# langchain-ai/deepagents SLOC report

> As of 2026-09-20 (commit c3a041e3d8f5), langchain-ai/deepagents contains 304,466 total lines: 244,556 code, 27,356 comments, 32,554 blank, across 791 files in 12 languages (top: Python 96.1%). Custom configuration (tests excluded, docs excluded, generated excluded). Counted with tokei via OctoCounts.

langchain-ai/deepagents has 244,556 source lines of code out of 304,466 total lines across 791 files, counted from the main ref at commit c3a041e3d8f5 by the OctoCounts tokei engine on 2026-09-20. 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 langchain-ai/deepagents to commit c3a041e3d8f5, 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 large codebase by counted code lines. Code represents 80.3% of all lines, comments represent 9.0%, and the repository averages 309 code lines per file. Python accounts for 96.1% of counted code.

| Language | Files | Lines | Code | Comments | Blanks |
| --- | ---: | ---: | ---: | ---: | ---: |
| Python | 467 | 275,701 | 235,071 | 13,715 | 26,915 |
| Shell | 36 | 4,061 | 2,569 | 1,305 | 187 |
| JSON | 14 | 2,262 | 2,262 | 0 | 0 |
| TOML | 50 | 2,445 | 1,930 | 214 | 301 |
| JavaScript | 2 | 1,046 | 958 | 2 | 86 |
| Makefile | 11 | 917 | 591 | 116 | 210 |
| YAML | 3 | 592 | 515 | 42 | 35 |
| SVG | 5 | 316 | 295 | 9 | 12 |
| Dockerfile | 33 | 477 | 255 | 143 | 79 |
| Jupyter Notebooks | 1 | 135 | 61 | 50 | 24 |
| Templ | 2 | 49 | 49 | 0 | 0 |
| Markdown | 167 | 16,465 | 0 | 11,760 | 4,705 |

Top language (Python 96.1%). Generated at 2026-09-20T00:04:18.091148073+00:00. Canonical report: https://octocounts.com/github/langchain-ai/deepagents

## Reproduce this report

[Reproduce this exact report and configuration](https://octocounts.com/github/langchain-ai/deepagents/commit/c3a041e3d8f593e4e4c9bfc273d52264ceff165b?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 langchain-ai/deepagents have?

langchain-ai/deepagents has 304,466 total lines, including 244,556 code lines, 27,356 comment lines, and 32,554 blank lines.

### How was the langchain-ai/deepagents line count measured?

OctoCounts resolved the public GitHub repository to commit c3a041e3d8f5, downloaded the source archive, counted it with tokei, and cached the report by commit, tokei version, and analysis options.

### What commit was counted for langchain-ai/deepagents?

This OctoCounts report was generated from main at commit c3a041e3d8f5 on 2026-09-20T00:04:18.091148073+00:00.

## Similar repository reports

- [topoteretes/cognee](https://octocounts.com/github/topoteretes/cognee) — Python, 244,313 code lines
- [python/mypy](https://octocounts.com/github/python/mypy) — Python, 243,223 code lines
- [ZhuLinsen/daily_stock_analysis](https://octocounts.com/github/ZhuLinsen/daily_stock_analysis) — Python, 255,502 code lines
- [K-Dense-AI/scientific-agent-skills](https://octocounts.com/github/K-Dense-AI/scientific-agent-skills) — Python, 233,598 code lines
- [experientiallabs/experiential](https://octocounts.com/github/experientiallabs/experiential) — Python, 255,796 code lines
- [matplotlib/matplotlib](https://octocounts.com/github/matplotlib/matplotlib) — Python, 256,762 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)