workflowstacks
ai-agent

SGLang: Fast AI Deployments

Get high-performance AI serving with SGLang, a framework for large language models, ideal.
advanced⏱ 1-2 hours💵 Free + LLM API costs
33,697 stars8,505 forksPythonGuide quality 8/10Updated 9/3/2026100% free · open source
What it is

Serve large language models on your own infrastructure for efficient performance.

Real use case example

"A founder wants to generate product descriptions for new Amazon products automatically. They use SGLang to serve a GPT model, integrate it with an Amazon script, and set up a cron job to run daily. The founder now gets custom product descriptions every night without manual effort."

Best insideClaude DesktopCursorClaude CodeAntigravity
When to use it
  • •When you need to deploy large language models with high performance and low latency
  • •When you want to serve multimodal models that integrate text, images, and other data types
  • •When you need a scalable framework for serving AI models in a production environment
Ready-to-paste prompt
Use the `python examples/client.py --model-name my_model --input-text 'Hello World!'` command to test the server with a sample input
Heads up: Make sure you have the required GPU drivers and CUDA libraries installed, as SGLang relies on GPU acceleration for high-performance serving
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/sglang && curl -fsSL https://workflowstacks.com/api/skills/sglang/claude-skill -o ~/.claude/skills/sglang/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How SGLang: Fast AI Deployments works
Codeflow
Free to inspect

SGLang: Fast AI Deployments is a very large Python project (~1.5M lines across 4022 code files, plus 2625 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~1.5M lines · 4022 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Docker
No API keys detected
Python 85%Rust 7%Cuda 5%C++ 2%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    examples/assets/.gitignore
    A worked example — copy this to get going
What's in each folder
docs/Documentation504 files
examples/Examples you can copy96 files
python/Folder4523 files
sgl-model-gateway/Folder407 files
experimental/Folder160 files
scripts/Helper scripts156 files
benchmark/Evaluations & benchmarks122 files
rust/Folder92 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
sgl-project
Language
Python
Category
ai-agent
Published
1/8/2024

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 276,806
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, ideal.
ai-agent★ 264,191
Superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 244,424
Linux: Open Source Kernel
Get the Linux kernel source tree for custom development, ideal for startup founders in need of a flexible OS foundation
ai-agent★ 210,750
Vue
This is the repo for Vue 2. For Vue 3, go to https://github.com/vuejs/core
ai-agent★ 204,069
Improve Code with andrej-karpathy-skills
Get better code behavior with andrej-karpathy-skills, 165k+ GitHub stars, for founders using LLMs.
ai-agent★ 197,010
FreeDomain: Free Website Domain
Get a free domain with FreeDomain.