Forkcast Monthly #1: superpowers, ECC, andrej-karpathy-skills, markitdown, claude-code, skills, bun

Episode Summary#

The first Forkcast Monthly roundup covers the biggest open-source projects from May 2026. The episode highlights the Superpowers agentic skills framework that has reached 200K+ stars, ECC’s performance optimization harness for AI coding agents, and Andrej Karpathy’s influential skills file that enforces structured thinking before coding. Also featured are Microsoft’s MarkItDown file converter, Anthropic’s Claude Code CLI, Matt Pocock’s engineering skills collection, and the Oven-sh Bun JavaScript runtime.

Repositories Covered#

superpowers#

An agentic skills framework and software development methodology that enforces TDD, spec-first workflows, git worktree isolation, and two-stage code review. With 200K+ stars, it defines how AI coding agents should work reliably across Claude Code, Codex, Cursor, and more.

ECC#

A performance optimization framework that layers skills, instincts, memory, and security modules on top of AI coding agents. Delivers 25-33% speed improvements and 150% better context utilization.

andrej-karpathy-skills#

A Claude Code plugin implementing four principles from Andrej Karpathy’s LLM coding observations: think before coding, simplicity first, surgical changes, and goal-driven execution. Forces the agent to state assumptions and define success criteria before writing code.

markitdown#

Microsoft’s open-source utility that converts various file formats (Office documents, PDFs, images, HTML, and more) into clean Markdown. An essential tool for feeding diverse document types into LLM pipelines and RAG systems.

claude-code#

Anthropic’s official CLI tool for AI-assisted coding. Provides an agentic coding experience directly in the terminal with file editing, shell command execution, git integration, and extensibility through skills, hooks, and MCP servers.

skills#

A collection of production-grade engineering skills for AI coding agents by Matt Pocock. Provides structured, reusable capability files that make agents more reliable at TypeScript, testing, and general software engineering tasks.

bun#

A fast all-in-one JavaScript runtime, bundler, test runner, and package manager written in Zig. Designed as a drop-in replacement for Node.js with significantly faster startup times, lower memory usage, and native TypeScript support.

TradingAgents#

A multi-agent LLM financial trading framework that simulates how a real trading firm operates. Multiple specialized agents collaborate on the full pipeline from data collection to strategy generation, supporting multiple model providers and simulated execution for strategy validation.

MoneyPrinterTurbo#

An AI-powered tool that generates high-definition short videos with a single click. Supports Web UI, API, and batch generation with subtitle and music management, compatible with multiple LLMs for automated video content creation.

RuView#

A Rust-based code review tool that provides structured, automated review of pull requests with custom rule sets. Helps teams maintain code quality standards consistently across their codebase.

ruflo#

A leading agent orchestration platform for Claude that deploys intelligent multi-agent clusters. Coordinates autonomous workflows with enterprise-grade architecture, self-learning swarm intelligence, and RAG integration for building conversational AI systems.

hello-agents#

A comprehensive Chinese-language tutorial series from DataWhale that teaches how to build AI agents from scratch. Covers agent architecture, tool use, memory systems, and multi-agent orchestration with hands-on examples. The most popular AI agent learning resource on GitHub.

twenty#

An open-source, community-driven modern CRM designed as an alternative to Salesforce. Built for AI integration with customizable objects, views, and automations. Uses React, NestJS, GraphQL, and PostgreSQL for a full-stack TypeScript architecture.

agent-skills#

A production-grade engineering skills library for AI coding agents by Addy Osmani. Standardizes engineering practices and quality gates to make agents more professional and reliable across various development workflows.

Understand-Anything#

The #1 trending GitHub project that transforms any codebase into an interactive, searchable, Q&A-ready knowledge graph. Built with TypeScript, it integrates with every major AI coding agent and makes legacy code instantly understandable.

cal.diy#

Fully open-source, MIT-licensed scheduling infrastructure — the community fork of Cal.com without enterprise features.

chrome-devtools-mcp#

AI coding agents can write code but can’t see what happens in the browser — they’re blind to layout bugs, console errors, network failures, and performance issues 42+ tools across 10+ categories (input, navigation, debugging, performance, network, memory, extensions, emulation), built on Puppeteer, 47 releases, 829 commits, v0.25.0 (May 2026), integrates with 19+ MCP clients (Claude Code, Cursor, Copilot, Gemini CLI, Windsurf, etc.), Chrome 144+ for auto-connect, Node.js 20.19+, Apache 2.0

CLI-Anything#

Auto-generates command-line interfaces for any software, making it controllable by AI agents.

CodeWhale#

An open-source terminal coding agent that pairs DeepSeek V4 with Xiaomi MiMo models using a harness system of rules, evidence, and feedback to keep models oriented instead of drifting during complex coding tasks.

