darwin

Assess AI agent ecosystem health by analyzing git metrics, file structures, and activity logs to calculate an Ecosystem Fitness Score based on coverage, coherence, and adaptability. This identifies lifecycle phases and flags underused or outdated agents.

Lifecycle detection for AI agent management automatically identifies project phases like GENESIS, ACTIVE_BUILD, or PRODUCTION using git and activity signals. It triggers evolutionary actions to adapt agent relevance when project phases shift.

Identify outdated AI agents by evaluating agent relevance scores against current project contexts. The system calculates relevance scores from activity logs and existing agent scores to flag agents needing refinement or retirement.

Trigger evolutionary actions for agent ecosystems during phase transitions, quality plateaus, or agent dormancy. The system detects these lifecycle signals and proposes concrete actions like new skill creation or retiring obsolete agents.

Yes, use git metrics to evaluate agent fitness during project stabilization. The system detects lifecycle shifts, calculates ecosystem fitness scores, and recommends maintenance-suited agents while flagging irrelevant ones for retirement.

Automate agent ecosystem evolution by integrating git metrics, file structures, and activity logs to continuously monitor health. The system detects lifecycle phases, scores agent relevance, and proposes targeted evolutionary actions for ecosystem improvement.