Projects & Contributions

One surface for todos, team projects, CI/CD, bug tracking, monitoring, docs, and OKR-driven planning — with AI agents as teammates.

A living wiki for novels, campaigns, and game lore — define canon, generate with citations, catch contradictions.

Study tracks for builders — product how-tos, developer tools, and engineering subjects, or generate paths from your own knowledge base.

3D UML modeling studio in the browser — model, connect, and export software architecture. No install.

Behavioral testing for AI agents — script conversations as directed graphs, judge every turn, catch regressions before your users do.

MCP-native work infrastructure for AI agents — artifacts, tickets, sessions, wiki, chat, review, and memory that outlive any one conversation.

Know where the hours go — timer and timesheet.

Premium scheduling at an honest price — $2.95/mo.

Graph, program, and solve on Mac.

A directory for a web worth reading.

Graph-augmented memory for agents — retrieval that finds what is connected, not just what is similar.

A social platform where agents and humans share and discuss versioned prompts, skills, and agent configs.

Wire a neural-net fighter, train its decision graph, and battle in ranked PvP — mobile game.

Keep the vibe, learn the why — turn the code you build with AI into knowledge that sticks.

A free text RPG built for screen readers, with AI-driven narrative and a physics engine.

A calm river of saved links.

Model Context Protocol SDK for Elixir (hex noizu_mcp). Servers and clients, compile-time tool schemas, stdio and Streamable HTTP. Not a JSON-RPC wrapper.

Multi-model/provider client for running inference against various LLMs (hex genai). Handles API inconsistencies between models, allows replay of chat threads (including tool calls) against various providers. Future work includes a grid optimizer for tuning prompts, models, and hyperparams.

llama.cpp NIF extensions (via Rustler) for in-process GGUF inference from Elixir (hex ex_llama ~> 0.2.3). Alpha. Chat templates currently default to Zephyr unless you pass meta[:template].

Robust Elixir client for OpenAI endpoints. More feature-complete than the GenAI client for OpenAI-specific work: fine tuning, audio, threads, assistants, and more.

Elixir macros for creating and querying Weaviate vector database records. Define schemas with a DSL and interact with the Weaviate API using native Elixir structs.

Conventions and system prompts for improving predictability of model output and behavior, with a focus on middleware system reliability. Defines in-fill syntax, agent definitions, clip continuations, and more.

Framework for composing multi-model/multi-agent/multi-channel virtual workgroups. Detailed architecture and documentation for multi-agent collaboration.

Advanced implementation of multi-agent systems. Further along in implementation compared to NoizuTeams with more complete logic setup.

SMart As Hell - Command line GPT tool for Linux servers. Creates user profiles with system metadata and experience level for contextualized assistance. Predated Microsoft and Anthropic's similar solutions.

Thoughts on composable AI systems, arrow of time/time decay activator functions, and a draft paper on dynamic runtime model tuning via additional QLora input nodes.

PHP library for fragmented key cache management. Efficiently handles cache invalidation across complex dependency graphs.

Java port of the FragmentedKeys library for managing cache key dependencies.

Implementation of fragmented keys for managing data stored across various iOS cache providers.

Protocols for DB/Config driven runtime rule engines. Great candidate for hooking operations to GenAI and other models to drive runtime behavior.

Scaffolding for managing domain objects and repositories with consistent patterns.

Scaffolding for managing large pools of long-lived working processes with built-in health monitoring.

Base records and protocols that drive other Noizu scaffolding libraries.

Domain-driven design objects for PHP applications.

A museum of the language spec — historical PHP BDD-style testing archive. Gherkin/Cucumber-style PHPUnit extension that routes BDD lines to handler methods.

Semantic markup that reads three ways: a styled page, structured records for a language model, and annotated terminal text. One standalone HTML file, no build step.

Library for defining reusable custom asserts for partially comparing objects, including verification that values are within or outside of specified ranges.

Embedded C streaming parser that tokenizes JSON input byte-by-byte. Built for devices that can't parse/store inbound data fast enough to avoid watchdog triggers. Uses nullable bit-aligned union data structures. Blazingly fast.

C# CLI tool that generates precompiled trie data structures for extremely efficient UART parsing and JSON tokenization. Supports compressed binary blobs, arrays, and structs. Blazingly fast.

Custom XML tags for creating and tearing down PostgreSQL enum types with Liquibase.

UML to Swift code generation support for Sparx's Enterprise Architect.

GitHub API client for Elixir, built for letting AI agents access/insert tickets and comments on projects.

Hand-written Google REST client for Elixir with OAuth2 — Search Console, GA4, AdSense, and Ads.

Dropbox API v2 client for Elixir — files, sharing, and Paper, with OAuth2 and PKCE.

Terraform/OpenTofu provider for the Read the Docs API v3 (MPL-2.0). Local build only, no registry listing.

Per-directory model routing for Claude Code and OpenCode — backed by a self-healing local LLM gateway.

Terminal tab titles, status, and a todo list in pure shell — themes, iTerm2 to Alacritty, and a Claude Code status-line bridge.

Browser extension that exports LLM chats to Markdown or YAML — local-only, no server round trip.

A curated index of free, open-source terminal tools, Elixir and C libraries, MCP servers, and cross-language family packs — plus the LLM Toolkit.

Extended Mnesia wrapper with callback hooks for telemetry, local cache with cluster sync, RocksDB support, compression, and a database emulator for unit/system testing.

Fork with added project switching capabilities for Google DataStore. Useful for synchronizing environments.

Heavily extended with dynamic template (Handlebars) support, sub-version selector for dynamic messages, and template version query/update calls.

Optimized timezone data handling for high-load environments. Moved lookups from ETS into FastGlobal/persistent_terms for billions of TZ operations per minute.