Provides an isolated MCP bridge giving Codex Hermes-style long-term memory, checkpoints, and optional tools, while keeping Hermes and Codex data read-only and requiring human approval for skill proposals.
Enables MCP clients and external AI supervisors to oversee and steer native Codex sessions through a thin local stdio bridge. It exposes eleven codex_* supervisory tools for tasks such as listing threads, starting turns, observing progress, steering, responding to approvals, interrupting, checkpointing, and rolling over work.
A zero-friction stdio MCP bridge connecting Cursor Desktop to a local Hermes Agent, enabling natural language task delegation with session continuity and profile awareness.
Enables ChatGPT (or any MCP client) to delegate coding tasks to a local Hermes-backed agent with async job management, supporting read-only investigation, implementation, and continuation of sessions via secure MCP tunnel.