Shape how your AI thinks

The problem

Agent config files grow into unmanageable walls of text. One monolithic prompt for every task. Copy-paste between projects. No way to switch behavior without rewriting everything. See Why Composable Prompts for the full case.

How it works

Instead of one monolithic config file, brainjar separates agent behavior into composable layers. Each layer is a markdown document managed on the server. Mix and match them per project, per task, or per session.

👻 Soul Who the agent is — voice, character, standards. The constant across all tasks.

🎭 Persona How the agent works — role and workflow. Switch per task.

🚧 Rules What the agent must follow — behavioral constraints and guardrails.

🧠 Brain A saved snapshot of soul + persona + rules. One command to activate.

Quick install

bun install -g @brainjar/cli
brainjar init --default

That gives you a soul, a persona, and rules — all wired into your CLAUDE.md and ready to go. Already have a large config file? Migrate it.

Built for agents

brainjar is built with incur, a CLI framework designed for agent consumption. Every command auto-detects whether it’s talking to a human or an agent — structured output (TOON, JSON, YAML) when piped, formatted text with context when interactive. Agents discover the full CLI via --llms, MCP server, or skill files.

brainjar status                     # human: formatted with context
brainjar status --format toon       # agent: structured data

These docs are agent-readable too. Point your agent at brainjar.sh/llms.txt for a doc index, or append .md to any page URL for raw markdown (e.g. /getting-started.md).