Search

Reusable integration framework for external service connectors (shops, couriers, payments, messaging, storage)

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

A CrewAI tool for smart web scraping via the Browserless /smart-scrape API.

Claude Code client for Android/Termux with WebSocket server

Storage functionality for Mindtrace

CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation

CSCS HPC Storage proxy

A pipeline to align, quality control, and summarize tiled amplicon coverage (of a virus, probably) from sequencing reads.

A framework for storing and managing component and application data for machine apps.

Python library for standardization, optimization and monitoring of LLM API calls

Benchmark any LLM provider against your actual prompts — latency, cost, quality

An AI coding assistant using various LLM models.

mmore: Scalable multimodal document extraction pipeline for custom RAG integration.

AI blog generator with 7-pass pipeline, multi-LLM support, pluggable backends, humanizer, SEO analysis, and AI detection.

TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090

CircuitPython BlockDevice for USB mass storage devices

JTON (JSON Tabular Object Notation) — A Tabular JSON-Superset Encoding for Efficient LLM Data Processing

Carbon-aware scheduling and telemetry for LLM applications

beekeeper embeddings watsonx extension

beekeeper embeddings huggingface extension