Stars
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
Jupyter notebook server extension to proxy web services.
Community-maintained Kubernetes config and Helm chart for Langfuse
Open Source Identity and Access Management For Modern Applications and Services
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
PSDify: A PowerShell module for workspace management for Dify, featuring various cmdlets for managing Apps, Knowledges, Models, and Members, etc.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A high-throughput and memory-efficient inference and serving engine for LLMs
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
Gateway API Inference Extension
LeaderWorkerSet: An API for deploying a group of pods as a unit of replication
Kubernetes-based, scale-to-zero, request-driven compute
Achieve state of the art inference performance with modern accelerators on Kubernetes
Dify 1.0 Plugin Support MCP Tools Agent strategies
The official Python SDK for Model Context Protocol servers and clients
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
🚀 The fast, Pythonic way to build MCP servers and clients.
This code utilizes Dify's CONSOLE API to batch download DSL files for all apps within the dashboard.
Dynamically provisioning persistent local storage with Kubernetes
Production-ready platform for agentic workflow development.
Test suite for C/C++/Fortran compilers developed by Fujitsu