"author:ewanni" matching MCP servers:

Enables reusable role-based agents, solo execution, and bounded multi-agent discussions with independent proposals, peer critiques, judge consensus, revision rounds, token budgeting, and SQLite audit logging.

Enables users to define and run reusable role-based agent profiles that complete tasks alone or in bounded multi-agent discussions with independent proposals, parallel critiques, an independent judge verdict, and optional revision rounds, persisting all session events to a local SQLite log. It works over MCP stdio with any OpenAI-compatible chat completions endpoint and exposes profiles as resources.