Typhon

Meet Typhon, your AI teammate.

Typhon is an AI agent that joins your team, and works alongside you.

An agent you assign to, not a tool you reach for.

Typhon sits beside the developer — invoked, prompted, watched. It reads acceptance criteria and looks at designs. It surfaces ambiguities back to you when the brief is unclear. It produces a plan, implements, tests, and waits for review before creating a PR.

Built on Claude Code, not around it.

Typhon runs inside Claude Code as skills.

Bring your own Claude.

Typhon doesn't bill you for the tokens it burns. You connect your own Claude credentials, and the agent runs on them.

Token usage
Authenticate with your Claude Max subscription. Typhon burns the same token quota you already pay for.

The credentials never leave your machine.

Writes its own tools, learns from what doesn't work.

Typhon works better over-time — not because the model got better, but because the agent's accumulated context did.

Tools

Common operations — running a particular query, generating a specific kind of file, checking a recurring invariant — turn into purpose-built tools the agent calls directly.

Lessons

When an approach fails — a plan that didn't survive contact with the codebase, a fix that broke something else — Typhon notices and writes the learning into permanent memory. The same mistake doesn't get made twice.

Documentation

Every feature ships with the architecture notes that explain it. The next ticket touching that area starts with a fuller picture.

You keep the keys.

Typhon is an agent, not an autopilot. Developers see a live transcript of its work and can veto, redirect, or take over at any point. Reviewers see a PR with a known plan attached — no archaeology required.