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

Hey Product Hunt 👋 - Job from the Kilo team.

Very excited for this launch. The new Kilo for VS Code is my daily driver, and this rebuilt version with agent manager is in my opinion the next step in agentic coding. I now let multiple agents run at the same time using agent manager, and it speeds up my workflow a lot. Super curious to hear what you think of it!

🚨 We're also hosting 2 live sessions TODAY:

10am EST | The Kilo Show for Non-Coders

We'll talk marketing automation, SEO, competitive analysis, and design

11am EST | The Kilo Show for Coders

We'll talk agent orchestration, codebase indexing, and IDE workflows

 yes, and we're hanging out here, on and all day - ask us anything ✌️

Does the agent manager have any limits on how many parallel agents you can run at once, or is it just constrained by your machine's resources?

 it is only constrained by the hardware you’re running on.

 for example, what's your setup and how many agents do you run in parallel?

 It's constrained by machine resources

Yes, and ICYMI you can read the docs for full details on parallel agents here:

 No limit, so it's a machine constraint if any!

Great update guys! Nice work!

ty! what's your favorite new feature in this release?

also curious what should launch next? take the poll here in

 thank you, happy you like it!

 anything we could share from the roadmap btw? any early previews on what's next for ?

 Thanks a lot!

let's spread the word on X!

Just curious, when multiple subagents are running in parallel, how does the merge back to the parent agent work? Does it ever create conflicts when two agents touch overlapping parts of the codebase?

 with the agent manager, each agent gets their own git worktree. That way they don’t conflict with one another. Then once they are done you can either open a PR directly from that worktree or have the agent merge it back into your local copy

adding here the direct link to the docs for full context re: Agent Manager

hope it helps - happy shipping!

 There are two default subagents, general and explore. Explore tends to be utilized to find or answer a question about the codebase, and general can be used to make parallel edits but in a way that is directed by the parent agent to not cause conflicts (separate folders, modules, etc)

 We use git worktrees to prevent conflict so that you can merge without issues!

also curious how many agents do you run in parallel?

Great questions! Fun fact: parallel agents was one of the bets in v7 that took the longest to get right.

Try it here:

vscode:extension/kilocode.kilo-code

Looking forward to your thoughts

How does Kilo handle context limits when you've got multiple subagents running on a large codebase? Does each subagent get its own context window or do they share?


 yes that’s the best part - each agent has their own context window. The parent agent passes only the context needed for the subagent to get its task done, and the subagent only passes the results back to the parent. All of the in between context doesn’t pollute one or the other

 Each subagent gets its own context, then provides a summarized report to the primary agent. You can view subagent sessions while they are running and the final report if you are interested.

 They each get their own when you're on separate worktrees (branching from the original agent), and can share when the work is merged back in :)

great question! also curious how many agents do you run in parallel?

Niiiice! Looks amazing and clean

 lfg! what new feature are you most excited about?

 also curious what should launch next from your POV? take the poll here in

 thank you!

   yes, and please help us spread the word on X -

 Thank you!

🔌 Plugged in

Been loving my experience with Kilo! Love the team and the speed at which things are shipped. This is just another great example of the speed at which this team can produce great work!

spot on! this team keeps shipping: for and , and more with ...

 Kilo Speed!

 to quote The Leaderboard, 's daily newsletter:

"The GitLab playbook for AI tools."

Source:

 Thank you! Glad you're enjoying it :)

Used the old Kilo VS extension and have been using the new. Love the changes and it works smoothly. Excited to see many of the coming updates, too.

Thank you, Josh!

Follow-up question: What should we build/improve/fix from your perspective? Take the poll here in

 thanks for joining us on the journey. What do you like most from the new version?

What do you like most from the new version?

 following this 👀

quick update: some users wanted more control back, and the team worked on , like better diffs before you approve and permission flow fixes.

curious about your pov - how do you like to work with AI coding agents? Human-in-the-Loop or agent-first?

 Thank you! Glad you're enjoying it.

A lot of people hit a breaking point when agents start generating more diffs than they can confidently review—how did you design the inline diff reviewer + line-comment-to-chat loop to reduce review fatigue, and what review metrics (time-to-approval, revert rate, “second pass” prompts) are you tracking to prove it works?

 Good question!

We offer both local reviews in the extension and automated reviews on Github and GitLab PRs.

You can specify the strictness in both cases, so that you can filter down to the review points you actually care about.

How does the multi agent system comparison handle tokens ? does it run them all in the background simultaneously ? btw Congrats on the launch :)

 Thank you!

And yes, while you can bring your own keys or use local models, most users pay for inference via the Kilo Gateway, which lets you switch freely between models using one balance.

You just pay for token at provider costs - whatever Anthropic charges for Opus, and whatever OpenAI charges for GPT, that's what you pay!

exactly - pay only for what you use. learn more about pricing here:

 it runs them on separated git worktrees

thanks for the support! help us spread the word on LinkedIn,