Tokenwise
Monitor model requests and review ways to reduce LLM operating costs.
Build, test, ship, and maintain better software.
Monitor model requests and review ways to reduce LLM operating costs.
Check Claude and Cursor usage from a configurable Mac menu bar companion.
Create consistent 2D game art, animate characters, and build playable browser games.
Record browser network activity and export technical evidence for bug reports.
Build, refine, and publish branded documentation through an AI-assisted workspace.
Manage feature flags with local evaluation, targeted rollouts, and a self-hosted dashboard.
Capture a webpage element and spoken feedback as context for an AI coding assistant.
Toggle Claude Code MCP servers and manage session restarts from the Mac menu bar.
Host persistent AI agents in individual virtual machines.
Return classifications, extracted fields, and small decisions through an API.
Find listening ports, understand their processes, and share local previews.
Run coding agents in separate worktrees and review their results in one workspace.
Compare computer-use agents through live tasks, recorded attempts, and human preferences.
A terminal coding agent connected to the teai.io model catalog.
Bring engineering alerts and agent handoffs into a native Mac workspace.
Review AI coding work through delivery plans, revisions, and evidence.
Review KiCad revisions through visual diffs, design discussions, and checks.
Create, play, and share small interactive apps from a plain-language idea.
Turn a plain-language idea into a small app that lives on your desktop.
Prepare data, configure model training, evaluate checkpoints, and ship through one CLI.