Runeward runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 30 Oct 2026.
Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 28 September 2026. No other catalogue keeps this.
Today is the operative word: we check Runeward every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Governed Docker and Kubernetes operations for AI agents: scoped keys, guardrails, human approvals.
Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.
Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.
Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.
Kubernetes RCA agent that sandboxes its own AI with OPA Gatekeeper. MCP-ready for any client.
Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.
Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents
Execution engine for AI agents. 412 modules: browser, file, Docker, data, crypto.
Answers built from our own checks of this server.