A skill for Claude Code and other agent hosts that produces 39 editorial diagram types as self-contained HTML+SVG.
Graph-native Python library for building knowledge graphs from enterprise data with deterministic reasoning and decision provenance.
Collection of example Agent Skills that teach Claude specialized tasks, plus the Agent Skills specification and a starter template.
Python package for Needle 2, a tiny 45M-parameter model for tool calling, device use, and structured extraction, plus LoRA tuning.
Open source macOS dictation app that converts speech to text with on-device AI enhancement and voice command control.
Desktop app, web UI, and Python library for running, fine-tuning, and serving local AI models including LLMs and diffusion models.
All-in-one team workspace that unifies email, chat, docs, tasks, CRM, and AI agents with shared team-level memory in one interface.
OSINT tool that checks whether an email address is registered on Twitter, Instagram, and 120+ other sites via password-recovery functions.
Open source intelligence (OSINT) automation tool that integrates with many data sources and analyzes target data via web UI or CLI.
Routes each LLM call to the cheapest capable model via gateway plugins, an embeddable library, or a standalone proxy.
Local-first desktop workspace where AI agents run beside your apps, chat tools, and integrations, with shared memory and model choice.
A collection of Agent Skills that teach skills-compatible AI agents to create and edit Obsidian markdown, bases, canvas, and vault content.
A Python engine for precise programmatic animations, designed for creating explanatory math videos.
A curated collection of specialized AI agent personas that install into Claude Code, Cursor, Codex, and other agentic coding tools.
DiT-based foundation model that generates synchronized audio and video from text or image prompts, in fast and production-quality modes.
Desktop app that turns photos into 3D models using open source AI models running locally on your GPU.
Open-source RAG engine combining retrieval-augmented generation with agent capabilities to give LLMs a context layer over documents.