A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.

Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Token insights.

Local-first A-share research workbench for DeepSeek Harness: market dashboards, watchlists, valuation, four investor agents, versioned reports, and continuous post-report chat.

DeepSeek Harness adapter for Qwen Token Plan CN with Responses tools, GLM Chat routing, and a versioned official catalog