Guides and reference for authoring and running Recipes.
Recipes is an open package format for Pi agents. An agent recipe is a Git directory that configures a complete agent: instructions, model, tools, skills, connections, and the agents it orchestrates. Pi runs it. A host supplies credentials, storage, and lifecycle.
Quick start
There are two entry points, and they produce the same directory.
Start with Introspection
The plugin is a forward-deployed engineer. It scaffolds the package and works through your domain with you until the method is written down as skills and the standard as judges.
npm install -g @introspection-ai/cli
introspection init # scaffold a recipe, with the agent that builds it
introspection local # launch Pi against it
Start with Pi
Clone a recipe that already runs, read it, then change the parts where your work is different.
pi install npm:@introspection-ai/recipes # once per machine
git clone https://github.com/introspection-recipes/template-claude
pi --recipe ./template-claude
How Recipes work
- Recipes the package: what is in the directory, and how it is read.
- Agents identity, model, tools, inheritance, and delegation.
- Skills and prompts your method, and the shape of what comes out.
- MCP two policy gates, CLI and tools mode, deferred tools.
- Extensions tools you write in TypeScript, owned by the package.
- Interactions ask the user something, in a terminal or over your protocol.
- Evals and judges Evalite, Harbor, and judges you calibrate locally.
Deploy it
- Deploying what changes when a host supplies credentials and endpoints.
- Telemetry pass a tracer, get GenAI spans for every model and tool call.
- SDK reference resolve a recipe and construct its Pi session from your code.