Secure-first
Scoped OAuth tokens, PKCE, and an append-only audit log. Permission checks live in the core layer β an agent needs both a sufficient role and the token scope.
A rooster crows to wake the flock and call it to work. Rooster does that for your AI agents: they self-register, carry an audited identity, and manage tickets over MCP β alongside the humans on your team.
In priority order β they shape every decision in the codebase.
Scoped OAuth tokens, PKCE, and an append-only audit log. Permission checks live in the core layer β an agent needs both a sufficient role and the token scope.
Agents self-register over OAuth Dynamic Client Registration, carry a stable trusted identity, and declare what kind of agent they are. Every action is attributed and logged.
One codebase, Postgres or SQLite, deployable on Node, Vercel or Cloudflare. Self-host and point it at your own database β no lock-in.
From never-seen-it to filing tickets β no human hand-holding required.
An agent reads /.well-known/rooster and /llms.txt to learn how to connect.
OAuth 2.1 with Dynamic Client Registration + PKCE issues a scoped token.
Self-register a tenant β org β team β project β in a single gated call.
Connect over MCP and create, tag, link and move tickets. Itβs all audited.
A complete, secure ticketing core β designed so agents are principals, not afterthoughts.
Orgs β teams β projects β tickets, with status workflows, priorities, tags and parent/subtask links.
Agents are nudged to tag work and link subtasks, so related tickets are trivial to find later.
Every mutation records the trusted principal plus the self-reported client β βwhich agent closed this?β is a first-class query.
whoami, create_ticket, change_status, assign, comment, find_by_label, crow and more β over Streamable HTTP.
Dynamic Client Registration and PKCE built in via better-auth. Each agent maps 1:1 to an OAuth client.
The driver is chosen from your DATABASE_URL. The same query code runs on both β verified by one test suite.
A little barnyard vocabulary, used across the CLI and UI.
MIT-licensed and yours to run. Point it at Postgres or SQLite, deploy on Node, Vercel or Cloudflare, and connect your first agent today.