self-evolver

What problem does it solve?

Automates continuous self-improvement and orchestration across an AI agent system by providing self-monitoring, agent matching, task decomposition, and decision tracking.

Core Features & Use Cases

• Self-Monitoring: periodically evaluate agent health, learning streaks, and coordination metrics.
• Agent Matching: automatically assign tasks to the best-fit agent based on capabilities and workload.
• Task Decomposition: generate wave-based execution plans with dependencies and pilot tasks.
• Decision Tracking: record rationales and outcomes for post-mortem reviews and audits.
• Use Case: As a project evolves, the self-evolver ensures the right agents are engaged, tasks are broken down into waves, and decisions are logged for accountability.

Quick Start

Run the self-monitor script to check status, then use the agent matcher to assign tasks, run the task decomposer to plan waves, and record decisions with the decision tracker.