[BudaDude]

I love Cursor, but it feels like a ticking time bomb with extensions not being updated at the same rate as VSCode.

Also another issue I am starting to see is the lack of shared MCP servers. If I have VSCode, Cursor, and Claude open, each one is running its own instance of the MCP server. You can imagine that with a dozen or so MCP's, the memory footprint becomes quite large for no reason.

[nojs]

It’s more of a ticking time bomb because it relies so heavily on upstream model providers who all have competing products, particularly Claude Code.

[ramoz]

I think about this daily. More devs are starting to pick up on Claude Code. The initial “not an IDE!” scare is usually diminished within the initial session.

I don’t think the future of agentic software development is in an IDE. Claude Code gives me power to orchestrate - the UX has nothing to do with terminal; it just turns out an agent that lives on the OS and in the filesystem is a powerful thing.

Anthropic can and will evolve Claude Code at a pace cursor cannot evolve IDE abstractions. And then yea - they are designing the perfect wrapper because they are also designing the model.

Long bet is Claude Code becomes more of an OS.

[steveklabnik]

You might find this post interesting: https://steipete.me/posts/2025/claude-code-is-my-computer

It… sure is something. I’m still thinking about if it’s horrible, visionary, or both.

[Hyperboreanal]

Note: the text of that article itself is AI generated.

> Automate Content: Like this very post. I use Wispr Flow to talk with Claude, explain the topic and tell it to read my past blog posts to write in my style.

[JimDabell]

Now I have the mental image of the owner of that blog tearing his hair out trying to get back into his computer, while the AI that locked him out is happily posting on his blog trying to convince other gullible humans to hand over control of their computers.

[steveklabnik]

Yes, the author (apparently) spent a lot of time with it.

[ramoz]

Wow yea, definitely resonates thanks for sharing.

This is why I think the future may be less about “agents” and more about “intelligent infrastructure”

I don’t want to chat. I want to point a wand and make things happen.

[dimal]

How are people using Claude Code day to day without spending a lot? I tried it on a moderately complex task and it chewed through tokens at an alarming rate. I quickly spent $2 and hadn’t even arrived at an adequate solution yet. I’ve heard other people say they’ve spent $10-20 in a coding session. I don’t see how that’s sustainable for me, so I’ve stuck with my $20/month Cursor subscription.

[brandall10]

They use a plan - Pro and Max are static plans with different caps over 5 hour sessions.

[saratogacx]

Pro isn't a static plan. Pro subs can access Claude Code but are paying via API metering. I have it setup at home and, while I haven't used it much, it can quickly add up.

What I did do, because my personal projects aren't too complex, is moved the model from Opus to Sonnet which is about 1/5 the cost.

For day-to-day stuff I have ProxyAI (on IntelliJ, continue.dev works for this too) pointed at Mistral's Codestra for auto-complete and to Claude 4 for chat.

Claude Code is just for giving the bot tasks to do without me being deeply involved in the work.

(edit) I just saw that pro is getting a rate-limited option for Claude code for the sonnet model only. I haven't tried it out but will give it a go sometime. https://support.anthropic.com/en/articles/11145838-using-cla...

[brandall10]

Pro is indeed a static CC plan as of yesterday. It won't automatically switch over, you have to re-login inside of Claude Code.

[xandrius]

Normally to make a new smallish feature it costs me about $0.40.

The core suggestion is to point specifically at the files you want it to read and use as a reference, otherwise it might go read some huge file for no reason. Also the tokens used depend on the size of the project.

Generally, if I'm doing something I can box, I'd use chatgpt and copy it in myself. If I want something matching the style, I'd use a guided Roo Code.

[Aeolun]

Until Claude Code becomes manageable price wise, I don’t think Cursor really sees them as their competition. I can burn the whole cursor subscription price in a single day with Claude Code.

[nextos]

I've found Emacs plus gptel very pleasant to use. And following the ethos of Emacs, it is backend agnostic and very malleable.

Besides, if you want something inexpensive, using Gemini 2.0 Flash as a backend is completely free. Google provides an API key at no cost.

[fhd2]

Ha, same. How do you use it? I tried all the fancy context management stuff multiple times, but I mostly just have a chat buffer open and copy paste stuff manually. Text wrangling is so damn efficient in Emacs. I pay around 10$ to Anthropic per month in API tokens for pretty heavy usage. With deliberate context management (I found keeping it small and focused vastly improves responses), cost is really not an issue.

Didn't try anything agentic within Emacs yet, don't find that helpful enough so far.

[karthink]

> tried all the fancy context management stuff multiple times, but I mostly just have a chat buffer open and copy paste stuff manually.

As of last week you can insert a link to a plain-text file in a chat buffer to include its contents in the prompt. It must be on a line by itself. In Markdown it looks

[like this](/path/to/file)

with Org links in Org chat buffers.

This feature is disabled by default to minimize confusion. To enable it you can flip the header line button that says "ignoring media" to "sending media". This works for sending images and other media too, if the model supports it.

[fhd2]

Nice! I love how practical gptel is :D

[nextos]

> How do you use it?

