Why Bonsai

The Problem

Claude Code is powerful out of the box. But the moment you need agents to coordinate, stay consistent across sessions, or follow your team’s standards — you’re writing walls of markdown by hand. Every project rediscovers the same patterns: identity files, memory protocols, security rules, scope boundaries, review checklists.

And if you want multiple agents working in the same codebase? You’re maintaining parallel instruction sets that drift apart.

What Bonsai Does

Bonsai gives your coding agent a workspace — not a pile of markdown files, but a layered system with clear semantics:

  Layer 6 │ Sensors       │ Automated enforcement via Claude Code hooks
  Layer 5 │ Routines      │ Periodic self-maintenance on a schedule
  Layer 4 │ Skills        │ Domain knowledge — standards, patterns, conventions
  Layer 3 │ Workflows     │ Step-by-step procedures — planning, review, audit
  Layer 2 │ Protocols     │ Hard rules — security, scope, memory, startup
  Layer 1 │ Core          │ Identity, memory, self-awareness

You pick the components. Bonsai generates a complete, wired-up workspace — with cross-linked navigation, auto-enforced hooks, and a shared project scaffold that keeps every agent on the same page.

One binary. No runtime. Works with any project.

Who It’s For

Solo developers

Want your Claude Code agent to behave consistently, remember context between sessions, and follow project-specific standards.

Teams

Coordinating multiple agents across a codebase — backend, frontend, devops — with a shared source of truth.

Anyone tired of copy-pasting

Stop copying agent instructions between projects. Bonsai generates everything from a catalog of battle-tested components.