Open source AI code reviews. Less headache, more deploy. 🔥
Joined September 2018
- Tweets 499
- Following 572
- Followers 489
- Likes 348
105 Photos and videos
Jun 15
Kodus just shipped a new release.
This time, we focused on practical parts of the review flow: making it easier to understand what’s happening, act on suggestions with less friction, and keep the experience more consistent behind the scenes.
Main updates 👇
1
2
3
98
Jun 15
⚙️ Improvements
We also shipped some important foundational improvements in this release.
The focus was on making builds more consistent and making token usage easier to track.
→ Backend on pnpm
We migrated the backend from Yarn 1 to pnpm.
This helps make builds faster, improves lockfile consistency, and reduces cache issues across environments.
→ Token usage screen
The token usage screen has been redesigned.
It is now easier to track usage by organization and period, and to understand how tokens are being consumed over time.
1
26
Jun 8
New Kodus changelog is out ✨
This release brings more flexibility for BYOK, better control over token usage, and a few reliability improvements across different setups.
Main updates below 👇
1
2
3
162
Jun 8
✨ Improvements
→ More resilient review agent
The review engine now handles empty or malformed LLM responses better.
This reduces loops in edge cases and helps ensure valid suggestions continue to be delivered even when the provider returns an unexpected response.
→ Telemetry for self-hosted environments
On-premise installations now automatically report health metrics, such as heartbeat, and usage data.
The goal is to make diagnosis and support easier without exposing sensitive customer data.
→ Faster Kody Rules
We improved the loading and synchronization of custom rules.
We also fixed the count of orphaned rules and made partial updates safer against race conditions.
→ GitLab compatibility improvements
• Support for GitLab 13.x in comment webhooks
• Diff fallback for versions earlier than 15.7
• Fixes for discussion threads and replies scoped by discussionId
• Self-hosted development environment documentation
1
45
Nem me lembro mais como era a minha vida antes de descobrir que a Kodus existia pqp
Apenas usem @kodustech
3
3
40
3,025
May 18
🥰🥰
70
Kody from Kodus retweeted
Apr 23
Moving between your PR comments and your editor to fix things one by one is a huge waste of time.
Open the PR, read comments, go back to the editor, repeat. It works, but you lose context fast.
You can pull those suggestions into the CLI:
↳ kodus pr suggestions --pr-url github.com/org/repo/pull/42
Now everything is local. Instead of going through each comment yourself, you let the review skill take the first pass.
It checks which suggestions actually make sense for that PR, applies the safe ones, ignores the noise, then runs checks again.
At that point you’re not working through a list of comments anymore. The PR already moved forward, and you’re reviewing what changed.
↳ Install: curl -fsSL review-skill.com/install | bash
1
1
290
Kody from Kodus retweeted
Apr 8
Code review catches code issues.
But who checks if the code actually implements the ticket?
Missing requirements, partial acceptance criteria, edge cases… most of this only shows up in QA or production.
We built Business Logic Validation in Kody for this.
It takes the PR diff, pulls context from Jira, and compares:
what was requested vs what was implemented.
You get:
→ MUST_FIX → missing or wrong logic
→ SUGGESTION → gaps and edge cases
→ Requirements Verified → what’s correct (with file line)
Setup takes ~1 minute. After that, it runs automatically on every PR.
You can also run it on demand:
→ @kody -v business-logic [ticket link]
Most teams review code quality, but few verify if the code actually solves the problem.
2
2
247
Kody from Kodus retweeted
Apr 2
Teach your AI reviewer your team’s unwritten rules
Every team has them:
→ “we don’t use Lodash here”
→ “API keys are camelCase”
→ “we’re migrating off SDK v2”
They show up in PR comments over and over.
With Memories, you can turn that into persistent context for Kody.
You literally just tell it:
→ @kody remember: API payload keys are camelCase
→ @kody in this repo we avoid Lodash
→ @kody we’re migrating from AWS SDK v2 to v3
From that point on, Kody carries this across every review. No need to repeat yourself.
Quick rule of thumb:
→ Use Memories → conventions, preferences, migrations
→ Use Rules → enforceable checks and patterns
This ends up being one of the highest leverage things you can do.
1
3
269
Apr 2
🧡🧡🧡
pra mim é impossível falar de trabalhar sozinho em produtos nesse ritmo insano de features sem mencionar o pessoal da @kodustech
cada um desses PRs só são mergeados depois que a Kody aprova
não sei oq seria de mim sem o code review desses caras
135
Apr 1
This battle is getting interesting 🐕
Apr 1
Traditional Precision-Recall curves tell you how your code review tool performs on static benchmarks.
They don't tell you how it performs against a Hawk.
Introducing Fight Index (FI).
4
224
Kody from Kodus retweeted
Mar 25
@kodustech saw one of the largest gains after the offline fixes (~ 10% F1).
1
2
15
783
Mar 20
😎
Mar 20
We’ve been trying to move away from that devtool website pattern where everything looks the same.
We’ve tried a few things, and this was one of the ones I liked the most.
you can now navigate the Kodus site as if it were a terminal.
take a look here: kodus.io
1
195