# gepa-ai/gepa SLOC report

> As of 2026-09-15 (commit 15ee314f9c7d), gepa-ai/gepa contains 48,145 total lines: 36,826 code, 4,440 comments, 6,879 blank, across 210 files in 9 languages (top: Python 97.3%). Custom configuration (tests excluded, docs excluded, generated excluded). Counted with tokei via OctoCounts.

gepa-ai/gepa has 36,826 source lines of code out of 48,145 total lines across 210 files, counted from the 15ee314f9c7d34ec153b809d401f42f55c4dcd76 ref at commit 15ee314f9c7d by the OctoCounts tokei engine on 2026-09-15. The report is cached by commit, tokei version, and analysis options, so recounting the same revision returns exactly these numbers.

OctoCounts produced this report by resolving gepa-ai/gepa to commit 15ee314f9c7d, downloading the repository source archive, and counting every source file with tokei, the open-source line counter written in Rust. The table below breaks the count down by programming language into files, total lines, code lines, comment lines, and blank lines, so the figures can be compared across languages and projects. Results are cached by commit, tokei version, and analysis options, so counting the same revision again reproduces exactly these numbers.

## Repository size insights

This is a medium-sized codebase by counted code lines. Code represents 76.5% of all lines, comments represent 9.2%, and the repository averages 175 code lines per file. Python accounts for 97.3% of counted code.

| Language | Files | Lines | Code | Comments | Blanks |
| --- | ---: | ---: | ---: | ---: | ---: |
| Python | 156 | 44,286 | 35,849 | 2,412 | 6,025 |
| JSON | 13 | 346 | 346 | 0 | 0 |
| YAML | 2 | 231 | 184 | 13 | 34 |
| Jupyter Notebooks | 2 | 240 | 176 | 41 | 23 |
| TOML | 1 | 162 | 132 | 16 | 14 |
| HTML | 1 | 92 | 88 | 0 | 4 |
| SVG | 3 | 64 | 51 | 11 | 2 |
| Markdown | 23 | 2,569 | 0 | 1,828 | 741 |
| Plain Text | 9 | 155 | 0 | 119 | 36 |

Top language (Python 97.3%). Generated at 2026-09-15T20:26:07.719011194+00:00. Canonical report: https://octocounts.com/github/gepa-ai/gepa

## Reproduce this report

[Reproduce this exact report and configuration](https://octocounts.com/github/gepa-ai/gepa/commit/15ee314f9c7d34ec153b809d401f42f55c4dcd76?analysis=%7B%22ignoredDirs%22%3A%5B%5D%2C%22ignoredLanguages%22%3A%5B%5D%2C%22profile%22%3A%22default%22%2C%22includeDocs%22%3Afalse%2C%22includeTests%22%3Afalse%2C%22includeGenerated%22%3Afalse%7D).

## Report FAQ

### How many lines of code does gepa-ai/gepa have?

gepa-ai/gepa has 48,145 total lines, including 36,826 code lines, 4,440 comment lines, and 6,879 blank lines.

### How was the gepa-ai/gepa line count measured?

OctoCounts resolved the public GitHub repository to commit 15ee314f9c7d, downloaded the source archive, counted it with tokei, and cached the report by commit, tokei version, and analysis options.

### What commit was counted for gepa-ai/gepa?

This OctoCounts report was generated from 15ee314f9c7d34ec153b809d401f42f55c4dcd76 at commit 15ee314f9c7d on 2026-09-15T20:26:07.719011194+00:00.

## Similar repository reports

- [google/agents-cli](https://octocounts.com/github/google/agents-cli) — Python, 35,436 code lines
- [ZSTDJan/windows-remote-mic-app](https://octocounts.com/github/ZSTDJan/windows-remote-mic-app) — Python, 38,370 code lines
- [RVC-Boss/GPT-SoVITS](https://octocounts.com/github/RVC-Boss/GPT-SoVITS) — Python, 38,981 code lines
- [MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark](https://octocounts.com/github/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark) — Python, 39,235 code lines
- [benji-carr/SPDCallDashboard](https://octocounts.com/github/benji-carr/SPDCallDashboard) — Python, 33,823 code lines
- [Yuan1z0825/nature-skills](https://octocounts.com/github/Yuan1z0825/nature-skills) — Python, 39,847 code lines

## Related OctoCounts pages

- [Recently analyzed repositories](https://octocounts.com/recent)
- [Popular SLOC reports](https://octocounts.com/popular)
- [Trending GitHub repositories](https://octocounts.com/trending)
- [Hall of Monoliths](https://octocounts.com/hall-of-monoliths)
- [TensorFlow vs PyTorch](https://octocounts.com/compare/tensorflow-vs-pytorch)
- [Django vs Ruby on Rails](https://octocounts.com/compare/django-vs-rails)
- [Laravel vs Django](https://octocounts.com/compare/laravel-vs-django)
- [GitHub SLOC counter guide](https://octocounts.com/docs/github-sloc-counter)
- [Counting methodology](https://octocounts.com/docs/methodology)
- [SLOC and code metrics glossary](https://octocounts.com/docs/glossary)
- [Original research: how filtering changes SLOC counts](https://octocounts.com/research)
- [OctoCounts API docs](https://octocounts.com/docs/api)