I have a global bind for gptel-send (C-c g).

Then, in any buffer, I typically type C-u C-c g.

This lets me customize the prompt and lots of parameters, such as the context, before gptel-send is actually called.

[natrys]

I tried aidermacs yesterday, it's neat if you use the vterm backend. Does a few things more automatically.

[travbrack]

I'm surprised nobody is mentioning how cheap copilot pro is. $20 and you get all you can eat inference without using your own api key for the models on vs code agent mode.

[goosejuice]

Copilot pales in comparison to Cursor Pro. I've trialed it three or four times in the last two years and stopped using it after a few days each time. Honestly, I have no idea why anyone pays for it given the alternatives.

My only wish is that Cursor had partnered with Zed. vscode isn't enjoyable.

[johntash]

FWIW,you can log in to github copilot with Zed and it will use your copilot subscription instead of needing to pay for api calls.

[travbrack]

I'm sure it is but cursor plus API usage is out of reach for my hobbyist usage

[artdigital]

I’m on Pro+ and get rate limited heavily. 1-2 hours of semi heavy use and the brakes kick in. I can’t stay productive in it because this always rips me out

[Aeolun]

All copilot models feel lobotomized. It’s like they’re deliberately running them at low performance or something.

[mogili]

I use with the Max plan ($100 per mo) and its well worth the money and only hit the limit once so far.

[artdigital]

I’m now also on Max but had to upgrade to the 200 plan in about a week of daily rate limits

The $200 plan so far has been fine. Only had it once that it looked like I might hit the limit soon, but that was a very heavy refactoring task

[vunderba]

Yeah, if you're a heavy user of Claude code, you pretty much need to use it with a Max subscription rather than a BYOK approach. But that starts at $100 / month so it's a significant bump from cursor.

[unmole]

> need to use it with a Max subscription rather than a BYOK

Why is that?

[steveklabnik]

Max is far cheaper.

[coolKid721]

For any professional SWE 1/200 a month is basically nothing in terms of the value it delivers. They just rolled it out to the 20/month plan with limited usage but as soon as people get used to it I have no idea why they wouldn't upgrade unless they are just entering the field and don't have a job yet.

[goosejuice]

Anyone pulling that a month not working for themselves doesn't have to think about the cost. That kind of salary is paid by corps with strict privacy policies.

Unless you do nothing else with your time I'm not sure how you'd utilize the $100/mo plan fully.

[coolKid721]

the pricing is for token usage in 5/hr windows not monthly caps. if you use it intensely a couple times a month within a 5hr window it's not hard to hit the cap and want to upgrade. Personally I just work on some side projects during work on another monitor and just every half an hour so throw something at it and that's been very valuable for me.

[lelanthran]

> For any professional SWE 1/200 a month is basically nothing in terms of the value it delivers.

If it is delivering that value indeed, then 100-200 dollars each month is exactly what that professional SWE is worth.

That SWE is going to have to pivot into something adjacent to provide value-add, and if the only value-add is "I can review and approve/reject", then it's only a matter of time[1] that there are no SWEs who can review and then approve/reject.

And that is assuming that the LLM coding performance remains where it is now, and does not improve to the review, orchestration, design and planning levels.

-------------------------

[1] Due to attrition

[myth_drannon]

They just announced Claude Code will come with the pro subscription ($20)

[falcor84]

Interesting, but the limit is really low:

> Pro ($20/month): Average users can send approximately 45 messages with Claude every 5 hours, OR send approximately 10-40 prompts with Claude Code every 5 hours. [0]

I can probably run through that in 5 minutes.

[0] https://support.anthropic.com/en/articles/11145838-using-cla...

[ghiculescu]

I’ve been running on this plan all morning (Australia time). Amazing value.

[artursapek]

The $17 Claude pro sub has access to Claude Code now, at a fixed cost. Cursor also hits limits. I spent $350 on Cursor overage in like a week.

[insane_dreamer]

Claude Code now comes with the $20 Pro subscription plan.

[geekraver]

And models eat apps over time. If you build an app that’s valuable, OpenAI takes note.

[jlowin]

One of the first features we added to FastMCP 2.0 [1] was server composition and proxying (plus some niceties around trying to reuse servers whenever possible) for exactly this reason, so that you can ideally run a single instance of your preferred servers without replicating the setup over every application. In some ways, MCP standardized how agents talk to APIs but introduced a new frontier of lawless distribution! This is something that has to improve.

[1]: https://gofastmcp.com

[SkyPuncher]

I just run two IDEs.

Cursor is essentially only the wrapper for running agents. I still do my heavy lifting in Jetbrains products.

It actually works out well because I can let Cursor iterate on a task while I review/tweak code.

[brabel]

Have you tried the Jetbrains agent, I think it’s called Jennie? I am trying it right now and it seems decent enough but I haven’t tried Cursor as I don’t really like vs code.

[scopendo]

I tried previous iterations of JetBrain's AI without much love, but need to look at Junie.

