Explore the directory

A training toolkit for fine-tuning large language models locally on Apple Silicon with MLX, supporting LoRA, DoRA, full-precision and quantized training across many preference-optimization algorithms.

• Models

A Docker Compose setup that lets Intel Arc GPU owners run Ollama, Stable Diffusion and Whisper speech recognition together behind Open WebUI, using a native SYCL or Vulkan llama.cpp backend for Ollama.

• Inference
• Containers

Open-source voice typing for Windows: press a shortcut, speak, and AI-cleaned-up text is inserted at the cursor, using local models, the user's own API keys, or a self-hosted backend.

• Speech

A LoRA and fine-tuning studio for image and video generation models such as Flux 2 Klein, Krea 2, MiniMax H3 and Qwen Image, covering training, repair and remixing on consumer GPUs down to 16 GB.

• Generative media

A curated, actively updated archive of research paper reviews toward artificial general intelligence, organized around agents, architecture, training, evaluation, RAG and knowledge, and on-device AI.

• Papers

An agentic workflow framework and hosted codebase-maintainer agent that turns issues into reviewed, tested changes and keeps a project's wiki current, with workflows defined as TypeScript configuration files.

• Coding agents
• Agent frameworks

The user-facing web frontend for the RuoYi-AI platform, providing AI conversations, agent interactions and knowledge-base question answering, built with Vue 3 and Ant Design Vue.

• Inference

A local codebase index that lets AI coding agents search instead of re-reading files, cutting input tokens by a reproducibly benchmarked 94 percent across Claude Code, Codex, Copilot, Cursor and Gemini CLI.

• Agent memory

Qdrant web-ui is a self-hosted web interface for viewing and managing collections in the Qdrant vector search engine, comparable to Kibana for Elasticsearch, with no additional services required.

• Databases

An AI coding assistant that understands a whole project's context and autonomously calls tools to complete complex development tasks, positioned as an alternative to Claude Code and Codex.

• Coding agents

A family of open-source large language models tuned to better understand Southeast Asia's diverse languages and cultures, developed by AI Singapore's Products Pillar.

• Models

A single-file, zero-dependency AI agent for Linux and Windows operations that only needs Python and an API key, with directory-scoped sessions and a safety check before running anything beyond read commands.

• Coding agents

monday.com's official framework connecting AI agents into its work platform, giving them structured access to boards, tasks and automations through a Model Context Protocol server and an agent toolkit.

• MCP servers

An Android app that runs Gemma, Qwen and LLaMA language models entirely on the phone for offline, private chat, including voice input, image input with OCR and camera-based prompting.

• Inference

A self-hosted, privacy-first personal AI assistant platform with autonomous agents, multi-provider model routing, voice and browser automation, IoT device control, and Telegram and WhatsApp connectivity.

• Agent frameworks

A full-stack generative AI library built on Hono and Jsonnet, treating prompt and chain management as a configuration-management problem rather than a UI or library design problem.

• Agent frameworks

Antfly is a search-and-inference database written in Zig that combines full-text, dense, sparse and late-interaction vector search with graph traversal in one engine, running the models that chunk, embed, rerank and extract data inside the process.

• RAG
• Databases

An in-progress Chinese-language technical book about industrial recommendation-system architecture and algorithms, covering the pipeline from recall through ranking, mixing and generative recommendation, for engineers with a machine-learning background.

• Books

The production Python client for building AI applications on Redis, covering vector index management, hybrid vector and full-text search, semantic caching, and an MCP server for exposing Redis indexes to AI clients.

• RAG
• Databases

A self-hosted project management and issue tracker with customizable Kanban boards, calendar and sticky-note views, real-time collaboration, and MCP-based automation for AI agents.

• MCP servers
• Workflow automation

A set of AI agent skill definitions that teach coding assistants to search, chat with and register agents in the Universal Agentic Registry, a directory of more than 72,000 agents across 14 or more protocols.

• Agent skills

A lightweight, modular, Kubernetes-native platform for deploying and serving large language models, separating model lifecycle management from inference traffic routing behind custom resource definitions.

• Inference
• Containers

A portable semantic memory layer for AI agents that gives them durable context across sessions, available as a managed hosted service, a self-hosted open-source core, a TypeScript SDK or an MCP server.

• Agent memory

A Model Context Protocol server that gives AI agents full access to Trello boards, including workflow-level tools such as acceptance-criteria extraction and checklist dependency queries that a plain API wrapper does not provide.

• MCP servers