30-second agent onboarding.

The intended path: one line installs the CLI, connects jerrycan to your coding agent, and leaves a guided runbook behind. You never write the code.

Have an agent? Just paste this.

# Claude Code, Cursor, Codex, Windsurf — any capable agent

Fetch https://jerrycan.cc/start and follow it to set up jerrycan and build my backend.

Or install and wire it yourself.

$ curl -fsSL https://jerrycan.cc/install.sh | bash -s -- --agent claude-code

# agent ids: claude-code · cursor · codex · windsurf · generic

This installs the jerrycan binary (CLI + the MCP server your agent talks to), wires it into your agent, and runs jerrycan onboard — the guided runbook the agent follows.

# wire the MCP server by hand instead

claude mcp add jerrycan -- jerrycan mcp

{ "mcpServers": { "jerrycan": { "command": "jerrycan", "args": ["mcp"] } } }

The loop the agent drives.

jerrycan_design requirements become a validated design.json — pointed questions, not guesses

jerrycan_scaffold a crate-per-module workspace, one route crate per module

jerrycan_gen_tests failing acceptance tests, generated from the design

jerrycan_check build + clippy + audit + tests + lints — machine-readable diagnostics

jerrycan_package hardened artifacts + SBOM, only when everything is green

jerrycan_deploy a deploy kit for the target platform, run by the agent

Driving it yourself instead.

$ cargo binstall jerrycan # prebuilt binaries, all 4 targets

$ cargo add jerrycan --features db,auth,validate,observe

A route module is Flask's Blueprints, reborn with compiler-enforced boundaries. Everything a handler needs is visible in its signature — guards are just dependencies. Full docs: llms.txt · docs/ai — every example is a CI-run doctest.

What it's for — and not.

FOR

CRUD-shaped, multi-tenant REST APIs — the backbone of most SaaS. Plus object storage and realtime (contract v2).

NOT (YET)

GraphQL / gRPC, edge / serverless. jerrycan runs as a normal long-lived service. We'd rather name the edges than oversell the middle.