Lector de Feeds

Introduction

Hi there, blog readers! For the last week or so I've been poking into AI code review tools. Yes, this is partly because of the Red Hat "you must do AI things!" policy. But also, to be honest, because they seem to be...actually good now. I set up AI reviews for pull requests to our openQA test repo as an experiment. But especially over the last couple of months, they've got to the point where well over half of the review notes are actually useful, and the writing style isn't so awful I want to stab myself in the eyeballs. So I'd quite like to keep doing them, but in a more open source-y way. So far I've simply been cloning the pull requests to a GitHub mirror of the repo that exists solely to get AI reviews done. That repo has Gemini Code Assist enabled so the PRs are reviewed by Gemini automatically, e.g. here. It's very simple, but entirely closed source, there's no control over it, and Google could take it away at any time.

We're in the middle of migrating Fedora projects from Pagure to our new Forgejo instance, so I decided to try and get some sort of AI review system integrated with Forgejo. And I kinda succeeded! I wrote a Forgejo integration for ai-code-review, a tool I found that was written by another Red Hatter, and managed to set up a proof-of-concept Forgejo Actions workflow using it on a repo I own that's hosted at Codeberg (since Codeberg has public Forgejo Actions runners available; we don't have Actions entirely set up in the Fedora instance yet). Right now it's using Gemini as the model provider just because that was the easiest thing to set up for a PoC, but ai-code-review's design makes the LLM provider easily pluggable, so it's trivial to swap it out. Long term I hope we'll get a Fedora LLM provider set up, serving open source models, and we can make it use that. There's an Ollama backend, and adding an OpenAI API backend should be pretty easy.

Before going any further with that, though, I decided to look around and see if there are other tools out there, and if so, which might be the best one. I poked around a bit and found a few, and wrote up a very half-assed comparative assessment. I figured this might interest others, so I've prettied it up a tiny bit and put it below. I make no claims that this is comprehensive, accurate or fair, please send all complaints to the happyassassin.net HR department! The takeaway is that I'll probably keep working on the ai-code-review approach and also experiment with forking Qodo's archived open-source pr-agent project and see if I can add Forgejo support to it, to compare it against ai-code-review.

If anyone knows of any I missed, please let me know! I briefly looked at RhodeCode but discounted it because it's a whole-ass forge, not just a review tool. ReviewBoard doesn't seem to have any LLM integration as best as I could tell.

The Contenders ai-code-review

• Repo: https://gitlab.com/redhat/edge/ci-cd/ai-code-review
• Author: Juanje Ojeda (Red Hat)
• Language: Python (typed)
• Architecture: Modular
• Tests: Yes, LLM-generated, fairly comprehensive unit tests, very limited integration tests
• Begun: August 2025
• Status: Active
• Forges: GitLab, GitHub, local changes (Forgejo supported submitted)
• Model providers: Gemini, Anthropic, Ollama
• Output: Console or PR/MR comment
• Deployment: Local execution, GitLab CI, GitHub Actions (one-shot deployment via container image in CI job)
• Prompts: Here

ai-codereview

• Repo: Red Hat internal
• Author: Tuvya Korol (Red Hat)
• Language: Python (untyped)
• Architecture: Monolithic
• Tests: No
• Begun: June 2025
• Status: Active
• Forges: GitLab, local changes
• Model providers: RH-internal Claude, Gemini, Granite
• Output: Console or MR comment
• Deployment: Local execution, GitLab CI (ad hoc deployment via curl/pip in CI job)
• Prompts: Red Hat internal

kodus-ai

• Repo: https://github.com/kodustech/kodus-ai
• Author: Kodus
• Language: Typescript
• Architecture: Modular
• Tests: Yes, handwritten, unit and integration, not sure of coverage
• Begun: April 2025
• Status: Active
• Forges: GitHub, GitLab, BitBucket
• Model providers: OpenAI, Gemini, Anthropic, Novita, OpenRouter, any OpenAI-compatible
• Output: MR/PR comment and/or review (seems to depend on configuration)
• Deployment: Local via yarn (indicated as for development only), as containerized webapp (for prod) with own installer - looks complex
• Prompts: Here

