Mat Warger

codex-plugin-cc. Use Codex from Claude Code to review code or delegate tasks.

agent-native. A framework for building agent-native applications.

FluidVoice. Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a ton :) Windows & iOS waitlist open. Linux soon.

gh-signoff. Local CI. Sign off on your own work.

alchemy-effect. Infrastructure as Effects

adk-python. An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

skills. Skills for coding agents

ponytail. Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

reatom. Reatom - the ultimate state manager

verrex. an Effect-native UI framework where E/R channels survive to compile-time — forget a service Layer and it's a compile error that names it

knip. ✂️ Find unused files, dependencies and exports in your JavaScript and TypeScript projects. Knip it before you ship it!

effect-delta. Schema-derived, compositional patches for Effect

headroom. Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

stack. TypeScript

foldkit. TypeScript

agent-skills. Useful skills for agents and claws.

Shen-Backpressure. Go

theoria. Elixir-native proof and specification kernel inspired by Lean's trusted-kernel architecture.

source. Generate MSW request handlers from various sources (HAR files, OpenAPI documents, etc).

waza. CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness

ash_scim. A SCIM 2.0 extension for Ash, compatible with AshAuthentication

native. Toolkit for building native desktop apps

agent-scan. Security scanner for AI agents, MCP servers and agent skills.

greenfield. A Claude Code plugin that reverse-engineers clean behavioral specs, test vectors, and acceptance criteria from any codebase, producing a provenance trail so a fresh team can reimplement without inheriting the original's internal structure.

multica. The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

destructive_command_guard. The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

Archon. The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

better-github. github but better

ex_dna. Code duplication detector powered by Elixir AST analysis

ex_slop. Credo checks that catch AI-generated Elixir code slop

mechatron. Rewrite of robot-js

strongbox-cli. CLI tool for accessing strongbox-password-safe via afproxy protocol

iterative-development. Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

graphiti. Build Real-Time Knowledge Graphs for AI Agents

fallow. Codebase intelligence for TypeScript and JavaScript. Free static analysis of code and styles: unused code, duplication, circular deps, complexity hotspots, architecture boundaries, design-system drift. Optional paid runtime layer (Fallow Runtime): hot-path review and cold-path deletion evidence from real production traffic.

taste-skill. Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

swarm-forge. A simple tool for coordinating several AI agents.

volt. Elixir-native frontend build tool — dev server, HMR, and production builds for JavaScript, TypeScript, Vue SFCs, and CSS. No Node.js required.

CodexBar. Show usage stats for OpenAI Codex and Claude Code, without having to login.

loopndroll. Keep Codex running forever

uniwind. From the creators of Unistyles: The fastest Tailwind bindings for React Native

reach. Program dependence graph and architecture/code-flow analysis for BEAM projects

rslint. High-performance, ESLint-compatible linter for JavaScript and TypeScript.

sandcastle. Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()

hand-compute. Skill to force AI coding agents to walk system execution by hand, catching races and state bugs that abstract review would miss.

ghostty_ex. Terminal emulator library for the BEAM — libghostty-vt NIFs with OTP integration

react-big-calendar. gcal/outlook like calendar component

react-big-schedule. React Big Schedule is a powerful and intuitive scheduler and resource planning solution built with React.

just-bash. Bash for Agents

executor. The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure environment.

claude-elixir-phoenix. Claude Code plugin for Elixir/Phoenix/LiveView — 20 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

ash_storage. Attachment and file management for Ash Framework

mempalace. The best-benchmarked open-source AI memory system. And it's free.

antithesis-skills. AI Skills for Antithesis Users

openwhispr. Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

orca. Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop and mobile.

openscreen. Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

coding-interview-university. A complete computer science study plan to become a software engineer.

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

skills. Public repository for Agent Skills

create-context-graph. AI agents with graph based reasoning memory, scaffolded in seconds

pretext. Fast, accurate & comprehensive text measurement & layout

base-ui. Unstyled UI components for building accessible web apps and design systems. From the creators of Radix, Floating UI, and Material UI.

oh-my-claudecode. Teams-first Multi-agent orchestration for Claude Code

impeccable. The design language that makes your AI harness better at design.

scrap. Tool for assessing whether, where, and how speclj specs should be refactored.

cia. Manage background agents in your Elixir app

codex-review-skills.

elves. Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

cmuxlayer. cmux MCP server — 25 tools for terminal agent lifecycle management. Spawn, monitor, and orchestrate Claude, Codex, Cursor, Gemini, Kiro agents. Thinking-state detection, chunked input, layout management.

