XorbitsAI builds production-ready infrastructure for Model Inference and AI Agents.
We focus on scalable model serving, agent orchestration, and intelligent system deployment — enabling teams to move from models to real-world AI systems.
Core Projects
xinference: a powerful and versatile library designed to serve language, speech recognition, and multimodal models.
xagent: Enterprise agent platform for building, deploying, and operating AI teammates.
xoscar: Python actor framework for heterogeneous computing.
Our Focus
We are building the next generation of AI infrastructure:
🔹 Scalable model inference
🔹 Agent orchestration & dynamic planning
🔹 Enterprise-ready deployment
🔹 Private & on-prem AI systems
From inference to intelligent agents — we help teams build real AI systems, not just demos.
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-re…
A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
xorbitsai/inference's past year of commit activity
You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.