Stars
🚀 The fast, Pythonic way to build MCP servers and clients
llm-d is a Kubernetes-native high-performance distributed LLM inference framework
Using InstrucLab to train LLM to help migrations from Jenkins pipelines to Tekton pipelines.
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
In charge of the redirection to the cluster-specific Red Hat OpenShift Dev Spaces instance from workspaces.openshift.com
This kickstart will serve a small language model on CPUs, using vLLM inference runtime
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…
Collection of demos for building Llama Stack based apps on OpenShift
Famous Vision Language Models and Their Architectures
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of …
Source To Image (S2I) image for Red Hat OpenShift providing OpenJDK
Run Red Hat Developer Hub (RHDH) locally with Podman Compose or Docker Compose. Ideal to test software catalogs, techdocs, dynamic plugins, templates, homepage customizations, configurations and mo…
Discover, run, and compose AI agents from any framework.
Backstage Plugins Developed by TeraSky
Composable building blocks to build Llama Apps
The proxy server for AI-native apps. Arch handles the pesky low-level work in building agents like clariyfing vague user input, routing prompts to the right agents and unifying access to any LLM - …