lingshu-agent-control-plane
Coordinate multi-model agents with plans, permissions, and acceptance
Coordinate multi-model agents with plans, permissions, and acceptance
Lingshu makes a primary agent the control plane for multi-model work. It defines scope and acceptance criteria before delegating to models, CLIs, scripts, or connectors, then reviews their increments and performs final acceptance. Phase reports, plus treating existing tests as protected contracts, help prevent drift, unauthorized actions, and weakening tests just to make a run pass.
Resource types
Use cases
Platforms
Provides Claude skill examples, the Agent Skills specification, and a template for custom skills.
Design agent workflows visually and expose them as APIs or MCP tools.
Audience
Public GitHub facts last synced Jul 10, 2026.
Build LLM apps with visual workflows, RAG, agents, and APIs.
Combine interchangeable models, data sources, and tools in LLM applications.