kong. 🦍 The API and AI Gateway

jido_symphony. Elixir

chrome-cdp-skill. Give your AI agent access to your live Chrome session — works out of the box, connects to tabs you already have open

skills. Skills for Real Engineers. Straight from my .claude directory.

drafter. An Elixir Terminal User Interface framework

crap4java. Crap analyzer for my java projects.

mutate4java. Mutation testing tool for my java projects.

mcporter. Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.

qmd. mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

OpenPackage. The open, universal, coding agent skills, agents, rules, and commands organizer and package manager.

autoresearch. AI agents running research on single-GPU nanochat training automatically

live_render. Server-driven generative UI for Phoenix LiveView

pi-autoresearch. Autonomous experiment loop extension for pi

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

openui. The Open Standard for Generative UI

cmux. Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

ouroboros. Agent OS: Stop prompting. Start specifying.

microgpt-ts. A complete GPT built from scratch in TypeScript with zero dependencies

rtk. CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

flue. The sandbox agent framework.

webview-bun. Bun bindings for webview, a tiny library for creating web-based desktop GUIs.

paperclip. The open-source app everyone uses to manage agents at work

symphony. Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

pinchtab. High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.

convexskills. AI agent skills and templates for building production ready apps with Convex. Patterns for queries, mutations, cron jobs, webhooks, migrations, and more.

convex-agent-plugins. An plugin for cursor to empower it to build the best apps ever.

opencode-worktree. Zero-friction git worktrees for OpenCode. Auto-spawns terminals, syncs files, cleans up on exit.

bowser. Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.

opencode-dcg-plugin. Destructive Command Guard (dcg) plugin for OpenCode - protects against dangerous commands

surf-cli. The CLI for AI agents to control Chrome. Zero config, agent-agnostic, battle-tested.

wasp. The batteries-included full-stack framework for the AI era. Develop JS/TS web apps (React, Node.js, and Prisma) using declarative code that abstracts away complex full-stack features like auth, background jobs, RPC, email sending, end-to-end type safety, single-command deployment, and more.

swarm-tools. 🐝 Multi-agent swarm coordination for OpenCode with learning capabilities, agent issue tracking, and management

overstory. Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more

axe-core. Accessibility engine for automated Web UI testing

peky. All your AI Agents like Claude Code, Codex CLI in a single TUI to keep things organized.

openclaw-studio. A clean web dashboard for OpenClaw. Connect your Gateway, manage agents, and ship faster. ⭐️ Star if you like it!

pyro_maniac. Declarative, framework-agnostic UI for Ash resources.

empire-2025. Clojure

disciplined-agentic-engineering. Acceptance Test Driven Development for Claude Code — inspired by Uncle Bob's approach from empire-2025

bombadil. Property-based testing for web and terminal UIs

shannon. Shannon is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

joelclaw. Personal AI operating system — blog, architecture decisions, and the journey from zero to a composable agent system.

adr-agent. Architecture Decision Record (ADR) agent

adr-skill. JavaScript

awesome-openclaw-skills. The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

agent-lightning. The absolute trainer to light up AI agents.

superpowers. An agentic skills framework & software development methodology that works.

stitch-skills. A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.

nact. nact ⇒ node.js + actors ⇒ your services have never been so µ

mobileapp. Kotlin

swarms. Multi-agent orchestration skills for Claude Code and Codex

dexter. An autonomous agent for deep financial research

MAHORAGA. autonomous trading agent powered by social sentiment analysis and ai that learns, grows, and adapts

omarchy. Beautiful, Modern & Opinionated Linux

CodexMonitor. An app to monitor the (Codex) situation

humanizer. Claude Code skill that removes signs of AI-generated writing from text

beans. A CLI-based, flat-file issue tracker for humans and robots. 🤖

alpaca-mcp-server. Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs

localstack. 💻 A fully functional local AWS cloud stack. Develop and test your cloud & Serverless apps offline

beads_viewer. Graph-aware TUI for the Beads issue tracker: PageRank, critical path, kanban, dependency DAG visualization, and robot-mode JSON API

compound-product. A self-improving product system that reads reports, identifies priorities, and autonomously implements fixes

CodexSkillManager. macOS app to manage your Codex skills

codex-ralph. Shell

docling. Get your documents ready for gen AI

ralph-tui. TypeScript

ratatui. A Rust crate for cooking up terminal user interfaces (TUIs) 👨‍🍳🐀 https://ratatui.rs

codex-1up. 🍄 Give your Codex CLI an extra life

codex-orchestrator. Delegate tasks to OpenAI Codex agents via tmux sessions. Designed for Claude Code orchestration.

wreckit. Wreck it Ralph Wiggum - My code is in danger!

humanlayer. The best way to get AI coding agents to solve hard problems in complex codebases.

the-augster. An 'additional system' prompt for the Augment Code extension in attempt to improve output quality.

ralphy. My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & Droid in a loop until your PRD is complete.

