Self-hosted web dashboard for supervising multiple Claude Code AI sessions in tmux. Live terminals, real-time git diffs, file browser, todo lists, prompt templates, and mobile PWA support. Micromanage your AI interns from any device.
CI for Claude Skills — lint, eval, and regression-test SKILL.md files across a model matrix, with a self-growing eval loop that turns uncovered regressions into permanent test cases.
Terminal UI to manage SSH keys, edit ~/.ssh/config, and audit your SSH security. Encrypted metadata + backups, an A–F security grade, byte-identical config editing. Single static binary, offline, no daemon.
Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.
Hand a live Claude Code, Codex, or opencode session to anyone with three spoken words - encrypted, no account. Or carry your whole Claude Code history to a new laptop, every path rewritten.
All-in-one engineering workflow & knowledge engine for Claude Code. One-command install, runs standalone (Node >=18, no bun). L0-L3 task classification, 13 runtime invariants, code review, browser QA, security audit, and a deduplicated knowledge base that compounds across tasks.