YYLO system / three open-source layers
Coordinate, remember, and evaluate agentic engineering work.
YYLO is one connected system: a control plane for action, a Git-native Ledger for task truth, and Benchmark evidence for comparing agent attempts over time.
Control plane
YYLO
Coordinate bounded agent execution, provenance, validation, review, and integration.
0.2.11 stable →Engineering memory
YYLO Ledger
Preserve Git-native tasks, wiki knowledge, workflow definitions, artifacts, dependencies and history.
0.4.0 stable →Evaluation evidence
YYLO Benchmark
Compare reviewed cases and independent attempts with later evaluations and separate result rows; frozen checklists make assessment criteria explicit.
0.2.1 stable →Ecosystem package
YYLO Skills
Reusable procedures for Ledger Records, planning and bounded delivery. Supports all three systems.
2.1.1 stable →Ecosystem package / independently versioned
Give agents reusable YYLO procedures.
YYLO Skills helps agents operate the three layers consistently without becoming another product layer.
Explore YYLO Skills →