It feels crazy to me that we are building "tool search" instead of building real tool with interface, state and available actions. Think how would you define a Calculator, a Browser, a Car...?

I think, notably, one of the errors has been to name functions calls "tools"...

well the name “function” is already taken - they deprecated it so that we could call functions, tools.

Well, I think they should have kept calling it function... ^^'

Nice but sad to see lack of tools. Most your code is about the agent framework instead of specific to SWE.

I've built a SWE agent too (for fun), check it out => https://github.com/myriade-ai/autocode

> sad to see lack of tools.

Lack of tools in mini-swe-agent is a feature. You can run it with any LLM no matter how big or small.

I'm trying to understand what does it got to do with LLM size? Imho, right tools allow small models to perform better than undirected tool like bash to do everything. But I understand that this code is to show people how function calling is just a template for LLM.

Mini swe agent, as an academic tool, can be easily tested aimed to show the power of a simple idea against any LLM. You can go and test it with different LLMs. Tool calls didn't work fine with smaller LLM sizes usually. I don't see many viable alternatives less than 7GB, beyond Qwen3 4B for tool calling.

> right tools allow small models to perform better than undirected tool like bash to do everything.

Interesting enough the newer mini swe agent was refutation of this hypothesis for very large LLMs from the original swe agent paper (https://arxiv.org/pdf/2405.15793) assuming that specialized tools work better.

Thanks for your answer.

I guess that it's only a matter of finetuning.

LLM have lots of experience with bash so I get they figure out how to work with it. They don't have experience with custom tools you provide it.

And also, LLM "tools" as we know it need better design (to show states, dynamic actions).

Given both, AI with the right tools will outperform AI with generic and uncontrolled tool.

Why do humans need a IDE when we could do anything in a shell? Interface give you the informations you need at a given moment and the actions you can take.

To me a better analogy would be: if you're a household of 2 who own 3 reliable cars, why would you need a 4th car with smaller cargo & passenger capacities, higher fuel consumption, worse off-road performance and lower top speed?

Here, the best time is defined as the highest chance of getting "some" visibility. Most posts quickly fade away.

You are right that there is lots of way to measure this but quality comments is way harder to judge and we don't have quantity traffic info.

Hey, Funnily, I had this idea/need recently. Just a message to encourage you in this direction !

Selfless plug, our own tool => https://www.myriade.ai

> I wish you luck in refining your differentiation. Can't agree more with you. It's about distribution (which Snowflake/Databricks/... have) or differentiation.

Still, chatting with your data is already working and useful for lots.

My 2 cents, building a tool in this space...

> Do you need an expert to verify if the answer from AI is correct?

If the underling data has a quality issue that is not obvious to a human, the AI will miss it too. Otherwise, the AI will correct it for you. But I would argue that it's highly probable that your expert would have missed it too... So, no, it's not a silver bullet yet, and the AI model often lacks enough context that humans have, and the capacity to take a step back.

> How is it time saved refining prompts instead of SQL?

I wouldn't call that "prompting". It's just a chat. I'm at least ~10x faster (for reasonable complex & interesting queries).

Awesome. Using Vue/Tailwind, I'm definitely interested in this. Maybe you could try to add examples of integrations with others frameworks? I'll play with it and give you my 2 cents.

Not sure if you're aware, but there's a well-supported Vue ShadCN library: https://www.shadcn-vue.com/

Yeah, it's excellent.

Hello there Ben. Sure thing, I'll try and expand the docs.

Hi HN,

Over the past few weeks/months, I’ve been working on Autochat, a lightweight Python library designed to make building AI agents simple and intuitive.

The focus of Autochat is simplicity:

- Extend an AI assistant's functionality by adding Python functions directly, or even class.

- Hide all the complexities/particularities of the providers (openai, anthropic, …)

I’d love your feedback on this. If you’ve got ideas for features, use cases, or critiques, let me know!

Seems weird that to me that it make a front page on HN (from an European pov ; it's quite common)

It's a fairly large cyberattack, so it's halfway interesting to HN readers.