Blueprint MCP is a Python MCP server that generates system diagrams from codebases asynchronously using Google’s Nano Banana Pro model, integrated with Arcade MCP and Cursor IDE.
personalized-podcast turns text or URLs into two-host AI podcast episodes using Claude Code for script writing and Fish Audio TTS for voice synthesis, all in a streamlined pipeline.
Meridian is a Claude Code plugin that solves session context loss in long AI coding sessions using lifecycle hooks and a persistent project workspace. Here’s how it works and how to get started.
Alpaca MCP Server v2 rewrites the official MCP server using FastMCP and OpenAPI tools, exposing Alpaca’s Trading API via MCP for AI clients with env-var config and toolset filtering.
unslop is a Python CLI tool that detects repetitive defaults in LLM outputs by empirical analysis, generating reusable anti-pattern profiles to improve prompt engineering.
A Python Playwright scraper automates Google Maps data extraction using XPath selectors. It reveals the real maintenance cost of brittle DOM scraping and dependency pinning.
hermes-hudui provides a TypeScript-based web UI to interact with the Hermes AI agent, offering real-time data visualization and control. Setup requires Python 3.11+, Node.js 18+, and a running Hermes agent.
Be More Agent is an offline-first conversational AI framework for Raspberry Pi, combining local LLM inference with hardware-aware audio resampling to handle ALSA quirks. Runs 100% locally.
ROMP evolves monocular multi-person 3D mesh recovery from single-frame regression to temporal tracking under dynamic cameras, packaged with ONNX acceleration and Docker support.
A-MEM is a Python agentic memory system that dynamically organizes LLM agent memories using semantic embeddings and automatic linking, inspired by Zettelkasten.
CrewAI is a Python framework for autonomous AI agents emphasizing speed, flexibility, and precise control through ‘Crews’ and ‘Flows’. It offers enterprise features for production-grade AI orchestration.
Explore a comprehensive LLM course with practical notebooks on fine-tuning (QLoRA, DPO), quantization (GPTQ), and tools like AutoEval and LazyMergekit. Ideal for aspiring LLM engineers.
Agno provides a minimal, production-ready Python framework for scalable agentic software with per-user isolation and native tracing in ~20 lines of code.
AIHawk offers an open-source AI agent that automates job applications. Its architecture balances open AI automation with the legal realities of third-party integrations.
This repo provides annotated PyTorch implementations of major deep learning papers with side-by-side explanations, aiding understanding and prototyping.
AutoScraper automates web scraping by learning extraction rules from sample data, avoiding manual CSS selectors. This Python tool eases scraping repetitive, similar web content.
Crawlee Python offers a dual approach to web scraping with lightweight HTML parsing and headless browser automation, balancing speed and interactivity for diverse scraping needs.
Microsoft’s “Generative AI for Beginners” offers 21 lessons with Python and TypeScript examples covering LLMs, prompt engineering, RAG, and AI app building.
face_recognition provides a simple Python API and CLI for highly accurate face detection and recognition using dlib’s deep learning model. It supports facial landmarks and multi-core processing.
HelloGitHub curates entry-level open source projects monthly, fostering community engagement through human curation rather than code complexity. Here’s how it works.
