Art & Design

Azure SRE Agent — Skills, Hooks & Deployment Guide

React Full-Stack Pipeline — Claude Code Plugin: 20 skills, 6 agents, 26 trained libraries, 23 design system specs. Complete React dev lifecycle from brainstorming to deploy.

Battle-tested system for consistent, high-quality Claude Code sessions. Layered config, session continuity, decay prevention, skill-driven workflows.

Exercise: Build applications with GitHub Copilot agent mode

Flutter Ultra MCP plugin: 8 MCP servers + ultra_flutter Dart packages + skills, replacing marionette_mcp and dart mcp-server with full cross-platform Flutter automation for Claude Code.

NLP project in collaboration with WHO, covering an agent-agnostic localization skill.

🚀 Monitor and manage multi-agent workflows with the Gastown Viewer Intent dashboard, featuring real-time tracking and interactive visualizations.

Squid Mesh is a Jido-native durable workflow layer with a friendly Elixir DSL for human-in-the-loop and agentic workflows

Deterministic graph runtime for agent workflows in Swift. Same input, same output, every time — golden-testable, checkpoint-resumable, and built entirely on Swift concurrency.

Fluent DSL for building durable agentic workflows and ontologies in .NET.

No hype, just architecture. A technical deep-dive into the raw components of the AI revolution—from Large Language Models to Agentic workflows—analyzed through the lens of scalable system design.

Local control tower for orchestrating tmux-based AI agent workflows

Containerise the AECA agentic workflow system with a single command. Multi-phase CI/CD pipeline: validate, build wheel, generate Dockerfile & compose, build production image.

Flowise-based multi-agent AI orchestration system using RAG, OpenAI embeddings, FAISS vector search, and sequential agent workflows for retrieval-grounded content generation and enterprise AI pipeline design.

Local-first AI development platform — VS Code extension · CLI · Web UI. Multi-agent workflow: Planner→Writer→Reviewer→Tester. Proudly Made in Canada.

wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.

Recently updated agent-adjacent repository: stonefruit/Data2Evidence-coding-agent-tools.

MageLab CLI — LLM chat and agentic tool use from the terminal

A high-performance, content-addressed database designed for AI agent workflows with cryptographic proofs and immutable versioning.

My hands-on journey into Agentic AI: starting with simple OpenAI API connections and evolving into complex, multi-agent workflows using LangChain. Exploring, learning, and building one agent at a time

Desktop AI agent orchestration workspace built with Tauri, Rust, Svelte, and graph-based multi-agent workflows.

Agentic AI-based feedback analysis system that automatically processes app reviews and support emails, classifies issues using multi-agent workflows, generates structured tickets, tracks metrics, and provides a Streamlit dashboard — built fully in Python without any paid APIs.

Long-context briefing packs for AI agent workflows, designed for MiMo V2.5 scale

Manage AI agent workflows with a git-native issue tracker that uses JSONL files as the database, requiring no extra services or binaries.