A referee for self-improving AI agent loops that mines past sessions for effective workflows, improves them, and requires measured proof before declaring anything better or done, never stopping until the user stops it.
Enables AI agents to learn from their work by recording tasks, extracting patterns, detecting mistakes, and proactively surfacing insights, all using the agent's own model through a cooperative intelligence pattern.
Multi-agent AI orchestrator that runs parallel coding agents in isolated sessions with self-improving intelligence, exposed via an MCP server for task execution and management.
Self-learning memory for AI coding agents. Observes tool sequences, user preferences, and recurring fixes — auto-promotes high-confidence patterns into behavioral rules. 22 tools, 2 prompts, SQLite-backed, zero config.