UltraRAG by OpenBMB

Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM. Maintained by katanaml on GitHub, where it has earned 5,188 stars from the community.

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances. Maintained by gpustack on GitHub, where it has earned 5,436 stars from the community.

Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop. Maintained by lemony-ai on GitHub, where it has earned 3,838 stars from the community.