ai-ml

LiteLLM provider for exoclaw

Development workflow toolkit for Claude Code with issue management, code quality commands, and automated processing

A modern RAG ingestion pipeline from Nvidia

Claude Automatic Optimizer — wraps PyTorch optimizers and consults Claude to tune hyperparameters

Geometric OOD detection for LLM hidden states

Full-stack Python + React framework for building applications with workflows, tables, UIs, and LLM integration.

FastHTML source selection component for transcript decomposition workflows, with federated database browsing, drag-drop ordering, and keyboard navigation.

Lean security proxy for AI coding tools — scan and redact secrets before they reach LLM APIs

Python SDK for Anthropic, OpenAI, and MiniMax AI providers

A tool to generate commit messages using OpenAI models.

A shell-based kanban task manager with NDJSON storage and high-performance search

Enrollment prediction pipeline: data loading, feature engineering, and LightGBM model helpers.

Automated LLM layer duplication configuration scanner with heatmap visualization

Virtual Meshtastic node using mudp transport and meshdb storage.

LLMNR/NBT-NS/mDNS Poisoner and rogue service provider

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