Source: https://seerepo.com/compare/alibaba/open-code-review/vs/JuliusBrussee/caveman
Markdown source: https://seerepo.com/compare/alibaba/open-code-review/vs/JuliusBrussee/caveman.md
Description: open-code-review and caveman share 3 technologies: net/http, Anthropic, and MCP. Both are written in Go.

# open-code-review vs caveman

open-code-review and caveman share 3 technologies: net/http, Anthropic, and MCP. Both are written in Go.

- [alibaba/open-code-review](https://seerepo.com/r/alibaba/open-code-review): Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
- [JuliusBrussee/caveman](https://seerepo.com/r/JuliusBrussee/caveman): 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

## What they share and what sets them apart

- In common: net/http, Anthropic, MCP
- Only in open-code-review: OpenAI
- Only in caveman: Postgres

## Side by side

| | open-code-review | caveman |
|---|---|---|
| Size | 182,440 lines written, 316 code files | 334,915 lines written, 435 code files |
| Who writes it | 2.3% of its commits signed by AI. With Claude Code, Cursor, Codex, and Warp | 74.4% of its commits signed by AI. With Claude Code and Cursor |
| Activity | Last push October 22, 2026, 812 commits, 48,785 stars | Last push October 28, 2026, 1,639 commits, 115,815 stars |
| Tests | 377 test files. 69.3% of its code files have a test that imports them | 711 test files. 72.6% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, open-code-review or caveman?

caveman, with 334,915 lines written in 435 code files; open-code-review has 182,440 in 316.

The proof: [JuliusBrussee/caveman's code at commit 9b68f7e](https://github.com/JuliusBrussee/caveman/tree/9b68f7ed12b05e7efaff18e65c5a3fc2849fd0a4)

### Which has more GitHub stars, open-code-review or caveman?

caveman, with 115,815 stars; open-code-review has 48,785.

The proof: [JuliusBrussee/caveman on GitHub](https://github.com/JuliusBrussee/caveman)

### Which has more tests, open-code-review or caveman?

caveman, with 711 test files; open-code-review has 377.

The proof: [JuliusBrussee/caveman's code at commit 9b68f7e](https://github.com/JuliusBrussee/caveman/tree/9b68f7ed12b05e7efaff18e65c5a3fc2849fd0a4)

### Which was updated more recently, open-code-review or caveman?

caveman: its last push was on October 28, 2026, and open-code-review's on October 22, 2026.

The proof: [JuliusBrussee/caveman's commits on GitHub](https://github.com/JuliusBrussee/caveman/commits)

### Which has more commits signed by AI, open-code-review or caveman?

caveman: an AI signed 74.4% of its commits, with Claude Code and Cursor; in open-code-review, 2.3%.

The proof: [the commits each tool signed in JuliusBrussee/caveman](https://seerepo.com/r/JuliusBrussee/caveman/ai)

## Sources

- alibaba/open-code-review: Read on October 28, 2026, at commit 375f64c (https://github.com/alibaba/open-code-review/tree/375f64cd6f67a48a135da83cfcf59c52669a09cb)
- JuliusBrussee/caveman: Read on October 29, 2026, at commit 9b68f7e (https://github.com/JuliusBrussee/caveman/tree/9b68f7ed12b05e7efaff18e65c5a3fc2849fd0a4)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.