Source: https://seerepo.com/compare/OpenPipe/ART/vs/sgl-project/sglang
Markdown source: https://seerepo.com/compare/OpenPipe/ART/vs/sgl-project/sglang.md
Description: ART and sglang share 12 technologies: FastAPI, OpenAI, Anthropic, AIOHTTP, apache-tvm-ffi, flashinfer-python, NVIDIA, quack-kernels, torch, transformers, Pydantic, and msgspec. Both are written in Python.

# ART vs sglang

ART and sglang share 12 technologies: FastAPI, OpenAI, Anthropic, AIOHTTP, apache-tvm-ffi, flashinfer-python, NVIDIA, quack-kernels, torch, transformers, Pydantic, and msgspec. Both are written in Python.

- [OpenPipe/ART](https://seerepo.com/r/OpenPipe/ART): Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
- [sgl-project/sglang](https://seerepo.com/r/sgl-project/sglang): SGLang is a high-performance serving framework for large language models and multimodal models.

## What they share and what sets them apart

- In common: FastAPI, OpenAI, Anthropic, AIOHTTP, apache-tvm-ffi, flashinfer-python, NVIDIA, quack-kernels, torch, transformers, Pydantic, msgspec
- Only in ART: weave, causal-conv1d, flash-attn-4, flash-linear-attention, megatron-core, ml-dtypes, torchtune, unsloth-zoo, litellm, peft
- Only in sglang: axum, tower, uvicorn, axum-server, pyzmq, blobfile, Redis, Tokio, wasmtime, indicatif, jsonwebtoken, cuda-python, humming-kernels, openai-harmony, torch-c-dlpack-ext, einops, torchvision, compressed-tensors, gguf, tokenizers, xgrammar, ModelScope, tch, torchaudio, hf-hub, partial-json-parser, datasets, mistral-common, tiktoken, llguidance, rmcp, sentencepiece, timm, pillow, minijinja, av, torchcodec, image, validator, tracing, psutil, prometheus-client, tracing-subscriber, k8s-openapi, kube, metrics, tracing-appender, metrics-exporter-prometheus, OpenTelemetry, opentelemetry-otlp, tracing-log, tracing-opentelemetry

## Side by side

| | ART | sglang |
|---|---|---|
| Size | 345,462 lines written, 415 code files | 3,312,331 lines written, 4,627 code files |
| Who writes it | 6.6% of its commits signed by AI. With Claude Code, Cursor, Codex, and Amp | 8.7% of its commits signed by AI. With Claude Code, Gemini CLI, Cursor, GitHub Copilot, Devin, Codex, CodeRabbit, and OpenHands |
| Activity | Last push November 10, 2026, 1,465 commits, 10,856 stars | Last push November 6, 2026, 21,830 commits, 38,542 stars |
| Tests | 391 test files. 49.2% of its code files have a test that imports them | 4,212 test files. 59.6% 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, ART or sglang?

sglang, with 3,312,331 lines written; ART has 345,462.

The proof: [sgl-project/sglang's code at commit 0afb736](https://github.com/sgl-project/sglang/tree/0afb736d0aab96e3ab80b4c54a376213a1db67a6)

### Which has more GitHub stars, ART or sglang?

sglang, with 38,542 stars; ART has 10,856.

The proof: [sgl-project/sglang on GitHub](https://github.com/sgl-project/sglang)

### Which has more tests, ART or sglang?

sglang, with 4,212 test files; ART has 391.

The proof: [sgl-project/sglang's code at commit 0afb736](https://github.com/sgl-project/sglang/tree/0afb736d0aab96e3ab80b4c54a376213a1db67a6)

### Which was updated more recently, ART or sglang?

ART: its last push was on November 10, 2026, and sglang's on November 6, 2026.

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

### Which has more commits signed by AI, ART or sglang?

sglang: an AI signed 8.7% of its commits, with Claude Code, Gemini CLI, Cursor, GitHub Copilot, Devin, Codex, CodeRabbit, and OpenHands; in ART, 6.6%.

The proof: [the commits each tool signed in sgl-project/sglang](https://seerepo.com/r/sgl-project/sglang/ai)

## Sources

- OpenPipe/ART: Read on November 13, 2026, at commit 534620a (https://github.com/OpenPipe/ART/tree/534620a41b82ed89667f4642cc0b8e1d00e2269b)
- sgl-project/sglang: Read on November 6, 2026, at commit 0afb736 (https://github.com/sgl-project/sglang/tree/0afb736d0aab96e3ab80b4c54a376213a1db67a6)

## 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.