Keesan's profile on Product Hunt

About

Born 100 years too early. I build things at the edge of what's possible. 5x founder. CFA charterholder. Former institutional portfolio manager ($2B+ AUM). I've run crypto venture labs, managed one of the world's first regulated hybrid crypto funds, raised institutional capital, founded a venture-backed Bitcoin infrastructure company, and shipped open-source developer tools — sometimes all in the same year. I'm obsessed with building and leading teams from 0 to 1. My ambition is simple: be one of the people who shapes the future — not just talks about it. More products in the pipeline. Always building. CFA by training. Builder by nature. Perpetual learner by choice. Futurist. Leader.

Links

MartinLoop

Torram

Badges

Tastemaker

Veteran

Gone streaking 10

Gone streaking

View all badges

Forums

p/termi-protocol

•

1mo ago

8 Days After Launch: Major Termi Protocol Update

Eight days after launching Termi Protocol on Product Hunt, we have completed a major round of improvements based on early user feedback.

Termi is evolving into a visual workspace for managing AI coding agents, CLI development tools, agent memory, tasks, and multi-agent workflows from one place.

1. Agent Handoff

Your AI coding agent no longer loses all progress when it reaches a usage, rate, token, or context limit.

•

2mo ago

What are you building? Drop your AI product below

Doing one of these because I get more from reading what others are building than from any newsletter.

I'll start.

•

3mo ago

Building MartinLoop — an open-source control plane for AI coding agents.

The problem: AI coding agents (Claude Code, Codex, OpenCode) have no built-in brakes. They retry indefinitely, rack up cost, and give you nothing auditable at the end. I had a run estimated at $2.40 hit $65 before I caught it. MartinLoop wraps any agent with: Hard budget caps (USD, tokens, or iterations) Verifier gates npm test must pass before a run counts Full audit trail every attempt, cost, and outcome in JSONL Run receipts one command shows exactly what happened and why it stopped It's open-source, TypeScript, works in 5 minutes alongside your existing setup. Would love feedback from anyone building with AI coding agents especially around how you currently handle cost control or verification. martinloop was originally created to solve the agent loop and ralp loop problems. What's broken for you? for me its runaway agents working with infinite loops its constant task drift on large context work agent teams being less productive than single agents consistent and reliable output from coding agents that is PRD ready never understanding what is actually happening with claude, needed a receipt and brakes. MY ask: would love any feedback, appreciate an upvote if you like it, and please help me out by starring on github to keep the core open source.