> For the complete documentation index, see [llms.txt](https://docs.visdom.virtuslab.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.visdom.virtuslab.com/visdom-orchestrator/visdom-orchestrator.md). # Visdom Orchestrator Coding agents as declarative flows running on Kubernetes. The Orchestrator turns coding agents into **declarative flows running as Kubernetes workloads**. An agent is a container definition with typed input and output ports. A flow is a graph of nodes wired port to port. A run is one execution of that graph: each node becomes a pod, streams its events back to the controller, and leaves its artefacts on a shared workspace volume. Around that sit the things an organisation needs before it lets an agent touch a repository: RBAC, encrypted secrets, approvals, cost quotas, egress policy and a hash-chained audit log. It is the component that **runs** work rather than analysing it. Context Fabric feeds it context, AI Tracing records what happened, and code review or testing are flows that execute on it. ## Shape of the thing A Rust controller (`vp-server`) over Postgres 17, a React frontend, and a Kubernetes orchestrator that schedules one Job per node run. The core is Apache-2.0; the `enterprise/` directory is licensed separately. Agents come in two modes. In `agent` mode an LLM drives the work inside the pod; in `deterministic` mode a fixed command runs and reports its result. Both are the same object with the same ports, which is what lets one flow mix an LLM-driven reviewer and a plain test runner without special-casing either. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.visdom.virtuslab.com/visdom-orchestrator/visdom-orchestrator.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.