pr-agent

• Repo: https://github.com/qodo-ai/pr-agent
• Author: Qodo (formerly Codium)
• Language: Python (untyped)
• Architecture: Modular
• Tests: Yes, handwritten, unit and integration, somewhat primitive, many commented out, 24% coverage (per codecov)
• Begun: July 2023
• Status: Archived (Nov 2025)
• Forges: GitHub, GitLab, Gitea, Gerrit, BitBucket, AWS CodeCommit, Azure DevOps, local changes
• Model providers: Any OpenAI-compatible (looks like some special handling for Azure), LiteLLM
• Output: MR/PR comment and/or review, has interactive features
• Deployment: Local execution or Forge CI. There's a custom GitHub action but it may be abandoned. Installable via pip, should be trivial to containerize for simple one-shot CI job deployment
• Prompts: Here

ai-pr-reviewer

• Repo: https://github.com/coderabbitai/ai-pr-reviewer
• Author: CodeRabbit
• Language: Typescript
• Architecture: Modular
• Tests: Barely any
• Begun: Feb 2023
• Status: Archived (Nov 2023)
• Forges: GitHub
• Model providers: OpenAI
• Output: PR review/comment
• Deployment: GitHub Action (no longer maintained). No generic or local deployment documented
• Prompts: Here

Conclusions

ai-code-review (Juanje) and pr-agent (Qodo/Codium) seem the best options.

Of the RH-developed, greenfield projects, ai-code-review is more featureful and better architected than ai-codereview, and not tied to an RH-internal model provider.

Of the existing public projects, ai-pr-reviewer (CodeRabbit) was very tied to GitHub, has no documented standalone deployment ability, and was archived fairly early in development. Plus it's in TypeScript. Kodus is actively developed, but similarly is in TypeScript, deployment looks complex, and from what I've seen I don't love its review style. Hard to say why but the project overall gives me a sloppy vibe. pr-agent (Qodo) had the longest development history and seems the most mature and capable at the point where it was abandoned (well, they actually seem to have done a heel turn and gone closed source / SaaS). It has a documented standalone deployment process which looks relatively simple and subject to integration into generic CI workflows.

In Mageia/9/x86_64: Mesa is an OpenGL 4.6 compatible 3D graphics library.

In Mageia/9/aarch64: Mesa is an OpenGL 4.6 compatible 3D graphics library.

In Mageia/9/armv7hl: Mesa is an OpenGL 4.6 compatible 3D graphics library.

In Mageia/9/i586: Mesa is an OpenGL 4.6 compatible 3D graphics library.

In Mageia/cauldron/x86_64: Rachota is a portable application for timetracking different projects. It runs everywhere. It displays time data in diagram form, creates customized reports and invoices or analyses measured data and suggests hints to improve user's time usage. The totally portable yet personal timetracker.

In Mageia/cauldron/i586: Rachota is a portable application for timetracking different projects. It runs everywhere. It displays time data in diagram form, creates customized reports and invoices or analyses measured data and suggests hints to improve user's time usage. The totally portable yet personal timetracker.

In Mageia/cauldron/i586: A program to convert images from PPM format into the control language for the Alps Micro-Dry printers, at various times sold by Citizen, Alps and Okidata. This program drives the Alps Micro-Dry series of printers, including the Citizen Printiva series, Alps MD series, and Oki DP series (but not yet the DP-7000). In the current release, the program drives the standard mode fairly well; the dye sublimation mode very well; and the VPhoto mode reasonably well. It supports all the colours available up to the DP-5000, including the foil colours.

In Mageia/cauldron/x86_64: A program to convert images from PPM format into the control language for the Alps Micro-Dry printers, at various times sold by Citizen, Alps and Okidata. This program drives the Alps Micro-Dry series of printers, including the Citizen Printiva series, Alps MD series, and Oki DP series (but not yet the DP-7000). In the current release, the program drives the standard mode fairly well; the dye sublimation mode very well; and the VPhoto mode reasonably well. It supports all the colours available up to the DP-5000, including the foil colours.

In Mageia/cauldron/x86_64: This tool tries to recover JFIF (JPEG) pictures and MOV movies (using recovermov) from a peripheral. This may be useful if you mistakenly overwrite a partition or if a device such as a digital camera memory card is bogus.

In Mageia/cauldron/i586: This tool tries to recover JFIF (JPEG) pictures and MOV movies (using recovermov) from a peripheral. This may be useful if you mistakenly overwrite a partition or if a device such as a digital camera memory card is bogus.

In Mageia/cauldron/x86_64: Rdfind is a program that finds duplicate files. It is useful for compressing backup directories or just finding duplicate files. It compares files based on their content, NOT on their file names.

