Kilo Code
The open-source agentic engineering platform
Start new thread

Kilo Code for VS Code - Parallel agents, diff reviewer, and multi-model comparisons

by•
We've completely rebuilt Kilo Code for VS Code, built on OpenCode server. New portable core, parallel tool calls, subagent delegation, inline code review, multi-model comparisons. Get started: kilo.ai/install

Add a comment

Replies

Best

this is great. Going to use it for building ActorDo.
KiloCode works as a good alternative to github copilot

Maker

 thanks, love to hear what you think coming from copilot.

Maker

 looking forward to it! gives you agentic coding across 500+ models - not a single Copilot-branded autocomplete. more about how both compares here:

enjoy!

 most people use 2-3 models, so 500 are anyway useless.
copilot is actually very good, autocomplete is just 0.1% of it's worth.

however I will test kilocode for the whole team.

Maker

   Fair point on the model usage! Yet part of what makes our Agent Manager so cool is how easy it is to experiment and run different models in parallel, testing the same prompt.
Curious how your Kilo test drive goes! Please share feedback here, or in

   that's true. Exactly that's why I wanna test it.

How does Kilo deal with context limits on large codebases with multiple subagents? Do subagents keep separate context windows or share the same one?
Maker

that's the best part: each agent has their own context window ✌️

 when you let them run on separate git work-trees the context windows stay separated

Maker

also curious: how many agents do you run in parallel?

Parallel coding agents with a diff reviewer is a solid upgrade over linear autocomplete. Curious how you handle merge conflicts when two agents edit the same function simultaneously.

Maker

great q - uses git worktrees to prevent conflict. you can merge without issues!

Maker

oh and one more thing: feel free to join the Discord server for help and support -

 as said, you can work on separated worktrees and solve merge conflicts using a git workflow

Maker

worth mentioning parallel work pays off when sessions are independent, i.e. neither one's output depends on the other, and they are unlikely to edit the same files. things like independent features, module-scoped refactors, a feature plus an unrelated bug fix, trying 2–4 approaches to the same problem.

learn more:

When KiloCode CLI? :D

Maker

Today. 

npm install -g /cli

Spoiler alert: launching soon on 👀

Maker

 we already have it :

 What about perplexity computer. I feel thats the goat now. Its like a step above Claude code. Well it uses claude code as a subroutine. But it feels 3-4x better than pure Claude code. Any plans to move up market. To move one step above claude code? # Inception the movie 😬

Maker

 spoiler alert!!1 🙈

This is the one feature I didn't know I needed till I saw it, Parallel agents in VS Code. Every other coding tool makes you wait till your working on one task to start the next. This completely eliminates the bottleneck. Also line-level diff review makes it usable instead of just blindly trusting whatever the agent spits out. Brian Turcotte does the diff reviewer work with all supported models or is it model-dependent?

Maker

yes!! parallel agents means your tool calls run at the same time instead of waiting in line. search, wait, read, wait, edit, wait. the new for fires those calls concurrently when they're independent.

it's the difference between waiting on your agent and working with it.

help us spread the word on X,

 the diff and local code reviewer works with any model

Maker

any AI models you'd recommend for code reviews? heard good things about M2.7

I've been running agents on the same branch as my main codebase and wondering why reviews feel so stressful. The worktree isolation answer is embarrassingly obvious in retrospect. The multi-model comparison feature is the sleeper hit here — being able to see how different models approach the same diff side by side is genuinely useful for building intuition about when to switch models. Does the comparison run them simultaneously or sequentially, and does it add a lot of latency to the workflow?

Maker

 Thank you! Your words just made my day.

Does the multi-model comparison run simultaneously?

Yes! Opus 4.8, GPT-5.5, M2.7... Try 'em all here:

vscode:extension/kilocode.kilo-code

And let us know how your experience is! Enjoy!

Congrats on the launch 🚀
Looks super solid — already shared this with our dev team, think they’ll really like it.

Maker

 amazing! join the Discord server for advanced help and support:

The line-level review flow on agent-generated diffs is honestly one of the smarter UX decisions I’ve seen in coding agents recently. Most tools optimize for generation speed, but trust and verification are probably the bigger long-term problem.

Maker

The line-level review flow on agent-generated diffs is honestly one of the smarter UX decisions I’ve seen in coding agents recently. Most tools optimize for generation speed, but trust and verification are probably the bigger long-term problem.

framing this!!1

The inline review on agent diffs is the bit I'd probably use most. When agents touch 6-8 files, reviewing only the final patch is where I slow down. Curious if those comments can carry across the VS Code + CLI handoff too?

Maker

thanks for your support! and good question.

TL,DR: yes.

this new extension has the same open-source core that powers Kilo CLI and Cloud Agents. one engine, multiple platforms. you can trigger local AI-powered code reviews from the editor or the terminal.

see the docs for the full setup and options:

The inline diff reviewer is the feature I didn't know I needed. There's always that moment where an agent makes a change that looks right at a glance but isn't -- having line-level review comments in context closes that loop. We use VS Code for our Next.js dev work so this is going on the team's list. Congrats on last month's #1.

Maker

Thank you, Schott! I'd love to get your feedback if you had a chance to use the new btw. You can:

Looking forward to seeing what you're building!

First
Previous
1234