Augment Code Blog

Congrats. From my experience, Augment (https://augmentcode.com) is best in class for AI code context. How does this compare?

Augment 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.

totally agree. Looks like the most common problem with the bubble is the terrible signal to noise ratio. Has anyone found a solution that works well? I see augment code is claiming their review agent is the best in terms of signal to noise ratio https://www.augmentcode.com/blog/we-benchmarked-7-ai-code-review-tools… has anyone tried it?

I 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 Augment is an AI tool flying under most people's radar; not sure why it's not all over Hacker News. [1] https://www.augmentcode.com/

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.

You can try the service for free at https://www.augmentcode.com/

Try Augment https://www.augmentcode.com/ The IntelliJ integration works really well. Not sure why they aren't more widely known.

Nice, 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 more content about your code base which helps when adding features to match your existing implementations without needing to explicitly feed it context in every agent message. It still uses Claude Sonnet 4 [1] under the hood so the results are great. Blows me away what AI agents are capable of these days, it's especially nice when they end up creating new Tailwind UIs (Vue) that's better looking than what I was even thinking about creating. [1] https://www.augmentcode.com/blog/claude-sonnet-4-the-best-model-with-t…

Intent from augmentcode is trying to be this https://www.augmentcode.com/product/intent

Think of a refactor where you tried one approach, rolled it back, then found the right fix. If you squash, all those failures vanish. With full history, an AI (or future you) can see the dead ends and spot patterns. I think that’s what Augment Code is doing with their Context Lineage idea: indexing the messy history so tools can explain how code evolved. https://www.augmentcode.com/blog/announcing-context-lineage

https://www.augmentcode.com/blog/ai-model-pickers-are-a-design-failure… 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.

It 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-extension

IMO 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-source). 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.

They raised 277M. I hope they don't need to raise more money: https://www.augmentcode.com/blog/augment-inc-raises-227-million

Official post: https://www.augmentcode.com/blog/augment-inc-raises-227-million

> 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 what their power foot margins are on inference. > just a blind faith that pricing by providers "covers all costs and more". It's not blind faith. I think they make a really good argument for why the pricing by providers almost certainly does cover all the costs and more. Again, including citing white papers by some of those providers. > Naive estimate of 1000 tokens per search using some simplistic queries, exactly the kind of usage you don't need or want an LLM for. Those token estimates were for comparing to search pricing to establish whether — relative to other things on the market — LLMs were expensive, so obviously they wanted to choose something where the domain is similar to search. That wasn't for determining whether inference was profitable or not in itself, and has absolutely no bearing on that. > Doesn't account at all for chain-of-thought (hidden tokens) that count as output tokens by the providers but are not present in the output (surprise). Most open-source providers provide thinking tokens in the output. Just separated by some tokens so…