Quick Start
1. Initialize a project
npx amodal initThis scaffolds an .amodal/ directory with a config file, sample skill, and sample knowledge document. The init command is interactive — it asks for your product type and sets up appropriate templates.
2. Configure your provider
Set your LLM provider credentials. Amodal auto-detects from environment variables:
# Pick one:
export ANTHROPIC_API_KEY=sk-ant-...
export OPENAI_API_KEY=sk-...
export GOOGLE_API_KEY=...Or configure explicitly in .amodal/config.json:
{
"name": "My Agent",
"provider": "anthropic",
"model": "claude-sonnet-4-20250514"
}3. Add a connection
Install a pre-built plugin or create a custom connection:
# Install a plugin (e.g., Slack, GitHub, Datadog)
amodal connect slack
# Or sync from an OpenAPI spec
amodal sync --from https://api.example.com/openapi.jsonConnections live in .amodal/connections/ and give the agent both API access and documentation.
4. Start the dev server
amodal devThis starts the runtime server on localhost:3847 with:
- Hot reload — edit any
.amodal/file and the agent updates instantly - File watching with 300ms debounce
- Session management with TTL
5. Chat with your agent
amodal chatThis opens a terminal chat UI (React-based TUI with Ink). You can also connect to a remote server:
amodal chat --url http://localhost:3847Or resume a previous session:
amodal chat --resume latest6. Validate and inspect
amodal validate # Check for missing connections, config issues
amodal inspect # Show compiled context with token countsWhat's Next
- Project Structure — Understand the
.amodal/directory layout - CLI Reference — All 30+ commands
- Add skills — Author reasoning frameworks
- Deploy — Ship to production