Vimox Shah

Vimox Shah

Building AI agents & developer tools

About

I’m a product-focused builder working at the intersection of AI, developer tools, automation, and intelligent workflows. I enjoy taking complex technical problems and turning them into practical products that are easier to use, easier to build with, and genuinely useful in day-to-day work. Currently exploring AI agents, agentic development workflows, developer infrastructure, automation, and new ways to make software development more autonomous. Always experimenting, shipping, and looking for ways to push what’s possible with AI-native products.

Badges

Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Maker History

Forums

•

14d ago

Clockwork - Book coding agents like meetings. Wake up to the report.

Book Claude Code, Codex, OpenCode or Hermes on a calendar. Clockwork runs each job in a sandboxed git worktree, caps the spend, pauses risky steps for your approval (even on your phone), and files a report you can turn into a PR. Pipelines, worker Macs, a CLI.
•

27d ago

Tokenflow - See where your AI spend actually goes

Your AI coding agents bill you monthly and tell you nothing. TokenFlow reads the logs Claude Code, Codex, Cursor and Cline write on your machine, prices every branch, and posts the cost on the pull request as a comment plus a status check — so a change over its declared budget fails before it merges. A guard hook brakes a session while it is still running, and an MCP server hands the same numbers to the agent spending the money. Local-first, zero dependencies, MIT. Nothing leaves your machine.
•

1mo ago

Clockwork - The calendar where your AI agents show up for work

Book AI coding agents on a real calendar. Clockwork runs them unattended in sandboxed git worktrees on your Mac, pauses for approval when something looks risky, and files a report with the actual dollar cost. Bring your own key or ride your existing subscription. Schedule recurring agent jobs on a real calendar, run them unattended in isolated sandboxes, and review honest reports.
View more