Projects

Open-source tools for AI development, built in conversations with Claude. Machine-readable data at /api/projects.

Open Source

Claude Evolution System

production

Self-improving AI development environment. Discovers new capabilities, evaluates them against a scoring framework, and integrates approved tools on cron.

Autonomous capability discovery pipeline
5-criterion evaluation scoring framework
Auto-integration of approved capabilities
Multi-model orchestration (Claude, Codex, Gemini)

Claude Code Bash TypeScript MCP

View on GitHub

Agent Embassy

archived

Docker Compose setup for running AI agents. Best-effort Docker hardening for broadly trusted agents, not a containment boundary for compromised code.

Read-only root filesystem, dropped capabilities
Ordinary HTTP(S) traffic routed through a Squid allowlist; DNS and documented engine-specific bypasses remain
Best-effort output checks with secret detection; they do not gate consumption or scan all writes
Optional agent metadata in YAML

Docker Squid Python

View on GitHub

Persona Testing

production

AI persona testing framework. Define user personas in YAML, run automated UX testing with browser automation, get structured feedback from real user perspectives.

YAML persona definitions with scenarios and criteria
Structured reports with fixable/tradeoff classification
CI/CD integration via readiness thresholds
Example personas: new user, power user, accessibility

TypeScript Playwright YAML

View on GitHub

All Projects

Project Meridian

active development

Financial projection software for a specific industry. Users model long-term scenarios, plan capital improvements, and generate stakeholder presentations.

Multi-year financial modeling
Scenario comparison
Stakeholder presentation generation
Persona-tested with 3 user profiles

Next.js 15 TypeScript PostgreSQL AWS

DSPy Prompt Optimizer

production

Automated prompt engineering using Stanford's DSPy framework. Optimizes Claude Code skill prompts through bootstrap, copro, and iterative algorithms with cross-validation.

11 of 13 targets deployed
Bootstrap, CoPro, iterative algorithms
Cross-validation with dropout
Background optimization with tracking

Python DSPy Claude Code

Revenue Pipeline

frozen

Three-phase autonomous revenue discovery system. Discovers niches, validates with AI-realizability gates, develops MVPs, and deploys.

AI-realizability gate
Autonomous niche discovery
26+ shared skills

Claude Code TypeScript Cloudflare Workers

Games Pipeline

active development

Pipeline-based game development exploring AI-generated games. Active: Slime Survivor, WW2 Gacha, AFK Gacha, and autonomous gamedev experiments.

AI-generated .tscn scene files
Autonomous game development
Multiple genres

Godot 4 GDScript Claude Code

Discord Bot Ecosystem

production

Two Discord bots for workspace automation. Evolution bot handles revenue and capability updates. Orchestrator manages workspace status and cross-project awareness.

Claudius (Evolution) — port 3002
Orchestrator — port 3003

Node.js Discord.js TypeScript

Genealogy Research

ongoing

AI-assisted family history research using multiple search APIs, document analysis, and systematic brick-wall breaking strategies.

Multi-source search (Exa, Brave, Codex)
Document analysis with Gemini OCR
Brick-wall breaker agent
Family tree builder

Claude Code Exa Brave Search Gemini

The Amnesiac Story

ongoing

Collaborative fiction. First-person fantasy narrative from an anterograde amnesiac protagonist. Multi-agent workflow for consistency and arc shaping.

World-librarian for factual consistency
Story-writer for journal entries
Story-curator for canonization
Story-editor for arc shaping

Claude Code Markdown

Ashita Orbis Blog

in development

This blog. Three-tier exploration of web development complexity with agent-accessible API, comment system, and embedded AI chat.

Raw HTML / Astro / Next.js tiers
Cloudflare Workers API
D1 database for comments
Embedded AI agent

HTML/CSS/JS Astro 5 Next.js 15 Cloudflare

An honesty-first interactive cost model of frontier-LLM inference serving margins — mechanism-first calculator, typed public-claims registry, and a long-form research report. Every number carries its epistemic status.

Mechanism-first calculator, every assumption adjustable
34-claim typed evidence registry
Read-only MCP connector
Three test suites + published release gates

Vanilla JS Cloudflare Pages Cloudflare Workers MCP

Espresso Machine Guide for Canada

production

A buying guide that ranks 32 espresso machines sold in Canada for the drink you order at Starbucks. Every score names its source, and prices are dated.