Provides durable queues, human-in-the-loop approval gates, and an audit trail for AI agent fleets, enabling blocking approval requests and reliable work handoffs.
A git-backed MCP server that centrally manages AI agent skills, tools, and knowledge with role-based access, change requests, and a remote OAuth 2.1 endpoint.
A local-first job broker with MCP and HTTP interfaces for orchestrating AI work, with cost-aware routing, observable state transitions, and human control.
Enables structured role-to-role handoffs and merge gating for multi-agent collaboration. It persists evidence and computes approval gates without invoking LLMs.