I found Ruby LLM to be surprisingly good - in terms of usability it's close to Vercel's AI framework.
It tries to strike a balance between working out of the box and being flexible... which has its challenges, still nice overall.
One big real-life pain I experienced is that caches don't always work, e.g. for xAI, since it only supports completions API and thought signatures are returned wrong.
We use and love RubyLLM! A wonderful and easy to use framework.
Agreed with another commenter on the frustration with the responses API not being naively supported; that seems like a huge miss. There is a connector from another dev, but it's buggy and not as high quality as the main gem.
Really looking forward to future development and especially 2.0!
Edit: Just saw that responses API is now native? I will definitely check that out.
Since a few mentioned Responses API: the reason why it wasn't implemented in 1.x is because RubyLLM 1.x effectively assumes a 1:1 mapping between provider and protocol. That assumption no longer holds since OpenAI has 2 protocols with different capabilities, and to access all VertexAI models we need to support a bunch under that single provider.
Therefore, a major refactoring to split Protocols and from Providers was needed, as well as a way to route different models to different Protocols under the same Provider, transparently.
That's one of the many things that's gonna ship with RubyLLM 2.0.
RubyLLM is very easy to use. Made extensive use of it for a project last year. Drawbacks are it was difficult to instrument for true trace observability and it has a pattern where retries will delete the underlying models so the history you see is clean but not necessarily great for seeing exactly what the sequence of API calls was.
I'm building something that is only pointed at Claude, and I don't anticipate moving away from the Anthropic ecosystem. Does RubyLLM offer me an advantage over directly using Anthropic's Ruby SDK?
To put it differently, is this more like choosing between Fog and aws-sdk-s3, or choosing between Active Storage and aws-sdk-s3?
Some of the things I like about RubyLLM:
1. the DSL - You can chain methods like ActiveRecord.
2. the Structure - If gives a way to organize agents, tools & prompts
3. the Portability - The costs of AI usage, will one day be an issue for any successful product. Being able to easily test and move from Anthropic to DeepSeek cut my bill down by over 90%. Knowing how easy RubyLLM makes it, ignoring this eventuality feels reckless to me.
4. ActiveRecord Integration - With a simple `bin/rails generate ruby_llm:install
`, you can save each chat to your database.
5. Agent Training - This is a side benefit of the above, but has been a huge unlock for me. Since I have all my chats saved, I will regularly pull down that history and give it to claude code to refine my agent instructions.
Why build it in such a way that there you're locked into one provider when you can just use this tool and have the ability to choose any provider in the future? I mean, even for fallbacks, like what if anthropic API is down that particular day when you need the service?
Not the commenter, but the reason is the same as the choice to use direct db driver vs ORM - you get to take full advantage of special features and intricacies of one system, rather than trying to maintain a lowest common denominator of functionality between multiple ones.
You can always build multiple clients however. It could be one thorough integration with one API, and a simpler backup via RubyLLM.
Unless of course RubyLLM supports all of the above, but even then, are they going to be able to keep up as much as a native client in the long term?
The answer is almost always that a native client for a more critical integration is the right call. You can always add another if you need it.
RubyLLM is awesome! I use it on side projects. So interesting how questions and comments from last year SF Ruby conf, https://youtu.be/y535u1EWqAg?si=rbyv52T035apKwQk are already features shipped in the ecosystem.
I spent a lot of time with RubyLLM a few months ago. Very nicely designed and implemented. I have my own LLM clients written in various Lisp languages and I thought about appropriating some of the design of RubyLLM. Imitation is flattery.
We use RubyLLM in production too, the most elegant library in this space I've seen so far.
I also liked how they run the issue tracker. If you select "Feature Request", it makes you explain how you explored workarounds, why you believe it belongs in RubyLLM etc to prevent scope creep.
> Error: You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. * Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 20, model: gemini-2.5-flash Please retry in 41.543129369s.
I have used a personal Gemini token for all users, which often exceeds quota. You can:
1. Check out the repo and use your own tokens
2. Use your own tokens in the browser, they are only held in the browser and are not being persisted or logged in the backend
It is quite nice, but not as nice as you'd want. You still have to set platform specifics when running completions when you want to tune things like temperature, effort, max tokens, etc.
