Masthead
Local-first session data for coding agents: capture work into SQLite, publish artifacts, retrieve via read-only MCP.
See the build arrow_forwardWhat Animas AI is for
I build the layer between people, agents, tools, and messy operations.
Most AI work does not fail because the model is weak. It fails because nobody captured the context, workflow rules, handoffs, review loops, and ownership model. That is the layer I like building.
psychology
Agentic workflows
Agents with durable context, task state, tool access, and judgment boundaries.
dashboard
Internal tools
Dashboards, admin panels, intake flows, and control surfaces for repeated work.
auto_awesome_motion
AI media systems
Avatar, voice, video, content, and review pipelines using modern AI media APIs.
api
Product engineering
React, TypeScript, SQLite, Supabase, PocketBase, APIs, and pragmatic glue code.
A working set of shipped products.
Open the work archive arrow_forward
ChartStead
Keep the call, review, speaker work, messages, and agenda together, then publish when the team is ready.
See the build arrow_forward
Pip
Spendable Cash Today, deterministic money logic, and an agent that explains approved actions.
See the build arrow_forward
Hotel Cleaning Schedule
Deep-clean planning for ~40–100 room houses: rooms and capacity in, a validated calendar out.
View product open_in_new
Executioner
A personal execution system with onboarding, payments, email, and AI-assisted planning.
View Executioner open_in_new
Milkbench
A visual benchmark for GPT 5.6 taste, with Luna, Terra, and Sol as model personalities.
View Milkbench open_in_new
Rat Detective Online
A multiplayer browser game with Three.js, TypeScript, physics, and real-time play.
Play live open_in_new
Wargus TypeScript
Classic RTS in the browser. Harvest, train, build, and fight on Garden of War.
Play live open_in_newOperating thesis
The person using the system is part of the system.
Good AI work is not just prompts. It is context capture, interfaces, review loops, permissions, data shape, failure handling, and the human confidence to use the thing when the work gets noisy.
groups
Strong with nontechnical operators
Hospitality and customer-facing work taught me how to translate messy human context into tools people can trust.
construction
Comfortable without clean specs
Most valuable systems start as fog. I can explore, prototype, test, and tighten until the shape appears.
manage_accounts
Ownership beats micromanagement
I do my best work with room to own the problem, make decisions, and show progress through working artifacts.
verified
Honest about AI limits
AI does not fix chaos by magic. It needs rules, memory, context, and maintenance to become useful infrastructure.
Built directly
Animas AI is Tyler Mayberry turning ambiguous AI work into working systems.
My best work is turning unclear operational problems into concrete systems: interfaces, workflows, data shape, automations, and agent loops that people can trust. Available for aligned full-time remote roles, contract work, and consulting where practical AI tooling matters.
Need someone who can turn ambiguous AI work into something real?
Send me the context. I will tell you what I would build first, what I would leave alone, and where a useful version probably starts.