-
vscode-dotnettools
This is a feedback repository to capture issues logged for the C# Dev Kit and related extensions from Visual Studio Code
Exactly. From: [0]
> I know it works as intended. Just curios why Microsoft decided to enforce this all of a sudden.
> Did GitHub Copilot just give up on playing fair with Cursor, admitting it's winning?
The game wasn't 'fair' to begin with and it was rigged for Microsoft to win anyway. (Cursor being based on VS Code).
If you're competing against Microsoft, expect them to race you to zero for years and at close to no cost for them.
It is all for Cursor to lose if they continue as they are.
[0] https://github.com/microsoft/vscode-dotnettools/issues/1909#...
-
Stream
Stream - Scalable APIs for Chat, Feeds, Moderation, & Video. Stream helps developers build engaging apps that scale to millions with performant and flexible Chat, Feeds, Moderation, and Video APIs and SDKs powered by a global edge network and enterprise-grade infrastructure.
-
kilocode
Open Source AI coding assistant for planning, building, and fixing code. We're a superset of Roo, Cline, and our own features. Follow us: kilocode.ai/social
I learned about your project from your comment on the Windsurf post but wanted to suggest that you plug your URL anytime you plug the project since it can make the difference between someone "adding it to their eventual list" versus "open in new tab, read, enjoy, engage"
https://github.com/Kilo-Org/kilocode#-kilo-code (Apache 2)
-
If you're using Cursor, but find it tends to struggle once your project reaches a certain size, and you're ok with something CLI-based, you might find the open source CLI coding agent I've built interesting: https://github.com/plandex-ai/plandex
- It can handle up to 2M tokens of context directly, and can index/work with/chat with projects up to 20M tokens (1M+ lines). Here's an example of chatting with with SQLite codebase to learn about how transactions are implemented: https://plandex.ai/_next/static/media/plandex-sqlite.0ee6cb2...
- All changes are committed to a version-controlled sandbox by default, preventing the problem of stray changes that you don't notice being left behind in the project.
- Being terminal-based allows for more seamless and powerful execution control and automated debugging. Here's an example of automatically debugging a browser app: https://www.youtube.com/watch?v=g-_76U_nK0Y&embeds_referring...
-
llmehelp
Discontinued Experimental workflows in AI technical assistance [Moved to: https://github.com/day50-dev/llmehelp] (by kristopolous)
the proper timeline is
cline -> roo -> kilo
There's also things like goose, plandex, and aider.
The real problem is what to do after all those bugs are written by the AI.
That's what my latest effort, https://github.com/kristopolous/llmehelp is trying to address.
-
There is a way to proxy it to other models: https://github.com/1rgs/claude-code-proxy
-
> That's not working in any IDE is it? The crux of the matter is the level of integration, with Cursor (and others) I can apply the suggestions via autocomplete and see git diffs with agent code.
Would a simple VSCode plugin for Aider not be able to do that? I haven't tried it out, but Aidermacs (https://github.com/MatthewZMD/aidermacs) is an Emacs plugin that supposedly mimics some of Cursor's feature - but by using Aider.
I'm not saying Cursor is bad or anything. It may well be as good as Aider or a bit better. But it's not vastly better. If you had $1M to spare, would you risk investing in Cursor?
Related posts
-
Beyond the Hype: A Look at 5+ AI Coding Agents for Your Terminal
-
Ask HN: AI tools to help you learn (GitHub, books, PDFs)
-
Show HN: Plandex v2 – open-source AI coding agent for large projects and tasks
-
Show HN: Plandex v2 – AI coding agent with diff sandbox, full auto, 2M context
-
Diagrams AI can, and cannot, generate