OpenSpec. Spec-driven development (SDD) for AI coding assistants.

ai-product-from-scratch. Build an AI communication analyzer from scratch to understand how AI products actually work. Learn prompt engineering, reasoning pipelines, and local LLM integration using Node.js - no frameworks, no abstractions, just fundamentals

json-render. The Generative UI framework

wreckit_rust. Wreckit - A Rust TUI application

ralph-playbook. A comprehensive guide to running autonomous AI coding loops using Geoff Huntley's Ralph methodology. View as formatted guide below 👇

how-to-ralph-wiggum. The Ralph Wiggum Technique—the AI development methodology that reduces software costs to less than a fast food worker's wage.

jido_ai. AI integration layer for Jido agents with LLM orchestration and reasoning strategies.

loom. if your name is not Geoffrey Huntley then do not use loom

claude-code-showcase. Comprehensive Claude Code project configuration example with hooks, skills, agents, commands, and GitHub Actions workflows

AppFactory. App Factory turns your ideas into real, working products. No coding experience required. Just describe what you want in plain English, and Claude builds it.

agent-browser. Browser automation CLI for AI agents

dekit. Run multiple commands in parallel

copilot-cli. GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.

ralph. A minimal, file‑based agent loop for autonomous coding.

accountability. TypeScript

rstack-examples. Examples of Rstack, including Rspack, Rsbuild, Rspress, Rsdoctor.

how-to-build-a-coding-agent. A workshop that teaches you how to build your own coding agent. Similar to Roo code, Cline, Amp, Cursor, Windsurf or OpenCode.

ai-agents-from-scratch. Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

playwriter. Chrome extension & CLI to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP

ash_jido. Compile-time bridge from Ash Framework resources to Jido Action modules

clawdinators. Declarative infra + NixOS modules for CLAWTINATOR hosts.

pdf-brain. 🧠 Local PDF knowledge base with vector search using libsql w/vectors

vibium. The verification layer for coding agents

gmcli. Minimal Gmail CLI

agentic_coding_flywheel_setup. Bootstraps a fresh Ubuntu VPS into a complete multi-agent AI development environment in 30 minutes: coding agents, session management, safety tools, and coordination infrastructure

vibe-kanban. Get 10X more out of Claude Code, Codex or any coding agent

gastown. Gas Town - multi-agent workspace manager

agent-scripts. Scripts for agents, shared between my repositories.

hyprwhspr. Native speech-to-text for Linux - Fast, accurate and private system-wide dictation

andy-timeline. The Andy Timeline: An AI assistant's origin story, told week by week

wallaby. Concurrent browser tests for your Elixir web apps.

summarize. Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.

BMAD-METHOD. Breakthrough Method for Agile Ai Driven Development

oracle. Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files.

ash_state_machine. The extension for building state machines with Ash resources.

tutorial-budget-app. A Phoenix Framework budget tracker, part of a tutorial series

isometric-city. IsoCity: City building simulation game.

chrome-devtools-mcp. Chrome DevTools for coding agents

dev-browser. A Claude Skill to give your agent the ability to use a web browser

bb. The resilient robotics framework

genui. Dart

nimble_publisher. A minimal filesystem-based publishing engine with Markdown support and code highlighting

toon. 🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

tidewave_app. Tidewave Desktop app and CLI

claude-code-infrastructure-showcase. Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents

helpcenter. A Helpcenter System Built in Elixir's Phoenix and Ash Frameworks

ecto. A toolkit for data mapping and language integrated query.

popcorn. Running Elixir in the browser

elixir_adoption. HTML

joken. Elixir JWT library

genserver_io. Online real-time games powered by Elixir, Phoenix, LiveView & GenServer

redoc. 📘 OpenAPI/Swagger-generated API Reference Documentation

beads. Beads - A memory upgrade for your coding agent

todoit. Elixir

waffle. Flexible file upload and attachment library for Elixir

req_llm. Composable Elixir library for LLM interactions built on Req and Finch

ash_ai. Structured outputs, vectorization and tool calling for your Ash application

phoenix_live_view. Rich, real-time user experiences with server-rendered HTML