Draft:CloudAEye
This draft is not written from a neutral point of view. Wikipedia articles must be written neutrally in a formal, impersonal, and dispassionate way. They should not read like a blog post, advertisement, or fan page. Rewrite the draft to remove:
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
CloudAEye is a software company that develops artificial intelligence tools for software engineering. Its products use large language models (LLMs) and code intelligence techniques to assist with code review, test failure analysis, code understanding, developer productivity, and software engineering workflows. Wellfound describes CloudAEye as a software-as-a-service (SaaS) artificial intelligence company based in the San Francisco Bay Area.
The company's principal product is CloudAEye Code Review[1], an AI-assisted code review system designed to identify bugs, security vulnerabilities, code-quality issues, and other potential problems in software changes.
CloudAEye integrates with source-control platforms and development environments, including GitHub[2], GitLab[3], Bitbucket[4], and Visual Studio Code[5]. In supported source-control workflows, users can initiate a code review within a pull request by commenting `@cloudaeye /review[6]`. Its Visual Studio Code extension provides code review capabilities directly within the development environment.
History
[edit]CloudAEye was founded in 2021. Its initial product focus was cloud operations and observability. CloudAEye later expanded its product portfolio to include AI-assisted software development, with code review becoming one of its principal products.
Integrations
[edit]CloudAEye provides integrations with software development platforms and development environments. Its documented integrations include GitHub, GitLab, Bitbucket, Visual Studio Code, and Claude Code.
The GitHub, GitLab, and Bitbucket integrations allow organizations to connect repositories and initiate automated code reviews from pull requests. The Claude Code integration provides a pre-commit workflow that checks code against the task definition before a pull request is created.
Benchmarks
[edit]In 2026, CloudAEye published[7] based on the open-source benchmark[8] developed by Martin[9]. It compares 21 AI-based code review tools. The benchmark evaluated 50 pull requests from five open-source software projects across five programming languages: Java, Python, TypeScript, Go, and Ruby. Each pull request was assessed against a set of human-verified issues, referred to as "golden comments," and the tools were evaluated using precision, recall, and F1 scores. The evaluation used an automated process to extract, deduplicate, and semantically match findings from each tool's review output.
According to the results published by CloudAEye, its code review system achieved the highest overall F1 score among the 21 tools evaluated, at approximately 65%. The benchmark also reported that CloudAEye had an 86% recall on one of the evaluated repositories and the highest precision across another.
| Rank | Code review tool | F1 | Precision | Recall |
|---|---|---|---|---|
| 1 | CloudAEye | 66.7% | 62.4% | 71.5% |
| 2 | Cubic Dev | 61.8% | 56.3% | 68.6% |
| 3 | Qodo Extended | 57.9% | 54.9% | 61.3% |
| 4 | Augment | 53.5% | 47.5% | 61.3% |
| 5 | Qodo | 48.4% | 42.9% | 55.5% |
| 6 | Propel | 46.9% | 44.4% | 49.6% |
| 7 | Macroscope | 46.0% | 48.4% | 43.8% |
| 8 | Cursor Bugbot | 45.5% | 47.2% | 43.8% |
| 9 | Devin | 44.2% | 54.3% | 37.2% |
| 10 | Greptile | 44.0% | 40.5% | 48.2% |
| 11 | Sourcery AI | 40.6% | 33.3% | 51.8% |
| 12 | Kodus | 40.5% | 46.7% | 35.8% |
| 13 | Baz | 40.3% | 49.0% | 34.3% |
| 14 | Claude Code Plugin | 37.6% | 34.8% | 40.9% |
| 15 | GitHub Copilot | 37.0% | 28.3% | 53.3% |
| 16 | Claude Code Reviewer | 35.3% | 34.8% | 35.8% |
| 17 | CodeRabbit | 35.2% | 25.7% | 56.2% |
| 18 | CodeAnt AI | 34.7% | 31.9% | 38.0% |
| 19 | Gemini | 33.9% | 31.1% | 37.2% |
| 20 | Kilo+Grok | 25.1% | 50.0% | 16.8% |
| 21 | Graphite | 16.1% | 100.0% | 8.8% |
C/C++ Benchmark
[edit]In 2026, CloudAEye published an open-source[10] benchmark[11] evaluating nine AI-assisted code review tools on C and C++ software. The evaluation used 16 pull requests from 13 open-source projects and compared the tools' findings with a set of human-verified issues. The benchmark measured precision, recall, and F1 score based on the number of correctly identified issues and false-positive and false-negative results.
According to the results published by CloudAEye, CloudAEye Code Review recorded an F1 score of 70.0%. Cursor Bugbot recorded an F1 score of 41.2% while Qodo Extended recorded 36.4%. Other tools included Greptile, Gemini, GitHub Copilot, OpenAI Codex, Claude Code Reviewer, and CodeRabbit.
