PyPI (Real-time)

A client to provide LLM responses for FutureHouse applications.

Lightweight AI prompt injection and system prompt leakage shield for LLM apps. Zero dependencies, works offline.

l4py is a Python library that simplifies logging configuration with features like JSON formatting, file rotation, and dynamic log levels via environment variables. It integrates seamlessly with Django and leverages the Python standard logging module for easy customization.

Nimbus AWS Security SDK — Bedrock RAG remediation and infrastructure provisioning

Python module to interact with Fragalysis

Model encryption and authorization extension for vLLM 0.17.0+ on Ascend NPU

Token budget and cost estimator for LLM prompts

lk_moe is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, supporting hybrid inference for MOE large models.

Auto-formatter for LLM prompt files

Machine-readable Django query profiling for LLMs, tests, and CI.

None

Test framework for LLM prompt files

This project contains standardized tools to use LLMs in research studies for improving patient care.

None