
YYLO
Coordinates coding agents with validated, auditable engineering work

About YYLO
YYLO is an open-source system of work for teams building software with coding agents. It takes a bounded engineering intent, delegates the execution to an agent working in an isolated worktree, and validates the result through tests, evidence receipts and policy-bound review before anything is merged.
The product is aimed at engineering teams who want agent output they can inspect and defend. Rather than replacing Git or an existing repository workflow, YYLO sits alongside it and keeps the task, session, review and evaluation evidence that explains what happened. Task responses, commits and merge outcomes stay available for future work.
Its differentiator is the memory layer. YYLO is moving toward linking intent, decisions, attempts, validated code and eventually real-world outcomes into a single engineering change record. The current release covers the control plane, a Git-based ledger and a benchmark for comparing agent attempts, with the broader roadmap presented as direction rather than current capability.