Enoch AI / Lab / Stack

Stack.

The tools behind my personal projects, what I use them for, and what I’m exploring next. This is a working setup, not a list of everything I’ve tried.

In use

Web applications
SvelteKit, TypeScript, and Tailwind for this site and DocLifts. PostgreSQL and Drizzle handle DocLifts’ data; Zod validates inputs at the application boundary.
Hosting and delivery
Cloudflare Pages and DNS for enoch.ai, with deployment triggered through GitHub. This site stays on Cloudflare Pages for low cost, redundancy, and less infrastructure to manage. DocLifts runs separately on an Akamai Cloud (Linode) VPS in Dallas: Ubuntu 24.04, Docker Compose, Node 24.22.1, and PostgreSQL 16. Cloudflare Tunnel serves the live Alpha at doclifts.runthe.ai; Tailscale remains available for private operations. Better Auth handles application accounts.
AI-assisted development
Codex handles implementation, tests, browser verification, documentation and releases. Hermes connects reviews to tools, project files and reusable skills; Claude and Claude Code also contribute to planning, implementation and review. Model choices can change; written requirements, human decisions and checks against the actual result stay central.
Project context and verification
Git keeps code and design decisions together. Repository instructions give coding agents the same ground rules; automated tests and browser checks provide evidence for a handoff. For DocLifts’ history import, I restored a database locally, tested repeat imports and a scoped rollback, and compared all 14 existing application tables before and after production import. Original workout notes and labeled estimates remain attached to the imported data.
Account-scoped agent access
DocLifts’ read-only MCP server is live in Alpha. It pairs OAuth consent and revocation with account-scoped workout, program, equipment and imported-notebook reads. Bulk sets preserve historical machine context. Public protocol checks and real Muse reads passed; other clients still need individual verification.
Data portability and account controls
DocLifts offers password-confirmed JSON and spreadsheet CSV ZIP exports, plus experimental Strong-style CSV. Native exports preserve imported notebook context and uncertainty; photos are metadata only. Account deletion and saved-photo removal use durable off-host journal acknowledgment and retryable cleanup. Restoring exports and a verified Hevy import remain unfinished.
Operations and security checks
Encrypted off-host backups are scheduled, and an isolated restore drill is complete. UptimeRobot checks DocLifts and both websites; Cloudflare alerts watch the DocLifts tunnel. Alert delivery and an outage/recovery drill still need verification. DocLifts remains on one VPS, with replacement-server recovery and capacity testing still ahead. See the security review and shipped fixes →
Read the DocLifts case study →

Exploring next

Structured agent handoffs
Hermes Kanban is an experiment in keeping task state, review feedback and verification evidence together. I haven’t decided whether to adopt it. The goal is to make work easier to resume across tools; stable project rules and release evidence already live in repositories and reviewed pull requests.
Focused, access-controlled tools
I’m exploring cloud applications built around a particular person or team’s workflow, rather than a public platform. That means working through who can access a tool, what it can do, and where human approval belongs.

Have a technical constraint or a different approach worth comparing?

Get in touch →

© 2026 Enoch AI LLC · Delaware · Privacy