In Mageia/cauldron/i586: Rdfind is a program that finds duplicate files. It is useful for compressing backup directories or just finding duplicate files. It compares files based on their content, NOT on their file names.

In Mageia/cauldron/x86_64: Unifont is a Unicode font with a glyph for every visible Unicode Basic Multilingual Plane code point and more, with supporting utilities to modify the font. This package contains tools and glyph descriptions.

In Mageia/cauldron/i586: Unifont is a Unicode font with a glyph for every visible Unicode Basic Multilingual Plane code point and more, with supporting utilities to modify the font. This package contains tools and glyph descriptions.

In Mageia/cauldron/i586: RANCID monitors a router's (or more generally a device's) configuration, including software and hardware (cards, serial numbers, etc) and uses CVS (Concurrent Version System) or Subversion to maintain history of changes. RANCID does this by the very simple process summarized here: * login to each device in the router table (router.db), * run various commands to get the information that will be saved, * cook the output; re-format, remove oscillating or incrementing data, * email any differences (sample) from the previous collection to a mail list, * and finally commit those changes to the revision control system RANCID also includes looking glass software. It is based on Ed Kern's looking glass which was once used for http://nitrous.digex.net/, for the old-school folks who remember it. Our version has added functions, supports Cisco, Juniper, and Foundry and uses the login scripts that come with rancid; so it can use telnet or ssh to connect to your devices(s). Rancid currently supports Cisco routers, Juniper routers, Catalyst switches, Foundry switches, Redback NASs, ADC EZT3 muxes, MRTd (and thus likely IRRd), Alteon switches, and HP Procurve switches and a host of others. Rancid is known to be used at: AOL, Global Crossing, MFN, NTT America, Certainty Solutions Inc.

In Mageia/cauldron/x86_64: RANCID monitors a router's (or more generally a device's) configuration, including software and hardware (cards, serial numbers, etc) and uses CVS (Concurrent Version System) or Subversion to maintain history of changes. RANCID does this by the very simple process summarized here: * login to each device in the router table (router.db), * run various commands to get the information that will be saved, * cook the output; re-format, remove oscillating or incrementing data, * email any differences (sample) from the previous collection to a mail list, * and finally commit those changes to the revision control system RANCID also includes looking glass software. It is based on Ed Kern's looking glass which was once used for http://nitrous.digex.net/, for the old-school folks who remember it. Our version has added functions, supports Cisco, Juniper, and Foundry and uses the login scripts that come with rancid; so it can use telnet or ssh to connect to your devices(s). Rancid currently supports Cisco routers, Juniper routers, Catalyst switches, Foundry switches, Redback NASs, ADC EZT3 muxes, MRTd (and thus likely IRRd), Alteon switches, and HP Procurve switches and a host of others. Rancid is known to be used at: AOL, Global Crossing, MFN, NTT America, Certainty Solutions Inc.

In Mageia/cauldron/x86_64: Redis is an advanced key-value store. It is often referred to as a data structure server since keys can contain strings, hashes, lists, sets and sorted sets. You can run atomic operations on these types, like appending to a string; incrementing the value in a hash; pushing to a list; computing set intersection, union and difference; or getting the member with highest ranking in a sorted set. In order to achieve its outstanding performance, Redis works with an in-memory dataset. Depending on your use case, you can persist it either by dumping the dataset to disk every once in a while, or by appending each command to a log. Redis also supports trivial-to-setup master-slave replication, with very fast non-blocking first synchronization, auto-reconnection on net split and so forth. Other features include Transactions, Pub/Sub, Lua scripting, Keys with a limited time-to-live, and configuration settings to make Redis behave like a cache. You can use Redis from most programming languages also.

In Mageia/cauldron/i586: Redis is an advanced key-value store. It is often referred to as a data structure server since keys can contain strings, hashes, lists, sets and sorted sets. You can run atomic operations on these types, like appending to a string; incrementing the value in a hash; pushing to a list; computing set intersection, union and difference; or getting the member with highest ranking in a sorted set. In order to achieve its outstanding performance, Redis works with an in-memory dataset. Depending on your use case, you can persist it either by dumping the dataset to disk every once in a while, or by appending each command to a log. Redis also supports trivial-to-setup master-slave replication, with very fast non-blocking first synchronization, auto-reconnection on net split and so forth. Other features include Transactions, Pub/Sub, Lua scripting, Keys with a limited time-to-live, and configuration settings to make Redis behave like a cache. You can use Redis from most programming languages also.