Build
Project Structure
See where agent definitions, Python extensions, tests, and dependencies live in a Connic project.
Last updated
On this page
A Connic project is a repository with a small set of recognized directories. connic init creates agents/, tools/, middleware/, and schemas/. Add guardrails/, hooks/, and tests/ when needed.
Project structure
my-agent-project/
What each directory contains
agents/
YAML files that define each agent. Use
_defaults.yaml for shared settings, then override them in individual agent definitions.tools/
Python modules containing custom tools. Parameter types and defaults define input schemas; docstrings define descriptions.
middleware/
Optional Python modules that run before and after an agent execution. Match modules to agents as described in Middleware.
hooks/
Optional Python modules that wrap individual tool calls. See Tool Hooks for discovery and signatures.
guardrails/
Optional Python modules containing custom guardrail checks.
schemas/
JSON Schema files referenced by an agent's output_schema field.
tests/
YAML suites containing inputs, mocks, and assertions. See the first-test guide for file matching and execution.
requirements.txt
Python packages installed with the project. Keep credentials out of this file and use environment variables for runtime secrets.
Create the scaffold
terminal
connic init my-agents --skill
cd my-agentsThe optional --skill flag adds the Connic project guidance used by compatible AI coding agents. Run connic lint after reorganizing files to validate discovery.