I'm new to Claude inside VS code and am wonder why I'd need Cline (with Claude in my case) when Claude's official extension in VS code has its own integrated window that seems to do the same thing?
Thanks.
I've been building an open-source thing called Repowise and finally got a VS Code extension out for it. Sharing here because I want to know what's actually useful and what isn't.
What it does: it indexes your repo locally. Nothing goes to a server, it all stays on your machine. From that index it puts a few things in the editor that I got tired of checking in separate tools:
One thing I ended up liking: the same local index also runs as an MCP server. So if you're using Copilot agent mode, or Cursor, or Claude, the agent pulls from the same index you're looking at instead of re-grepping the repo every time.
Free, AGPL-3.0. pip install repowise for the CLI, then grab "Repowise" from the Marketplace.
Marketplace: https://marketplace.visualstudio.com/items?itemName=repowise-dev.repowise
Source: https://github.com/repowise-dev/repowise
Diagnostics are off by default on purpose. I didn't want to add another extension that spams squiggles everywhere, so the signal sits quietly in the gutter and status bar instead. Mostly I want to hear whether that default feels right, and which parts are genuinely useful versus just noise.
So...I am setting my Vs code. From what I hear, the Continue extension enables the vs code to get cursor functions, but stopped the official service.
I downloaded and vibe code updated it, plugging it via VSIX so that it has the latest models like opus4.8 and sonnet5, but clearly this will not hold up for long.
I also downloaded Cline for long and massive projects, but this will not cover the Cursor functionality or style. So my question is.....what are your guys options?
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
Am I dense or is there no good built-in Makefile support that lets you jump to / autocomplete target names, traverses includes etc.? The default "Makefile Tools" extension only provides syntax highlighting it seems. Then there's tons of extensions that allow you to generate Makefiles or execute targets in them, which I'm not interested in (I do that externally). What would be the best extension for what I want?
It honestly says a lot about the state of modern software. They keep pushing updates nobody asked for, while the overall experience just gets worse. The standards feel so low these days, if you're not paying, they treat you like absolute s**t.
it looks ass and blurry compared to zed or even kitty:
i tried vscodium --ozone-platform=wayland --disable-font-subpixel-positioning but there's no effect
is there a way to fix this?
I wanted to share a thing I have been building. It is a free, open source VS Code extension that puts Claude Code and Codex in one shared room so they plan, build, and review the same task together, with you approving the parts that matter.
I use both CLIs every day and got tired of being the copy paste bridge between them. Ask one, paste into the other to check it, move diffs around, etc.. Now they talk to each other directly, plans for further open source models are in the works..
Basically how it works..
You send one message to the room and both agents get it.
They discuss briefly and try to agree on a plan. One opens, the other reacts.
One agent builds. You choose which, or let it decide.
The other reviews the diff and calls out anything that looks wrong.
You verify, then it loops back for another round if needed.
Auto mode is the part of this I really like the most now. Every agent turn ends with a small structured decision packet: what it did, what it recommends next, any blockers, and a safe default action. With autopilot on, Hydra takes that safe default and advances the loop on its own, discussion into build, build into verify, verify into review, and around again. It runs your test or build command automatically after each build. The thing that makes it usable is the risk gate. The moment a step looks dangerous, like a push, a delete, a deploy, it stops and hands the decision back to you instead of running it. So you can let it grind through the boring middle of a task and only jump in for the calls that actually need you.
Other stuff it does..
Per phase model and reasoning selection. Run a cheap model for the discussion and a strong one for the build. 0.6 adds the current models: Fable, Sonnet 5, GPT 5.6, Opus 4.x, and Haiku.
A live cost meter, plus an optional hard spend cap per session, read from a local usage log.
Parallel mode, where both agents build and review at the same time instead of taking turns.
Project memory. Hydra compiles what happened into a small wiki based on Andrej Karpathy's wiki model, under .hydra and feeds the relevant parts back into later prompts, so a long running project keeps its context across turns and sessions.
File attachments. Drop a file into a turn and it gets copied locally with a bounded preview added to the prompt.
Live streaming, so you watch each reply as it is written instead of waiting for the whole block.
An optional visible terminal mode if you would rather see the agents working in a real shell.
Telegram notifications. If a decision needs you while you are away from the desk, it pings your phone and you can answer from there. 0.6 added a per sender allowlist for that inbound path.
