Kunpeng-Skill is a powerful multimodal distillation toolkit that transforms high-value insights from repositories, websites, UIs, videos, images, and documents into reusable methodologies, model-agnostic regeneration specifications, and more.

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift

Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.

Windows 11 shell extension (Rust): Explorer thumbnails for 331 file types Windows can't show, including camera RAW, PSD, HEIC/AVIF, video, ebooks, comics and CAD. Crash-isolated, source-available rebuild of SageThumbs.

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.

Omnia Vault - the all-in-one project brain: an Obsidian LLM wiki, Graphify code graphs, a living plan that triages new videos against itself, and a Claude Code ⇄ Codex relay. Everything your project knows, in one clonable vault.

Desktop AI Assistant powered by GPT-6, GPT-5, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants,and more. Linux, Windows, Mac

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.

lightweight Python-based MCP (Model Context Protocol) server for local ComfyUI

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

An MCP Multimodal AI Agent with eyes and ears!

All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine

A free Agent Skill for writing short-form hooks, scripts, and carousels for TikTok, Reels, and YouTube Shorts.

Professional cloud sync & VFS for Obsidian. Features zero-space VFS, 4K streaming, MCP AI engine, and P2P collaboration. Supports Baidu/Aliyun/Quark/WebDAV/S3.

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