workflowstacks
ai-agent

Clipper: Ultra‑Fast Prediction Serving for Real‑Time Apps

Clipper delivers low‑latency, C++‑powered prediction serving so founders can scale real‑time AI features instantly. Backed by 1.4k+ GitHub stars, it’s built for performance‑critical startups.

From the repo · “A low-latency prediction-serving system”

1,421 stars+1★ this week278 forksC++Guide quality 8/10 · reviewed Oct 6Updated 4/26/2021100% free · open source
What it does

Clipper is a low-latency prediction-serving system that allows you to deploy and manage machine learning models for real-time predictions.

When to use it
  • •You need to deploy machine learning models for real-time predictions in your application
  • •You want to reduce the latency of your prediction-serving system
  • •You need to manage multiple machine learning models and versions in a scalable way
Ready-to-paste prompt
python -m clipper_admin deploy --name my_model --version 1 --input-type dob-double --output-type double my_model.py
Heads up: You need to have CMake and a C++ compiler installed on your system to build Clipper, and you need to have the necessary dependencies installed, such as OpenSSL and Boost
Saves to your device
Use with Claude
New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/clipper && curl -fsSL https://workflowstacks.com/api/skills/clipper/claude-skill -o ~/.claude/skills/clipper/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 Clipper: Ultra‑Fast Prediction Serving for Real‑Time Apps works
Codeflow
Free to inspect

Clipper: Ultra‑Fast Prediction Serving for Real‑Time Apps is a large C++ project (~40k lines across 217 code files, plus 26 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit 67 months ago, Apache-2.0 license, has a test suite.

Size
Large codebase
~40k lines · 217 code files · ~6 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
C++
No API keys detected
C++ 55%Python 26%CMake 9%Scala 3%Shell 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    bin/run_ci.sh
    Where the program starts running
  3. 3
    src/frontends/README.md
    Inside src/ — the main logic begins here
  4. 4
    examples/__init__.py
    A worked example — copy this to get going
What's in each folder
src/Core code — the actual logic93 files
bin/Command-line entry points19 files
examples/Examples you can copy32 files
containers/Folder117 files
clipper_admin/Folder61 files
dockerfiles/Folder29 files
integration-tests/Folder25 files
cmake/Folder15 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseLast update 67 mo ago
Quick Actions
Details
Creator
ucbrise
Language
C++
Category
ai-agent
Published
10/27/2016

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/clipper.svg)](https://workflowstacks.com/skills/clipper?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,974
superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 277,153
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, backed by 276k+ GitHub stars, ideal for founders.
ai-agent★ 253,255
Linux – 251k+ GitHub stars for building custom kernel solutions
Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.
ai-agent★ 30,125
jitsi-meet
Jitsi Meet - Secure, Simple and Scalable Video Conferences that you use as a standalone app or embed in your web application.
ai-agent★ 253
Hyperloom
An agentic system that auto-optimizes LLM workloads on AMD GPUs.
ai-agent★ 168,020
Transformers: Fast, Scalable ML Models for Text, Vision, Audio
Founders can deploy and train state‑of‑the‑art multimodal models with a single Python library, backed by 167k+ GitHub stars. Ideal for AI‑first startups.