Explore the directory

Vemto is an open-source desktop application that generates Laravel code, migrations, models, factories, seeders, CRUD and API code, from a visual, synchronized data-schema editor.

• Libraries

A Model Context Protocol server for long-term investors, providing stock fundamentals, historical prices, options data, market movers, an earnings calendar, the Fear & Greed index and technical indicators.

• MCP servers

An independent, evidence-backed guide to running large language models locally on AMD Strix Halo (Ryzen AI MAX+ 395) hardware, covering BIOS setup, Ollama, llama.cpp, ROCm and cross-vendor benchmarks.

• Books

A full training presentation and hands-on lab set for using Claude Code in professional software development, covering project creation, the branch-first workflow, subagents, hooks, skills and plugins.

• Tutorials

A set of SKILL.md files that teach AI coding assistants ROS1/ROS2 engineering practice — correct QoS, lifecycle nodes, launch files, Docker bringup and tests — instead of only ROS syntax.

• Agent skills

A managed retrieval-augmented-generation API server, built with FastAPI and LangChain, that exposes collections and documents over REST with PostgreSQL and pgvector for storage and vector search.

• RAG
• Databases

A curated, cross-platform catalog of plugins, skills, MCP servers, apps and agent tools for assistants such as Claude Code, Codex/ChatGPT, Gemini CLI, Antigravity, Grok and OpenCode.

• Curated lists

A weekly-updated, side-by-side guide to AI agent frameworks, tools and resources, paired with an interactive Next.js web app for searching and filtering agents, frameworks and infrastructure tools.

• Curated lists

A semantic search engine for competitive programming problems that simplifies each problem statement with an LLM, embeds it, and finds similar problems across roughly 255,000 indexed statements from vjudge and other sources.

• RAG

An MCP server exposing read-only Apache Doris capabilities to AI agents, organized as eight stable domains with fifty-five progressively disclosed child tools covering catalog, query, cluster, ingestion, search, governance and lakehouse operations.

• MCP servers
• Databases

A full-stack, async-first Python framework for building production AI agents, providing orchestration, tool execution, memory management, a secure code sandbox, a skills ecosystem and streaming in one OpenAI-compatible design.

• Agent frameworks

A Model Context Protocol server bridging MCP clients to Xero's accounting API, covering OAuth2 authentication, contacts, chart of accounts and invoice management.

• MCP servers

A customer-service demo built on LangChain and LangGraph that combines a ReAct reasoning loop, retrieval-augmented generation over a Chroma vector store, and multiple callable tools, shown through a Streamlit interface.

• RAG
• Tutorials

A CLI, local web and desktop AI agent product that runs entirely on the user's own machine, letting one person operate a team of specialist agent sessions with self-evolving skills.

• Coding agents

A demonstration-only, Google-published reference implementation of a customer-service agent for a fictional airline, using LangGraph, tools and retrieval-augmented generation to query Google Cloud databases through MCP Toolbox.

• Tutorials

A free, no-signup beginner's tutorial that builds a working AI agent — one that reasons, calls tools and loops until a task is done — using only free-tier APIs and local Python.

• Tutorials

A self-hosted AI gateway that connects files, databases, APIs and MCP tools to local or hosted models behind one OpenAI-compatible API, with authentication, observability and an admin UI.

• RAG
• LLM gateways

The code repository for a paid Udemy course on large language model internals, covering transformer architecture, tokenization, training, fine-tuning, inference and PyTorch implementations from scratch.

• Tutorials

A macOS menu bar and desktop app, with a new Windows Tauri build, that tracks OpenAI Codex and Claude Code quota windows, token usage, today's tasks and a locally computed AI usage score.

• Desktop utilities

An MLX extension for Apple Silicon that adds INT8/INT4 activation quantization and an optimized decode attention kernel to speed up LLM prefill and autoregressive decode on M5 Macs.

• Inference

A terminal coding agent with native adapters for 28 model providers, so it talks to each provider's API directly with no proxy layer in between.

• Coding agents

A family of small, on-device AI SDKs for Swift, Kotlin and JavaScript that run offline on a phone, Mac or browser tab, covering tasks such as PII redaction, emoji suggestion, speech enhancement and content tagging.

• Libraries

An MCP server exposing DeepSeek's V4.1 Flash API — text and visual chat, the Responses API, fill-in-the-middle completion, file uploads and model or balance lookups — as eleven tools.

• MCP servers

A cross-platform desktop app that runs Claude Code, Codex and other Agent Client Protocol-compatible agents side by side, with rich tool-call visualization, an integrated terminal, git and MCP server management.

• Coding agents