Hacker Newsnew | past | comments | ask | show | jobs | submit | usecodenaija's commentslogin

While Firefox's tab groups are a great addition, it's intriguing to consider whether relying on traditional tab groups is keeping us from embracing more innovative solutions like BrowserGPT by CivAI.

BrowserGPT not only manages tasks but does so with voice commands, offering a forward-thinking approach to browsing automation. Are we holding onto old habits at the expense of exploring groundbreaking technology?


So, OpenAI’s Codex CLI is Claude Code, but worse?

Cursor-Agent-Tools > Claude Code > Codex CLI

https://pypi.org/project/cursor-agent-tools/


Astroturfing alert. This comment author is also the author of cursor-agent-tools.


Never heared of Cursor Agent tools. And that is better than Claude Caude according to whom? Genuinely curious.


Are you living in a cave?

anyways, here you go:

Cursor Agent Tools is a Python-based AI agent that replicates Cursor's coding assistant capabilities, enabling function calling, code generation, and intelligent coding assistance with Claude, OpenAI, and locally hosted Ollama models.

https://github.com/civai-technologies/cursor-agent


I've been quite unimpressed by Codex for now... even the quality of the code is worse than Claude for me


This tool has nothing to do with Cursor.

Very misleading to use popular brand like that, possible scam.


Maybe read the docs before replying:

Cursor Agent Tools is a Python-based AI agent that replicates Cursor's coding assistant capabilities, enabling function calling, code generation, and intelligent coding assistance with Claude, OpenAI, and locally hosted Ollama models.

https://github.com/civai-technologies/cursor-agent


Being inspired by someone's work DOES NOT give you right to use their trade mark.

It's like making a new operating system and calling it Windows because you "replicate" capabilities of MS Windows. Please read about trademark law.


Standardizing agentic AI prematurely could stifle innovation and diverse approaches.

Unlike networking protocols, AI agency may benefit more from competing frameworks that explore different philosophical and technical foundations before converging on standards.


Makes sense. Current networking standards ultimately emerge from ARPA, a single actor - this was a single vendor solution being adopted. AI agent field has many more actors, the situation resembles browser wars or even something more loose common-approach-wise.


"Show HN is for something you've made that other people can play with. HN users can try it out, give you feedback, and ask questions in the thread."

this post and other one falls under this requirement

I made a Jarvis-like program with llms and i gave a how-to guide on setting it up yourself, the post includes a GitHub link to download the files and set it up


It's a tutorial, the fact it contains some code doesn't change this - many tutorials do. The other link is a signup page. These aren't valid Show HNs.


what price are you willing to pay for this service?


I'm going to be brutal here. Take it as you want.

1. The nascent AI startup world is under the illusion that there is an inexhaustible supply of subscription payers who will all pay $5 - $20 a month for what are effectively low barrier AI features. Note, not full applications, just features.

2. Most of these features are 'interesting' at best. Almost none of them are compelling enough to attract subscribers faced with multiple choices for their money.

3. Top of the tree for subs are mission critical AI applications which are mandatory for work. Design tools like Adobe Firefly spring to mind as an example. Bottom of the tree are 'nice to have' feature utilities, which don't really add huge amounts of value to daily lives. Examples could be browser assistants, or AI search tools, or AI holiday finders etc etc et.

4. 99% of these startups will fail.

5. The only realistic and faint possibility for success in this brutal current climate is to release either a) on a credit per use basis (probably with a freemium up front for testing or b) to release on a freemium to gain traction with premium tiers once the application value has been proven in action.

This is all, or course, in my limited expertise opinion.


- i'd argue that a tool like this could become indispensable by enhancing the productivity of internet users who spend significant amounts of time completing online tasks (remote workers), and browsing for information, such as researchers, journalists, or academics

- the tool has the potential to act as a single point of interaction that enhances other online tools and services

- and it's pretty cool and convenient having your own "Jarvis" on the browser

- Regarding monetization, adopting a hybrid model could indeed be beneficial. Starting with a freemium model to build user trust and demonstrate value, followed by premium features for power users, could be a strategic approach

I'll look into giving out free licenses in my next post

btw love the feedback, much appreciated


Thanks. I admire anyone who starts up something in this business climate. :)

Your comments make sense. :) I think you're going to be fighting against free or almost free alternatives such as OpenAI models API pennies per search etc etc. Also there are a number of browser plugins like Kagi.com (freemium) which already offer some AI functionality alongside other features.

The only way you'll win is to convince prospective buyers with compelling use cases, and you'll only find that through users who give feedback. Another reason for some sort of trial period or freemium option?

Anyway good luck. I wish you well in your quest.


Thanks alot!


it only works on chrome for now


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: