Enables LLM agents to route responses as accept, verify, or ask-a-human based on token logprobs, and provides an MCP server for delegating generation to local models with confidence bands.
MCP server for storing and retrieving context-specific agent rules, enabling AI agents to access relevant guidelines efficiently and reduce context window usage.
MCP server that provides tools for evaluating LLM agent reliability, including adversarial task generation, automated LLM-as-judge assessment, and confidence statistics.
MCP server that enables AI agents to run a deterministic orchestration loop with decomposition, subagent execution, and review feedback across multiple LLM backends.