Hi! Valid challenge, I am probably misremembering. We were playing with various 'one-interface to all providers' solutions and I might have mixed up RubyLLM there. Sorry for that.
I will have a deep dive into which things I felt we needed to adapt per provider.
I didn't mean to imply that you have to solve all of our wants of course.
One thing we did do was monkey-patch the spot where tool_calls are performed by RubyLLM. We had our own mechanism for that and were able to skip RubyLLM's and still extract the tool calls and run them through our own tool harness. That all worked beautifully. I don't know if that type of stuff is something you want PRs on or that you want to keep steering towards the route that does everything within RubyLLM classes. Happy to contribute some of that.
We had already implemented tool_calls in our own database and have a system that executes them and creates our conversation array, etc. So we wanted to leverage the providers that RubyLLM supports without having to change the tool execution in our platform.
FWIW, I don't think the GP post is disparaging (at least as I read it right now.)
I think it is fair to list limitations from using a library that provides an abstraction; it can suggest why a tool isn't right for a person's use cases.
But it also sounds like this API handles those pretty well.
I have been a fan of Ruby for many years, but in this fast paced era the Ruby ecosystem always struggled with the dependency versioning. Gems I relied on were never available or compatible with the rest of the ecosystem.
Why would anyone still build in dynamically typed languages in 2026? Why relinquish the crystal clear signals that static typing is able to provide to the LLM?
You static typed evangelists have lost your damn minds. You seem to have completely misunderstood what this library even is because you have some primal urge to boast static typing at every chance.
You can build high quality software with dynamically typed languages, and Ruby is an absolute dream to read and write.
I was on team dynamic typing for about 12 years, and Ruby was a big part of that. I still think dynamic languages can be wonderful to read and write.
But after using modern statically typed languages with good inference, I changed my mind. Many of my old objections were really objections to verbose type systems, not static typing itself. With inference, you can keep a lot of the readability while gaining safer refactoring, better tooling, and earlier feedback.
That doesn’t mean dynamic languages can’t produce high-quality software. They obviously can. But I don’t think appreciating modern static typing is just evangelism.
And yes, I understand what this library is about, it's for "beautiful" easy to use interface to AI providers for Ruby apps. It's the popular play nowadays with litellm, bifrost, gomodel and vercel gateway. We have at least couple AI gateways, libraries like that every week on HN.
I didn't misunderstand what this library is about. I assume the authors are using LLM's to help author their code in general, even meta-frameworks like this.
Static typed languages had been around a long time before Python, JS and Ruby gained popularity. All three of the latter now support some form of type hints.
Why did people switch to these languages in the first place and what's driving the current back-to-typed-languages trend?
Even as rails dev, I am seeing that you might be right. It’s really hard to find specific pros nowadays that Ruby brings to the table. All that talk about conventions over configurations and vast presence of Rails in weights is fun, but if writing speed isn’t an issue anymore, then Ruby on Rails has serious problems with larger codebases
they introduced static typing (Sorbet) to avoid problems, it's completely different app and looks nowhere close to what you experience in standard Rails app
No, it's just a tool someone posted that's written in Ruby, with a strong signal that the authors are LLM proponents. It could have been a todo list and I'd still have the same question.
It tries to strike a balance between working out of the box and being flexible... which has its challenges, still nice overall.
One big real-life pain I experienced is that caches don't always work, e.g. for xAI, since it only supports completions API and thought signatures are returned wrong.
Responses API is now implemented and it's coming in RubyLLM 2.0
https://github.com/crmne/ruby_llm/blob/main/lib/ruby_llm/pro...
Agreed with another commenter on the frustration with the responses API not being naively supported; that seems like a huge miss. There is a connector from another dev, but it's buggy and not as high quality as the main gem.
Really looking forward to future development and especially 2.0!
Edit: Just saw that responses API is now native? I will definitely check that out.
Since a few mentioned Responses API: the reason why it wasn't implemented in 1.x is because RubyLLM 1.x effectively assumes a 1:1 mapping between provider and protocol. That assumption no longer holds since OpenAI has 2 protocols with different capabilities, and to access all VertexAI models we need to support a bunch under that single provider.
