introducing the greptile CLI.
a full greptile review for your local changes, right in your terminal.
1. npm i -g greptile
2. checkout your branch
3. greptile review ๐ฆ
introducing the greptile CLI.
a full greptile review for your local changes, right in your terminal.
1. npm i -g greptile
2. checkout your branch
3. greptile review ๐ฆ
We review code for 22,000 teams, and we don't use one AI model to do it. Each job goes to the model that fits it best.
We put @nvidia Nemotron 3 Ultra to the test on two of the most demanding: ~4.5x cheaper reply classification and 62% cheaper indexing in beta. Read how, then try it free https://t.co/1o4liEOp29.
introducing repo clusters
you can now group related repos into a cluster, like frontend, backend and docs. when greptile reviews a PR on one of those repos, it will have complete context of the others.
greptile will also intelligently suggest clusters
CEO of @greptile, @dakshgup is speaking at DASH ๐ฏ
In the CEO panel, that includes @zachlloydtweets (CEO @ @warpdotdev) and Jay V (@opencode), they will discuss if coding agents are reviewing PRs, debugging issues, writing code, and executing tasks across your stack, what does that mean for the future of software engineering?
Grab you $49 DASH Builder ticket (made for those that ship): https://t.co/cKCDzRVw07
June 9 in NYC. Datadog
i think about code review a lot
it's really broken now. absolutely impossible to review all the PRs manually
for a long time cursor bugbot felt like the best solution. today it's without a doubt @greptile
feels like a codex vs. claude code vibe shift. good reminder to always keep building
Greptile is coming to Tokyo, Japan! ๐ฏ๐ต๐ฆ
To celebrate, we are hosting a community Happy Hour for our users and friends. It's happening on Monday, June 8th, 7-10 pm.
Get a chance to win free Greptile credits, merch, and free drinks!! Looking forward to it. :)
-----------------------------------------------------------
@greptile ใๆฑไบฌใซใใฃใฆใใพใ๏ผ๐ผ
ใใใ่จๅฟตใใฆใใฆใผใถใผใฎ็ใใพใปใๅ้ใฎใใใฎใณใใฅใใใฃใปใใใใผใขใฏใผใ้ๅฌใใพใใ
๐ 6ๆ8ๆฅ๏ผๆ๏ผ ๐ 19:00โ22:00
Greptileใฏใฌใธใใใใชใชใธใใซใฐใใบใๅฝใใใใฃใณในใใใใซใใชใณใฏใ็กๆใงใ๏ผ
็ใใพใซใไผใใงใใใฎใๆฅฝใใฟใซใใฆใใพใ๐
RSVP/ๅๅ ็ป้ฒ:
https://t.co/yPxVOwEwbn
As of last week, I started incorporating @greptile into my code review process.
My first impression has been quite positive: it helps me understand pull requests faster, identify potential risks earlier, and take a more systematic look at details that might otherwise be missed during the review process.
I believe AI-powered code review tools will continue to play a growing role in software development workflows. For now, my goal is not to completely replace manual review, but to make it more efficient, consistent, and focused.
launching 5 things:
1. multi-repo context support
2. rebuilt web app for super large orgs
3. integrations with claude/codex/devin
4. .greptile/rules files
5. rebuilt learning so greptile maintains internal docs about your company
How do i detect AI slop? I find adding skills, gates with scripts being added along with @greptile in CI.
This makes the process a bit slow since i detect review findings aftermath in CI
1. @greptile chugs a bit
2. @github is slow in CI (can't move to @useblacksmith)
since opensource generasity is with @github (not sure for how long)
reference https://t.co/HcFhEycmtE