ai-ml

Behavioral reliability under pressure. Test how LLMs behave when things get hard.

The fastest way to collect human preference data for LLMs

An integration package connecting Sarvam AI and LangChain.

Python package to allow easy integration to Neo4j's GraphRAG features

Asyncio Circuit Breaker pattern with optional Redis storage.

Python SDK for GateCtr — One gateway. Every LLM.

Monitor your Claude Code session context in real-time - track token usage and never run out of context

Neuro-inspired memory system for LLMs (server + Python SDK)

FlashInfer: Kernel Library for LLM Serving

Production-ready Telegram FAQ bot with Russian LLMs, RAG, and multi-provider fallback

Portable Claude Code workspace archives

A Python package for tuning vLLM hyperparameters.

Self-hosted semantic search and knowledge management for LLM-driven development

Atomic Model Fragmentation (AMF) - Universal LLM Decomposition Library

Backend.AI Storage Proxy

LangChain BaseTool for estimating and deploying NEAR smart contracts

Canonical result and measurement data storage APIs for Cogniflow

Realtime prediction using neuroglancer

growingnn is a cutting-edge Python package that introduces a dynamic neural network architecture learning algorithm. This innovative approach allows the neural network to adapt its structure during training, optimizing both weights and architecture. Leveraging a Stochastic Gradient Descent-based optimizer and guided Monte Carlo tree search, the package provides a powerful tool for enhancing model performance. Now with PyTorch support for enhanced performance and GPU acceleration!

Extract structured context from your git history — PR descriptions, standups, weekly reports, and LLM-ready JSON.