Using Windsurf plugins in JB ides has been working for me, albeit not as powerful yet as the Windsurf VS Code fork.

[rpwverheij]

have you compared Windsurf (previously codeium, had to look it up) to Github Copilot agent or ChatGPT? I'm mostly still using ChatGPT's App integration. It can see my currently open files in webstorm and can directly suggest and apply changes from the app. And I find the suggestions better then JetBrain's AI integrations. But curious about Windsurf / CoPilot Agent

[okinok]

Jetbrains Junie is pretty good and comparable to Cursor in my experience. And since it is already included in my Jetbrains license, I have had no need for Cursor.

[SkyPuncher]

A bit.

Last time I tried, it didn't support RubyMine (whomp)

[etoxin]

Same here, everyday coding in Webstorm, Oh I have a task I can offload to copilot, I open VSCode and let a Github CoPilot Agent do that.

Knowing what tools are better for what really helps.

[rpwverheij]

have you tried the CoPilot agent tab in Github copilot chat in Webstorm? I wonder if/why you find using it through VSCode better in any way then using it directly in WebStorm.

[insane_dreamer]

I use the Claude Code plugin in PyCharm in the same way.

[tevlon]

That's why i use Docker MCP Catalog. One MCP Server to rule them all. more info: https://www.youtube.com/watch?v=6I2L4U7Xq6g

[greymalik]

Here’s an alternate link if you prefer to read text instead of watching a 6 minute video: https://docs.docker.com/ai/mcp-catalog-and-toolkit/catalog/

[tuananh]

I wrote my own tool for that too :D

https://github.com/tuananh/hyper-mcp

it's a MCP server with WASM plugin system, packaged, signed & published via OCI registry.

[xyc]

I recently discovered toolhive which is pretty handy too https://github.com/stacklok/toolhive

[manorek]

I don't understand. Is this meant to run locally? Because I tried to deploy my agent using GitHub MCP server to K8s. I can't ask my agent to run docker command in a pod.

[nsingh2]

Cursor and other VSCode forks connect to Open VSX [1] for extensions. Barring some of the Microsoft extensions, I've found that pretty much all the extensions I use are available and kept up to date on Open VSX. Cursor seems to have enough funding to support their own variants of the Microsoft extensions, like Python and C++.

The one issue I've run into is that the VSCode version Cursor uses is several months old, so we're stuck using older extensions until they update.

[1] https://open-vsx.org/

[artdigital]

You can change it back to use the normal Microsoft marketplace

[sroussey]

How?

[artdigital]

Add a `product.json` and set the extension gallery URL through that

``` { "extensionsGallery": { "serviceUrl": "https://marketplace.visualstudio.com/_apis/public/gallery", "itemUrl": "https://marketplace.visualstudio.com/items", "cacheUrl": "https://vscode.blob.core.windows.net/gallery/index", } } ```

https://github.com/getcursor/cursor/issues/2195

This is technically against the ToS of the extension gallery though

[MuffinFlavored]

> If I have VSCode, Cursor, and Claude open

This is good user feedback. If Cursor is "Claude + VSCode", why do you need the other 2 open?

[cmrx64]

for me, I’ll keep doing work on the codebase in a separate vscode while Cursor’s agent is wiling away at it, so as to not be distracted or interrupted by the agent activity in the corner of my screen. and then i’ll have a claude or aistudio tab open doing bigger analysis or planning tasks, reading papers together, etc.

[MuffinFlavored]

What would you say to somebody who doesn't trust Cursor to "take the reigns off" and go "agent mode" and do such large changes? Even with "checking/approving/having the final say" as a user, I feel there is time lost if the AI does not do the changes the right way/makes small pesky mistakes.

Autocomplete: yes

Asking questions: yes

I know everybody is all into agent mode and it isn't a Cursor specific thing, I'm just confused why everybody is into it.

[cmrx64]

I just accept that when I return to the Cursor window, it is going to have made some mistakes and I’m going to have to spend some time fixing things. I agree it’s a delicate balance, and sometimes it feels more like I’m exploring methods of steering the AI than I am doing anything about the code.

my usecases have been building relatively self-contained, well-specified components of distributed systems out of academic papers and my own design notes / prototype skeletons, in rust. there’s a lot of context for the agent to ground against, and it can blow out ideas into their implications relatively well ime.

the experience of fixing up lots of pesky mistakes that you yourself would never make is kinda annoying.

[tuananh]

Just use other transport like streamable http.

i wrote a MCP with plugin system where you only need to run 1 instance and add plugins via config file.

https://github.com/tuananh/hyper-mcp

[TranquilMarmot]

What are you using MCP for?

We recently launched Zapier MCP, we host the servers for you: https://zapier.com/mcp

[mmasu]

why would you open 3 IDEs all at once :-)

[elAhmo]

TIL that it doesn't have the same extensions as VSCode. I thought they share the same directory.

[hn_throw2025]

This is only effectively a problem for a handful of MS vendored extensions.

[TechDebtDevin]

Just run it on http

[vFunct]

this is the way.

STDIO MCP is really just a quick hack.