists as a plugin. Colleagues who have used Cursor have switched to Augment and say it's better. Seems to me like Augmen…
Comment linking /
on “Claude Code: Now in Beta in Zed”Submitted Augment Code: Developer AI for Teams as a story · 29 points
HN discussionRight now the Swe-Bench leader Augment Agent still use Claude 3.7 in combo with o1. https://www.augmentcode.com/blog/1-open-source-agent-on-swe-... The findings are open sourced on a repo too https://github.com/augmentcode/augment-swebench-agent
Comment linking /blog/1-open-source-agent-on-swe-bench-verified-by-combining-claude-3-7-and-o1
on “OpenAI o3 and o4-mini”Submitted Why GPT-5.2 is our model of choice for Augment Code Review as a story · 12 points
HN discussion> Nothing on infra costs, hardware throughput + capacity (accounting for hidden tokens) & depreciation That's because it's coming at things from the other end: since we can't be sure exactly what companies are doing, we're just going to look at the actual market incentives and pricing available and try to work backwards from there. And to be fair, it also cites, for instance, deepseek's paper where they talk about w…
Comment linking /blog/developers-are-choosing-older-ai-models-and-16b-tokens-of-data-explain-why;
on “How OpenAI uses complex and circular deals to fuel its multibillion-dollar rise”Submitted Augment Raises $227M at $977M Valuation to Empower Software Teams with AI as a story · 10 points
HN discussionTry Augment https://www.augmentcode.com/ The IntelliJ integration works really well. Not sure why they aren't more widely known.
Comment linking /
on “GitHub Copilot: The Agent Awakens”Submitted #1 open-source agent on SWE-Bench Verified by combining Claude 3.7 and O1 as a story · 9 points
HN discussionThey raised 277M. I hope they don't need to raise more money: https://www.augmentcode.com/blog/augment-inc-raises-227-mill...
Comment linking /blog/augment-inc-raises-227-million
on “Augment, a GitHub Copilot rival, launches out of stealth”Submitted Augment Code's Next Chapter as a story · 4 points
HN discussionOfficial post: https://www.augmentcode.com/blog/augment-inc-raises-227-mill...
Comment linking /blog/augment-inc-raises-227-million
on “Augment, a GitHub Copilot rival, launches out of stealth”Submitted Rethinking LLM Inference: Why Developer AI Needs a Different Approach as a story · 4 points
HN discussionCongrats. From my experience, Augment ( https://augmentcode.com ) is best in class for AI code context. How does this compare?
Comment linking /
on “Launch HN: Nia (YC S25) – Give better context to coding agents”Submitted AI transformation is a systems problem: a conversation with Justin Reock, DX as a story · 3 points
HN discussionhttps://www.augmentcode.com/blog/ai-model-pickers-are-a-desi... Augment does not have a model picker. It uses Claude 3.7 right now. The context engine is the magic sauce. It’s miles ahead of all the other tools, almost always gets it right where others fail.
Comment linking /blog/ai-model-pickers-are-a-design-failure-not-a-feature
on “Cursor hits $9B valuation”Submitted A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all as a story · 3 points
HN discussionNice, only got the pro plan and didn't want to get Nickel and Dimed per usage so ended up ignoring claude code, but will give it another go now to see how far I can get with the Pro plan. Turned out to be a blessing as it led me to discovering augmentcode.com which I'm now using. It's a monthly usage cap but has a unique context engine where it indexes your entire code base which gives its agents access to a lot mor…
Comment linking /blog/claude-sonnet-4-the-best-model-with-the-best-context-engine
on “Claude Code is now available to Pro plans”Submitted What spec-driven development gets wrong as a story · 3 points
HN discussionYou can try the service for free at https://www.augmentcode.com/
Comment linking /
on “Augment.vim: AI Chat and completion in Vim and Neovim”Submitted We're in an Exponential as a story · 3 points
HN discussionIt looks like it integrates directly with the Augment service [1] (and it's made by them). It sounds like Augment is some kind of a bespoke coding assistant that also does various RAG things to automatically get better context on large codebases. Never tried it so no idea how good it is. 1: https://www.augmentcode.com/blog/augment-code-vim-and-neovim...
Comment linking /blog/augment-code-vim-and-neovim-extension
on “Augment.vim: AI Chat and completion in Vim and Neovim”Submitted Show HN: We got sick of juggling terminals for AI agents so we built a workspace as a story · 3 points
HN discussionAugment Code ( https://www.augmentcode.com/ ) extension in VSCode. The remote agent feature is fantastic and the local agent is worth buying credits for. I've tried almost every AI editor (Cursor, Windsurf, Roo/Cline etc.), tried CLI-based coders (Claude Code, Aider, Codex etc.), and have used them all with ton of useful MCPs and in the end, I've had the best results with Augment.
Comment linking /
on “Ask HN: What useful AI tools do you use every day?”Submitted We Added ACP Support to Augment (Now in Zed, Neovim, and Emacs) as a story · 3 points
HN discussionIMO these are exactly the right observations given the current tools. Maybe give Augment a try ( https://www.augmentcode.com/blog/augment-is-free-for-open-so... ). Disclosure: I work there. We've tried hard to improve AI models in these dimensions, but certainly a long way to go. Feedback would be highly appreciated.
Comment linking /blog/augment-is-free-for-open-source
on “Ask HN: Teams using AI – how do you prevent it from breaking your codebase?”Submitted Augment Code model comparison: GPT-5 vs. Claude Sonnet 4 as a story · 3 points
HN discussion
