llm

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

A self-hosted web interface for interacting with large language models

A self-hosted AI inference engine for running large language models locally

An identity and single sign-on platform supporting modern auth protocols

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A toolkit for automating and estimating taxes using reproducible calculations

A minimal knowledge base for storing and organizing notes and text snippets

A straightforward method for training your LLM, from downloading data to generating text.

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.

A recommendation engine for Plex and *Arr libraries to suggest what to watch next