Aider Blog

Interesting article. What are the alternatives that address the issues raised? I see some folk recommending https://pi.dev/. Has anyone used https://aider.chat/ and liked it?

I just started using aider, recommend it: https://aider.chat/ It indexes files in your repo, but you can control which specific files to include when prompting and keep it very limited/controlled.

Congrats on the launch! As someone who is ignorant and not following all of the recent releases. Isn't Claude-code a proprietary version of https://aider.chat/ in the first place?

I really don't like the snarky tone of the parent comment. Nonetheless, I don't think this is even something that can easily be benchmarked. I'd recommend you take a look at aider [1], and consider how I drew similarities between it and what's presented here. Has ClosedAI presented any benchmarks / evaluation protocols? [1] https://aider.chat/

Anyone got a "best practises" or even a few "my workflow" blog posts on how to best use LLM's with a local code base? Just saw someone recommend: https://aider.chat/ Thought there might be more worth exploring from this community. ;-)

I love using https://aider.chat/ When you say glue between the browser though not sure if you're looking for something to automatically watch your browser's behavior. For now you can just pass screenshots to aider through the clipboard

Aider is AI pair programming in your terminal. Aider lets you pair program with LLMs, to edit code in your local git repository. Start a new project or work with an existing git repo. Aider works best with GPT-4o & Claude 3.5 Sonnet and can connect to almost any LLM. https://aider.chat/ See LLM Leaderboards as well: https://aider.chat/docs/leaderboards/

You can do this with aider in any IDE: https://aider.chat/ I think the focus on speed is great, but I don't feel my IDE's speed has held me back in a decade.

Do you have an API that could be plugged into https://aider.chat/ ? It's by far the best way to use GPT4 for coding, in my experience, and more speed is exactly what it could use. But it needs an OpenAI compatible API.

Some hints for people stuck like this: Consider using Aider. It's a great tool and cheaper to use than Code. Look at Aiders LLM leaderboard to figure out which LLMs to use. Use its architect mode (although you can get quite fast without it - I personally haven't needed it). Work incrementally. I use at least 3 branches. My main one, a dev one and a debug one. I develop on dev. When I encounter a bug I switch to debug. The reason is it can produce a lot of code to fix a bug. It will write some code to fix it. That won't work. It will try again and write even more code. Repeat until fixed. But in the end I only needed a small subset of the new code. So you then revert all the changes and have it fix it again telling it the correct fix. Don't debug on your dev branch. Aider's auto committing is scary but really handy. Limit your context to 25k. Only add files that you think are necessary. Combining the two: Don't have large files. Add a Readme.md file. It will then update the file as it makes code changes. This can give you a glimpse of what it's trying to do and if it writes something problematic you know it's not properly understanding your goal. Accept that it is not you and will write code differently from you. Think of it as a moderately experienced coder who is modifying the codebase. It's not going to follow all your conventions. https://aider.chat/ https://aider.chat/docs/leaderboards/

I don't use it this way yet, but aider has a watch mode that would be fun with vim: https://aider.chat/docs/usage/watch.html I imagine with vim, from the document you're editing, you'd go: :ter to get a terminal. Fire up aider with --watch-files in the terminal. Hop back up to the file and start telling it what to do. Hit L when it's done to see the changes. That's just a guess but after writing it out I kinda want to try it. When I use aider it's via its chat interface and then I load the file with vim in another terminal tab to follow along but I think --watch-files with vim would be fun.

Aider [0] wrote a piece about this [1] way back in Oct 2023! I stumbled upon it in late 2023 when investigating ways to give OpenHands [2] better context dynamically. [0] https://aider.chat/ [1] https://aider.chat/2023/10/22/repomap.html [2] https://openhands.dev/

You can also switch between models with aider https://aider.chat/

https://aider.chat/docs/leaderboards/ I think this is my most favourite benchmark that fits me best. Stuff I can run at home is down the list alot, but that's fine with me.

Aider and Goose are also open source. Goose is backed by a big company, but Aider isn't and was one of the first (that I know of at least). https://aider.chat/ https://block.github.io/goose/

I think Auto-GPT or a similar project did something like this in 2023. Aider has an option where you can combine different models, so one does the thinking and one implements the changes. https://aider.chat/docs/leaderboards/ e.g. o3 (high) + 4.1 There used to be more such combinations in this list but it seems they were removed. A while ago I think the best thing on the list was such a hybrid.

Aider is in large part written by AIs, they even have some stats here: https://aider.chat/HISTORY.html Besides that, I think your best bet is to find someone on youtube creating something "live" using a LLM. Something like this: https://www.youtube.com/watch?v=NW6PhVdq9R8

Could really use a comparison versus the seemingly de-facto terminal AI coding tool Aider. https://aider.chat/

Qwen3 family (and the R1 qwen3-8b distill) is #1 in programming and reasoning. However it's heavily censored on political topics because of its Chinese origin. For world knowledge, I'd recommend Gemma3. This post will be outdated in a month. Check https://livebench.ai and https://aider.chat/docs/leaderboards/ for up to date benchmarks

i think you are missing the elephant in the room: ai what skills do you having using https://www.anthropic.com/claude-code https://aider.chat/ etc? that's the cli to master

Vibe-wise, it seems like progress is slowing down and recent models aren't substantially better than their predecessors. But it would be interesting to take a well-trusted benchmark and plot max_performance_until_date(foreach month). (Too bad aider changed recently and there aren't many older models; https://aider.chat/docs/leaderboards/by-release-date.html has not been updated in a while with newer stuff, and the new benchmark doesn't have the classic models such as 3.5, 3.5 turbo, 4, claude 3 opus)

We looked into many different diff/merge strategies[0] before finding Relace. Their apply model was a simple drop-in that reduced the latency of our UX substantially, while keeping error rates low. Great work Preston and Eitan! [0] https://aider.chat/docs/more/edit-formats.html

Try https://aider.chat + OpenRouter.ai, pay-as-you-go, use any model you want, I use Claude Sonnet. It has a very good system prompt so the code is pretty good without a lot of fluff.

Aider has a configuration for each supported LLM to define the best diff format for each; so for certain ones they're best at diff format, Gemini is best at a fenced-diff format, Qwen3 is best at whole file editing, etc. Aider itself examines the diff and re-runs the request when the request when the response doesn't adhere to the corresponding diff format. Edit: Also the Aider leaderboards show the success rate for diff adherence separately, it's quite useful [1] 1 - https://aider.chat/docs/leaderboards/

Have you tried Aider? They're making a CLI coding agent for quite some time and have gained quite a bit of traction. [0] https://aider.chat/

I've ended up using aider with pycharm, it's not as feature rich as cursor but works great for me https://aider.chat/docs/usage/watch.html

This is the closest I've found that's akin to Claude Code: https://aider.chat/

I don't understand the appeal of investing in leaning and adapting your workflow to use an AI tool that is so tightly coupled to a single LLM provider, when there are other great AI tools available that are not locked to a single LLM provider. I would guess aider is the closest thing to claude code, but you can use pretty much any LLM. The LLM field is moving so fast that what is the leading frontier model today, may not be the same tomorrow. Pricing is another important consideration. https://aider.chat/docs/leaderboards/

Maybe I am not understanding something here. But there are third party options availabe that to the very same thing (e.g. https://aider.chat/ ) which allow you to plug in a model (or even a combination thereof e.g. deepseek as architect and claude as code writer) of your choice. Therefore the advantage of the model provider providing such a thing doesn't matter, no?

"gemini 2.5 pro exp" is superior to Claude Sonnet 3.7 when I use it with Aider [1]. And it is free (with some high limit). [1]https://aider.chat/