Therefore, a major refactoring to split Protocols and from Providers was needed, as well as a way to route different models to different Protocols under the same Provider, transparently.
That's one of the many things that's gonna ship with RubyLLM 2.0.
If you're curious: https://github.com/crmne/ruby_llm/commit/d398354da493570b050... https://github.com/crmne/ruby_llm/commit/0875ce2dfeae9d28a3a...
Rails-style instrumentation landed in 1.16.0.
https://rubyllm.com/instrumentation/
To put it differently, is this more like choosing between Fog and aws-sdk-s3, or choosing between Active Storage and aws-sdk-s3?
Some of the things I like about RubyLLM: 1. the DSL - You can chain methods like ActiveRecord. 2. the Structure - If gives a way to organize agents, tools & prompts 3. the Portability - The costs of AI usage, will one day be an issue for any successful product. Being able to easily test and move from Anthropic to DeepSeek cut my bill down by over 90%. Knowing how easy RubyLLM makes it, ignoring this eventuality feels reckless to me. 4. ActiveRecord Integration - With a simple `bin/rails generate ruby_llm:install `, you can save each chat to your database. 5. Agent Training - This is a side benefit of the above, but has been a huge unlock for me. Since I have all my chats saved, I will regularly pull down that history and give it to claude code to refine my agent instructions.
You can always build multiple clients however. It could be one thorough integration with one API, and a simpler backup via RubyLLM.
Unless of course RubyLLM supports all of the above, but even then, are they going to be able to keep up as much as a native client in the long term?
The answer is almost always that a native client for a more critical integration is the right call. You can always add another if you need it.
I love how MINASWAN Hacker News is when talking about Ruby!
I also liked how they run the issue tracker. If you select "Feature Request", it makes you explain how you explored workarounds, why you believe it belongs in RubyLLM etc to prevent scope creep.
https://github.com/tweibley/legate
> Error: You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. * Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 20, model: gemini-2.5-flash Please retry in 41.543129369s.
I'm not sure where you got that.
`chat.with_temperature(0.2)`
https://rubyllm.com/chat/#controlling-response-behavior
`chat.with_thinking(effort: :high, budget: 8000)`
https://rubyllm.com/thinking/#controlling-extended-thinking
Max tokens is the only one of your list that require provider specific params:
https://rubyllm.com/chat/#provider-specific-parameters
I'm one guy doing it for free. Happy to see your contribution!
I will have a deep dive into which things I felt we needed to adapt per provider.
I didn't mean to imply that you have to solve all of our wants of course.
One thing we did do was monkey-patch the spot where tool_calls are performed by RubyLLM. We had our own mechanism for that and were able to skip RubyLLM's and still extract the tool calls and run them through our own tool harness. That all worked beautifully. I don't know if that type of stuff is something you want PRs on or that you want to keep steering towards the route that does everything within RubyLLM classes. Happy to contribute some of that.
You work your arse off for free and the guy who made the disparaging comment didn't even bother to research to see if he had the details right.
Hat's off to you Carmine for all your work. Many people really do appreciate it.
I think it is fair to list limitations from using a library that provides an abstraction; it can suggest why a tool isn't right for a person's use cases.
But it also sounds like this API handles those pretty well.
You can build high quality software with dynamically typed languages, and Ruby is an absolute dream to read and write.
I was on team dynamic typing for about 12 years, and Ruby was a big part of that. I still think dynamic languages can be wonderful to read and write.
But after using modern statically typed languages with good inference, I changed my mind. Many of my old objections were really objections to verbose type systems, not static typing itself. With inference, you can keep a lot of the readability while gaining safer refactoring, better tooling, and earlier feedback.
That doesn’t mean dynamic languages can’t produce high-quality software. They obviously can. But I don’t think appreciating modern static typing is just evangelism.
And yes, I understand what this library is about, it's for "beautiful" easy to use interface to AI providers for Ruby apps. It's the popular play nowadays with litellm, bifrost, gomodel and vercel gateway. We have at least couple AI gateways, libraries like that every week on HN.
Why did people switch to these languages in the first place and what's driving the current back-to-typed-languages trend?