Mergestorm

AI PR review agents. Catch issues before merge.

[Mergestorm @Mergestorm]

Stacked PRs from your terminal.

npm i -g mergestorm
mg stack create
mg stack submit

Two layers → chained PRs → land.

https://t.co/WRDP5B3Cj6

[Mergestorm @Mergestorm]

Don’t sleep on Breeze

[Mergestorm @Mergestorm]

Tell Breeze what you want in plain words. Get a live page with its own link. No code. Free to start.

[Mergestorm @Mergestorm]

Vortex now reviews every push on Claude Haiku 5.5: adaptive thinking, 1M-token context, live today.

https://t.co/0xSVUn4PAp

[Claude @claudeai]

Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released.

On average, it costs around 75% less to run than Claude Haiku 4.5.

[Mergestorm @Mergestorm]

How it works and how to set it up: https://t.co/Zk3NNKvgZv

[Mergestorm @Mergestorm]

Surge is in public beta.

On-demand CI runners for GitHub Actions. They start when your jobs queue and scale to zero when CI goes quiet.

One line in your workflow. If Surge is off, jobs fall back to GitHub-hosted runners.

Minutes included with paid plans.

[Mergestorm @Mergestorm]

The one line:

runs-on: ${{ https://t.co/Kccxpq780f_SURGE_RUNNER || 'ubuntu-latest' }}

Set while Surge is on, so the job runs there. Unset otherwise, so it runs on GitHub as before.

[Mergestorm @Mergestorm]

New mark.
Same storm. Cleaner lines.

Five bars. One tip. Built for the merge gate.

[Mergestorm @Mergestorm]

We moved the review fleet to DeepSeek V4.1 Flash.

Vortex is the one to try: it runs on every push, 1 credit, no extra setting. Turn it on, open a PR, and you’ll see the pass.

How we cut over, and how to pick Flash for Tempest: https://t.co/VBEMkU9Kuw

Deploy Vortex: https://t.co/Ex9dHjf7pj

[Mergestorm @Mergestorm]

If you’re using Mergestorm’s Vortex agent to review your PRs, you are already using the all new DeepSeek V4.1 Flash.

Give it a try.

[DeepSeek @deepseek_ai]

🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.

🔹 Introducing the smallest model in our new architecture family, with native visual understanding.
🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models.

1/6

[Mergestorm @Mergestorm]

Your next PR. GPT-6 Astra in the reviewer seat. Try Mergestorm Tempest.

https://t.co/0xSVUn4PAp

[Mergestorm @Mergestorm]

Automatic review on your GitHub PRs

[Mergestorm @Mergestorm]

GitHub might be down but Mergestorm has a mayday path built in.

Run your reviews on a local branch. You can use npm mergestorm (the mergestorm cli) to run reviews without touching GitHub.

[GitHub Status @githubstatus]

We are experiencing high error rates around 20% for web experiences and api traffic. Archive downloads and raw repository content downloads are experiencing an approximate 50% error rate. Investigations are on-going into the root cause, and updates will... https://t.co/WB8TquG3GM

[Mergestorm @Mergestorm]

We ran a blind A/B on real Vortex PR reviews: Claude Haiku 4.5 vs DeepSeek V4 Flash. Same diffs, same prompts.

72 paired runs. DeepSeek was 85.6% cheaper and posted more inlines.

Next: a 4-agent DeepSeek fleet, in parallel. Still cheaper than one Haiku pass.

Small honest study: https://t.co/6l7fB8UpN7

[Mark Arguinbaev @marginsystems]

Elevate your PRs with Stacked Layers and Review Units so you can ship production quality code faster.

Perfect for agentic workflows like Cursor

[Mergestorm @Mergestorm]

We’re working on releasing a specialized GitHub PR stacks workflow with our proprietary review unit architecture to elevate your coding review agents.

Our agents are now able to properly review each PR within a stack, then do special seam reviews between each PRs and look at the stack as a whole.

Now you can ship a big feature a set of smaller PRs and get proper review for the whole stack and for individual PRs.

[Mergestorm @Mergestorm]

@michaelokeje Did they end up releasing it?

[Mergestorm @Mergestorm]

@nkgoutham @13scoobie @droid I will run it through tonight

[Mergestorm @Mergestorm]

I have used SOL for planning a few times and it seemed solid, but haven’t experimented with it enough I’m way too comfortable and trusting with Opus.

I always use Cursor’s default for the model selection.

Fable High
Opus High

Don’t think I’ve ever used xhigh.

If your plans are well scoped you don’t really need the higher versions.

[Mergestorm @Mergestorm]

Please man if this is AI, tell it to stop using em dashes. If you’re a human you should also stop using em dashes even if you feel like it, a sad truth but it will help your visibility whether you like it or not.

For human eyes, yes it’s important to get human input into your coding pipeline, the question is where?

We can automate code review + patching on a branch / PR level.

You have some options:

You can use humans to prompt agents to open issues + PRs. Then trust your pipeline enough to let it automatically review the code + patch it, using specialized agents and harnesses (which we’ve built if you’re interested)

You also need humans to sanity check your code at the merge gate, whether you’re using Graphite for stacked PRs or just normal gh.

Humans are critical to prevent drift and AI slop, but their job is now much higher level, even higher than architecture.

[Mergestorm @Mergestorm]

@nkgoutham @13scoobie @droid Exactly!

I am so happy with Opus / Fable I just didn’t even get a chance or have a need to try out SOL.