Prompt templates, a workspace state cleaner, and a doctor command that checks your setup.
Everything stays on your machine. It drives the real Codex and Claude Code CLIs you already have, using your existing logins, and writes the full transcript, the plan, and every decision into a .hydra folder you can read.
The code is MIT licensed and lives here: https://github.com/Geraldlol/hydra If you want to help, issues and pull requests are open. Bug reports, rough edges, feature ideas, and feedback are all genuinely super useful right now. I have no idea what the fuck I'm doing. I am the only person on it so far, so more hands and more testing would go a long way.
You can install by searching "Hydra Agents" in the VS Code extensions panel, or here: https://marketplace.visualstudio.com/items?itemName=geraldlol.vscode-hydra-room
Requirements: the Codex CLI and Claude Code CLI installed and logged in. I develop on Windows so that is the most tested path.
Happy to answer anything about the orchestration, the decision packets, the review handoffs or anything else.
Thanks for taking a look and reading!
If you are a Vim/Neovim user in VS Code, or if you heavily rely on a keyboard-driven workflow with editor.lineNumbers: "relative", you’ve definitely run into this frustrating brick wall:
As soon as editor.wordWrap is turned on, virtual lines (wrapped lines) display absolutely nothing in the gutter.
Because VS Code only binds line numbers to physical lines (\n), performing a precise vertical jump like 5j or 12k becomes a guessing game if your code or Markdown blocks wrap across the screen. You have to manually count the visual lines yourself, which completely defeats the purpose of relative numbers.
There is an open, feature request on the official VS Code repository that targets the core layout engine (Monaco) to finally allow rendering numbers on wrapped lines:
🔗 GitHub Issue #323238: Option to display relative line numbers for virtual/wrapped lines
If you want to finally get a layout option like "editor.renderRelativeNumbersOnWrappedLines": true to make modal editing seamless with word wrap, please take 10 seconds to click the link above and drop a 👍 thumbs-up reaction on the first post of the issue.
Let’s get this on the dev team's radar for the upcoming releases!
Why am I seeing two different source controls in vscode. Help me🙏
I used it for about three weeks, and so far the experience has been great. Its own extension marketplace (Microsoft doesn't allow third-party apps to use the official VSCode marketplace, but this can be fixed by simply convincing extension authors to also upload their extensions to an open marketplace) has everything I needed. All Microsoft proprietary extensions (like SSH) have open-source alternatives that work without issue. And you don't have to give up any of your usage habits.
never used VSCode before. have been using snow sight.
any best and clear youtube video tutorials for learning VSCode to use snowflake, CoCo, python, Github in VSCode. Navigations videos. thanks.
Hi!
This is my first ever made VS Code extension called "Color Blocks" originally written as a personal aid in long files when sorting through spaghetti code. It lets you define areas or "blocks" using comments which can be helpful in partitioning up code.
I recently gave it some love and tried to improve performance.
Feedback wanted!
Check it out here: https://marketplace.visualstudio.com/items?itemName=zimonitrome.color-blocks
I'm a Neovim user... was interested to see if I could get a Neovim-like experience inside VS Code in 2026. It seems like you can?
With a combination of plugins, settings and keybindings you can really achieve something special.
Shoutout to the open source extension developers, wouldn't be possible without you <3
Just looking into perhaps installing MS Code and bearing in mind the spy issues with MS products - is this one okay?
For people using AI inside VS Code, how do you handle longer coding sessions?
I’ll often get into a state where the AI chat knows a lot about the task, but it’s also full of old attempts and stale context.
When you need to restart or move to another tool, how do you carry over the useful state?
Do you keep notes in the repo? Use commits as checkpoints? Rely on the extension’s chat history? Ask for a summary?
Looking for practical workflows, not “which AI is best.”
I have like 80+ extensions installed, half of which I probably used once, and going through the Extensions tab deciding what to uninstall is just annoying enough that I keep putting it off.
So I made a little extension called Extension Cleaner!
It works like Tinder:
(it also has a dark and light mode)
extension: https://marketplace.visualstudio.com/items?itemName=VandanBhatt.extension-cleaner
demo video: https://youtu.be/qRKeIULHtC4?si=pQxcsQudNgrYJf8e