The benchmark covered a range of open-source C and C++ projects, including Fastfetch, libuv, nginx, MicroPython, PHP, Valkey, nlohmann/json, Dragonfly, CARLA, Godot, Windows Terminal, OpenCV, and Tesseract. The benchmark follows a similar methodology developed by Martin and the results were published in open-source by CloudAEye.
| Rank | Code review tool | Precision | Recall | F1 |
|---|---|---|---|---|
| 1 | CloudAEye | 70.0% | 70.0% | 70.0% |
| 2 | Cursor Bugbot | 50.0% | 35.0% | 41.2% |
| 3 | Qodo Extended | 28.6% | 50.0% | 36.4% |
| 4 | Greptile | 27.8% | 50.0% | 35.7% |
| 5 | Gemini | 24.4% | 50.0% | 32.8% |
| 6 | GitHub Copilot | 20.8% | 50.0% | 29.4% |
| 7 | Claude Code Reviewer | 17.3% | 65.0% | 27.4% |
| 8 | OpenAI Codex | 29.4% | 25.0% | 27.0% |
| 9 | CodeRabbit | 27.8% | 25.0% | 26.3% |
Recognition
[edit]In 2022, Wellfound, formerly AngelList, selected CloudAEye as one of its top startups[12] in the artificial intelligence category. Wellfound stated that its selections were based on a combination of investor and industry-expert input and data concerning interest in startups on its platform.
In 2023, CloudAEye was selected as one of the 200 companies participating in the Startup Battlefield program at TechCrunch Disrupt[13]. CloudAEye identifies the event as one of its company milestones.
In 2024, CloudAEye was included in a Startup Grind Global article titled "Global 2024 – AI Startups You Don't Want to Miss.[14]" The article selected CloudAEye as one of the AI startups featured in connection with the Startup Grind Global conference.
CloudAEye also announced that it had joined NVIDIA Inception[15], a program for startups developing technologies using NVIDIA platforms. The announcement was made through CloudAEye's LinkedIn account.
These recognitions are independent events involving different organizations, but they do not by themselves constitute independent evaluations of CloudAEye's products or establish the company's commercial performance.
References
[edit]- ↑ CloudAEye. "AI Code Review Tool for Engineering Teams | CloudAEye". www.cloudaeye.com. Retrieved 2026-08-18.
- ↑ "Configure - CloudAEye Documentation". docs.cloudaeye.com. Retrieved 2026-08-18.
- ↑ "GitLab - CloudAEye Documentation". docs.cloudaeye.com. Retrieved 2026-08-18.
- ↑ "Bitbucket - CloudAEye Documentation". docs.cloudaeye.com. Retrieved 2026-08-18.
- ↑ "Getting Started - CloudAEye Documentation". docs.cloudaeye.com. Retrieved 2026-08-18.
- ↑ "Review Code - CloudAEye Documentation". docs.cloudaeye.com. Retrieved 2026-08-18.
- ↑ CloudAEye. "AI Code Review Benchmark: Compare 21 AI Code Review Tools". www.cloudaeye.com. Retrieved 2026-08-18.
- ↑ CloudAEye/code-review-benchmark, CloudAEye, 2026-06-15, retrieved 2026-08-18
- ↑ withmartian/code-review-benchmark, Martian, 2026-08-17, retrieved 2026-08-18
- ↑ CloudAEye/c_cpp_benchmark, CloudAEye, 2026-07-02, retrieved 2026-08-18
- ↑ CloudAEye. "AI Code Review Benchmark: Compare 9 AI Code Review Tools". www.cloudaeye.com. Retrieved 2026-08-18.
- ↑ "The Top Startups of 2022 - Wellfound (formerly AngelList Talent)". wellfound.com. Retrieved 2026-08-18.
- ↑ Tambe, Neesha (2023-09-18). "Introducing the Startup Battlefield 200 companies at TechCrunch Disrupt 2023". TechCrunch. Retrieved 2026-08-18.
- ↑ Vijga, Lidia (2024-04-16). "Global 2024 - AI Startups You Don't Want to Miss". BYVI. Retrieved 2026-08-18.
- ↑ "#nvidiainception | CloudAEye". LinkedIn. Retrieved 2026-08-18.
- provide significant coverage: discuss the subject in detail, excluding routine coverage like product launches, staff appointments, or financial reports and listings in databases or listicles;
- are reliable: from reputable outlets with editorial oversight;
- are independent: not connected to the subject, such as press releases, the subject's own website, or sponsored content.
Please add references that meet all three of these criteria. If none exist, the subject is not yet suitable for Wikipedia.