Llm Infrastructure Python Packages

context-compiler

Deterministic state engine for managing conversation state and constraints in LLM applications.

nvprobe

nvProbe - Open-source NVIDIA GPU benchmark suite for CUDA workload automation, Slurm HPC cluster profiling, and MLPerf reporting

context-compiler-directive-drafter

Draft candidate Context Compiler directives from natural-language input.

context-compiler-example-integrations

Example integrations and enforcement-point demonstrations for Context Compiler.

damper

Reliability control for the Anthropic Python SDK

getkora

AI Workload Control Layer for routing deterministic, reusable, retrieval-needed, tool-needed, and provider-needed work before model invocation.

dotprmpt

prmpt is a declarative, versioned behavioral contract that specifies how an LLM must be invoked, constrained, composed, and interpreted by the surrounding system in order to produce reproducible behavior.

pcmi

Persistent Cognitive Memory Infrastructure — durable, multi-tenant memory layer for AI agents. HTTP + gRPC, hybrid retrieval, background workers, observability. Go.