Explore the directory

A full-featured, multi-workspace AI chat client with local-first storage, real-time cloud sync, a plugin system and MCP support, now deprecated in favor of a successor project.

• Inference

A macOS and Linux terminal UI for managing Ollama models, letting you list, inspect, sort, edit, run, unload, copy, rename, delete and push models with hotkeys.

• Inference
• Terminals

An AI-first design platform that supplies design skills, UI prompts and layout guidance to more than 20 AI coding tools through a hosted MCP server, so an assistant can generate more consistent user interfaces.

• MCP servers
• Design tools

A local-first personal AI assistant, small enough to read in an afternoon, built to show the four pillars behind a serious agent: harness, loop, memory and evaluation, with state kept in one SQLite file the user owns.

• Agent frameworks
• Agent memory

The first fully open-source generative-recommendation framework, providing an end-to-end pipeline of semantic ID construction, supervised fine-tuning and reinforcement learning, reproducing OneRec.

• Models

An Apple Silicon port of Karpathy's autoresearch project, running fixed-time autonomous training-experiment loops natively through MLX with no PyTorch or CUDA dependency.

• Agent frameworks
• Models

A hardware and configuration guide for running state-of-the-art large language models and speech-to-text locally, covering everything from a $2k single-GPU setup to a $40k multi-GPU rig.

• Inference
• Tutorials

An MCP server for Slack workspaces that can run with no configured permissions in a stealth mode or with OAuth tokens, supporting DMs, group DMs, GovSlack, smart history fetching and message search.

• MCP servers

A curated, code-analyzed index of open-source repositories that train LLM agents using reinforcement learning, organized by taxonomy such as base frameworks, search and RAG, web and GUI, tool use, and multi-agent RL.

• Curated lists

An open-source terminal coding agent powered by MiniMax models or a user's own model, that understands a project, makes changes and runs tests from the command line, with search, plugins and multimodal tools in the same workflow.

• Coding agents
• Terminals

A self-hosted Ruby on Rails web publishing platform built around a multi-user blogging engine, following IndieWeb principles of hosting and syndicating your own content.

• Backend

A unified MCP server for real-time search that supports general web search, search across specific domains such as finance, academic, security, legal and code, parallel batch queries, and full-page URL content extraction.

• MCP servers

A step-by-step guide and interactive notebook for building and scaling a retrieval-augmented generation LLM application for production, from ingesting documents through serving and evaluation.

• RAG
• Tutorials

An autonomous agent framework for Elixir that models agents as immutable state, actions that transform that state, signals that route events, and directives that describe effects for the runtime to execute.

• Agent frameworks

An 18-step, hands-on tutorial that walks through building a minimal AI agent from a simple chat loop up to an event-driven, multi-agent system with scheduling and long-term memory.

• Agent frameworks
• Tutorials

A tool that turns a folder of documents into a domain-expert training dataset and a fully fine-tuned custom LLM, optionally running entirely offline with no external API key.

• Models

A Core ML model zoo for iOS and macOS that packages PyTorch models converted into ready-to-use .mlpackage files, each with a conversion script and a SwiftUI sample app.

• Models
• Mobile

A free, 92-part Chinese-language tutorial series covering Claude Code and Codex CLI, fact-checked against each tool's official documentation from installation through advanced workflows.

• Tutorials

A Linux update agent for embedded systems that installs software to eMMC, SD, NAND or NOR flash over local media or OTA, with atomic fail-safe updates, delta updates and cryptographic signing.

• CI/CD

A GPU-accelerated reference architecture for building video analytics agents that search, summarize and answer questions over live or recorded video using vision-language and language models plus retrieval-augmented generation.

• Agent frameworks
• RAG

A bilingual and crosslingual embedding and reranker model pair for retrieval-augmented generation in English and Chinese, developed by NetEase Youdao and used in its own RAG products.

• RAG
• Models

An operational handbook and knowledge base for building, running and maturing a Security Operations Center or CSIRT, covering detection engineering, threat intelligence, SOC metrics, automation and incident-response playbooks.

• Security
• Curated lists

A 9B-parameter multimodal foundation model that pairs a Qwen3.5 language backbone with a vision encoder for general visual understanding, spatial reasoning and agentic tool use.

• Models

A macOS app for discovering, organizing and editing AI coding-agent skills and agents across tools such as Claude Code, Cursor, Codex, Windsurf and Amp.

• Agent skills