UI-TARS-desktop#

ByteDance’s open-source multimodal AI agent that automates GUI interactions — it sees the screen, controls the mouse, and operates browsers and desktop applications. Features MCP tool integration and a vision-language model for understanding UI elements.

codegraph#

A pre-indexed code knowledge graph for Claude Code, Codex, Cursor, and OpenCode. Provides local semantic indexing and graph traversal that dramatically reduces file scanning and tool calls across large multi-language codebases.

maigret#

Manually searching for a person’s accounts across hundreds of websites is tedious — there’s no unified way to cross-reference usernames. 3,000+ sites (default 500 highest-ranked), recursive search using discovered usernames, Tor/I2P support, AI analysis via OpenAI API, 8 output formats (HTML, PDF, XMind, JSON, D3 graph), 7 install methods, 1,300 commits.

openhuman#

A local-first personal AI assistant with memory tree, Obsidian wiki integration, 118+ third-party integrations, and TokenJuice compression. Runs with Rust, React, and Tauri for a native desktop experience.

taste-skill#

A composable frontend skill set that gives AI agents better design taste. Stops agents from generating boring, generic UI by applying adjustable design dials for layout, motion depth, and information density. Supports Codex, Cursor, and Claude Code.

financial-services#

Anthropic’s official toolkit and reference implementation for building AI applications in the financial services domain. Provides domain-specific patterns, compliance-aware workflows, and integration blueprints for banking, insurance, and fintech use cases.

claude-plugins-official#

Anthropic’s official plugin registry for Claude Code. Standardizes plugin structure with three extension mechanisms — Skills, Commands, and MCP Servers — including 30+ first-party plugins for LSP support, PR review, and code quality.

dexter#

Deep financial research requires hours of manually sifting through data, filings, and cross-referencing information. 6 LLM providers, 3 data sources (Financial Datasets API with income/balance/cash flow statements, Exa, Tavily), self-validation with loop detection, WhatsApp integration, Bun runtime, LangSmith-based eval.

scientific-agent-skills#

A collection of specialized AI agent skills for scientific research workflows. Covers literature review, citation graph analysis, peer review simulation, and methodology validation to accelerate academic and research processes.

ai-engineering-from-scratch#

A free, open-source curriculum with 503 lessons across 20 phases that teaches AI engineering from math foundations through production systems. Every lesson ships a reusable artifact — a prompt, a skill, an agent, or an MCP server.

academic-research-skills#

A comprehensive suite of Claude Code skills for the full academic research pipeline. Handles literature review, citation formatting, data verification, and logical consistency checking while keeping the human researcher in the loop.

CloakBrowser#

Every web scraper eventually hits Cloudflare, reCAPTCHA, or fingerprinting. Stock Playwright scores 0.1 on reCAPTCHA v3 — instantly flagged as a bot. 57 C++ source-level fingerprint patches (not JS injection). reCAPTCHA v3 score: 0.9 (human-level) vs Playwright’s 0.1. Cloudflare Turnstile: PASS. FingerprintJS: PASS. BrowserScan: NORMAL (4/4 checks). bot.incolumitas.com: 1 fail vs Playwright’s 13 fails. 30+ detection sites tested. navigator.webdriver: false (source-level patch). Humanize mode: Bezier mouse curves, per-character typing delays, realistic scroll acceleration. ~190MB RAM idle, ~280MB with 3 tabs. Drop-in Playwright replacement. Cross-platform: Linux, macOS, Windows. MIT wrapper + proprietary binary.

hysteria#

Standard VPN protocols get throttled or blocked on restricted networks. TCP-based proxies choke on lossy connections with 5%+ packet loss, making them unusable in many regions. Customized QUIC protocol designed for unreliable and lossy networks. Traffic masquerades as standard HTTP/3 to evade censorship without collateral damage. Proxy modes: SOCKS5, HTTP Proxy, TCP/UDP Forwarding, Linux TProxy, TUN. Builds for every major platform and architecture. v2.9.1 released May 10, 2026. 81 releases, 1,310 commits. MIT licensed. Legacy v1 maintained separately. Custom authentication, traffic statistics, access control.

agentmemory#

A persistent memory system for AI coding agents that maintains context across sessions. Works with Claude Code, Codex, Cursor, and Copilot without client-specific dependencies.

compound-engineering-plugin#

The official Compound Engineering plugin for AI coding assistants like Claude Code, Cursor, and Codex. Provides AI skills and agents that make each unit of engineering work easier through structured planning, execution, review, and knowledge capture.

knowledge-work-plugins#

Anthropic’s official open-source repository of plugins for knowledge workers. Covers sales, customer support, product, marketing, legal, finance, and data roles. Sets the standard for plugin structure — naming, permissions, and README conventions for the ecosystem.

Watch#

• Video: https://www.youtube.com/watch?v=5YtUHAjaqVk
• Cover: https://i.ytimg.com/vi/5YtUHAjaqVk/hqdefault.jpg

Notes#

Transcript and notes will be added from Forkcast output artifacts.