I built MuonTickets, a Git-native, file-based ticketing system designed for AI agents and high-parallel development workflows.
Instead of using external issue trackers, tickets live directly inside the repository as Markdown files (/tickets/T-000123.md). State changes are commits. Validation runs in pre-commit and CI.
The idea is simple:
One ticket = one file
Strict lifecycle: ready → claimed → needs_review → done
Dependency-aware task picking
WIP limits enforced
mt pick lets agents self-select the best ready task
Mermaid graph output for dependencies
JSON export for LLM tooling
It’s optimized for multi-agent workflows where coordination becomes the bottleneck rather than code generation.
There’s no database, no SaaS backend, and no sync layer. Git becomes the coordination substrate.
install the repo as submodule and ask your AI agent to implement it
Instead of using external issue trackers, tickets live directly inside the repository as Markdown files (/tickets/T-000123.md). State changes are commits. Validation runs in pre-commit and CI.
The idea is simple:
One ticket = one file
Strict lifecycle: ready → claimed → needs_review → done
Dependency-aware task picking
WIP limits enforced
mt pick lets agents self-select the best ready task
Mermaid graph output for dependencies
JSON export for LLM tooling
It’s optimized for multi-agent workflows where coordination becomes the bottleneck rather than code generation.
There’s no database, no SaaS backend, and no sync layer. Git becomes the coordination substrate.
install the repo as submodule and ask your AI agent to implement it