LexDev

Bismarck v5 is a game-experiment platform where players play Walreign Empire web games that trigger real development work through Codex/GPT-5.4; v0.4 was torn down on 2026-04-23 and the domain was retained for the rebuild.

LLM cost intelligence product line — the v1 public calculator launched, and on 2026-06-05 the v2 line split into two domain-scoped products: Trace (production LLM/API cost for startup CTOs) and Crew (AI dev-tool cost for platform engineering leads), each with approved positioning and ICP, pre-code.

AI form builder with drag-and-drop editing, conditional logic, public renderer, submissions, Stripe billing, and 10 field types — Turnstile verification, GDPR consent, response limits, and export/analytics remain before launch

CLI-first adversarial AI debate system with debate, duel, roast, review, compare, history, and export commands built on a stable Rust debate engine

AI orchestration engine powering Bismarck's workspace management, code generation pipelines, and multi-agent task routing

AI coding subscription pacing app for Claude, Codex, Gemini, and future providers; Pitwall Local is in technical GitHub beta/source-install readiness, while the monorepo preserves the path to a future CalcLLM-powered connected edition with opt-in cloud sync and team cost dashboards.

Cloud code snippet manager with Clerk, tRPC, AI tagging, semantic search, Gist import, and VS Code extension — Stripe lookup-key billing migrated; plan gating, tests, and production polish remain before launch

Config-as-code product analytics for PostHog - a free OSS CLI and SDK adoption wedge with deferred hosted team-governance monetization.

AI-powered raster-to-vector conversion for Glowforge, xTool, and Cricut fabricators — web and desktop pipeline shipped, conversion funnel complete, Stripe lookup-key billing migrated

Agent-native browser QA and automation platform — Playwright-backed runtime with semantic page snapshots, an MCP server for agent control, and a provider-backed test planner; the browser-runtime refactor is the latest workstream

Block-based web terminal library — five-package TypeScript/React monorepo (core, parser, block-model, transport, react) with CI

Managed infrastructure and control plane for AI coding agents — persistent cloud machines run parallel agent sessions while the Agent Board dashboard provides monitoring, approval routing, and mobile access; dual-track as a personal dogfood workstation and a commercial SaaS, currently in AFPS discovery.

Public catalog of reusable agentic workflows and skill packs for Claude Code and Codex agents — structured prompt-to-ship pipelines with inspectable sessions, pack mapping, and proof-of-work documentation.

Owned domain awaiting mission assignment. No codebase, no users — held in reserve.

AI dev-tool cost intelligence for platform engineering leads — per-engineer attribution across Copilot, Claude Code, Cursor, and Windsurf within the calcLLM product line

Production LLM and API cost intelligence for startup CTOs — answers why the bill is 3x what token pricing implies, within the calcLLM product line

Auto-generated, auto-maintained product tutorials and videos from a GitHub repo plus staging app — YAML-defined flows regenerated in CI/CD for DevRel teams

Mobile remote control for AI coding agents over SSH — Expo/React Native client with a tmux session UI for monitoring and driving Claude Code sessions from a phone

AI-powered SVG animation tool — describe an animation in text and get SMIL/CSS output, backed by Gemini

Interactive Terraform plan visualizer and linter with AWS architecture diagrams and live apply streaming

TypeScript SDK for multi-agent AI apps — DAG task decomposition, parallel agent execution, token budgets, and streaming