skypilot

The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

skypilot-org/skypilot

View on GitHub ↗

The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

skypilot grew +1.2% in the last 30 days, ranks 19th of 371 in Production Serving & Deployment, actively maintained, last commit today.

Star trajectory

135 days tracked
2026-07-0210.8k stars today2026-11-15
Momentum

+1.2% in 30d, below the Production Serving & Deployment median of +1.2%.

Maintenance

Last commit today, fresher than the median of 4d.

How it compares in Production Serving & Deployment

skypilot
10.8k
stars
+1.2% 30d
commit today
Production Serving & Deployment median
290
stars
+1.2% 30d
commit ~4d ago
Leader · vllm
96.9k
stars
+3.2% 30d
commit today

Ranked 19th of 371 by stars.

Ranked by shared tags, then keywords, then stars
  1. The Cloud Native AI Platform

    +55 (+0.3%) in 30d · Committed 45d ago · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference

  2. AgentENV (AENV) is a distributed platform for running agent environments at scale.

    +111 (+3.1%) in 30d · Committed yesterday · Rust · MIT

    Shares Distributed Inference, Production Serving & Deployment

  3. cubestudio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台,算法全链路流程,多租户,算力租赁平台,token中转,拖拉拽任务流pipeline编排,多机多卡分布式…

    +55 (+2.2%) in 30d · Committed 33d ago · Python · Other license

    Shares Production Serving & Deployment, Distributed Inference

  4. A unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run…

    +27 (+1.2%) in 30d · Committed yesterday · Python · MPL-2.0

    Shares Production Serving & Deployment, Distributed Inference

  5. High Performance Serving Runtime For Interactive Super Intelligence System

    +266 (+17%) in 30d · Committed today · Python · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference

  6. Agentic RL on Any Harness at Scale

    +19 (+2.2%) in 30d · Committed 2d ago · Python · Apache-2.0

    Shares Distributed Inference, Production Serving & Deployment

  7. GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over…

    -55 (-8.0%) in 30d · Committed 129d ago · Python · MIT

    Shares Distributed Inference, Production Serving & Deployment

  8. A high-performance inference system for large language models, designed for production environments.

    -1 (-0.2%) in 30d · Committed 331d ago · C++ · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference

  9. JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs…

    +4 (+0.9%) in 30d · Committed 313d ago · Python · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference

  10. llm-d Router: The intelligent entry point for inference requests

    +60 (+15%) in 30d · Committed yesterday · Go · Apache-2.0

    Shares Distributed Inference, Production Serving & Deployment

Language
Python
License
Apache License 2.0
Contributors
294
Forks
1.4k
Watchers
77
Open issues
152
Releases
47
Created
2021-08-11
Stars this week
+29

You've seen where skypilot stands today.

Get the moves before everyone else: the 5 Production Serving & Deployment repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain skypilot?

Claim this page to add your own call-to-action.

Claim this page