Stars
Forks
Watchers
Developer links
RocketplaneIO
RocketplaneIO is a self-hosted AI SRE platform that gives Kubernetes clusters zero-instrumentation eBPF observability plus a copilot capable of safely diagnosing and fixing issues without your telemetry ever leaving your infrastructure. Point it at any cluster, and an eBPF DaemonSet starts capturing HTTP, gRPC, SQL, Redis, and Kafka spans across every service, including compiled binaries, with cross-service context propagation and no code changes required. The live service map draws itself from actual network traffic, matching technology logos from container images and coloring each node's health from RED metrics. Every log line sits two clicks from its parent distributed trace, and a PromQL query engine, embedded from the real Prometheus evaluator, runs over ClickHouse for long-term metric retention. The complete Kubernetes inventory (Services, Ingress, ConfigMaps, network policies, persistent volumes, CRDs) syncs continuously and is searchable alongside traces and logs. When the copilot identifies a problem, it picks from a catalog of roughly 30 risk-classified safe actions; each action verifies its preconditions, captures a before-state snapshot, executes, checks the result, and rolls back automatically on failure. Disruptive operations pause for explicit human approval before proceeding. An MCP endpoint exposes the identical guardrailed toolbox to external AI agents, so Claude Code or Cursor can operate the cluster through the same safety boundary the browser copilot uses. Complex remediations compose as searchable, forkable Starlark workflows that compile deterministically at save. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.
Benefits
- Automatic eBPF Observability
- eBPF-based distributed tracing captures HTTP, gRPC, SQL, Redis, and Kafka spans across all services including compiled binaries without sidecars, SDKs, or code annotations; service maps are drawn from live traffic automatically.
- Guardrailed AI Remediation
- The copilot proposes fixes from roughly 30 risk-classified safe actions, each with precondition checks, before-state snapshots, automatic rollback on failure, and LIFO snapshot recovery on cancellation.
- Complete Cluster Inventory
- Services, Ingress controllers, ConfigMaps, network policies, persistent volumes, and CRDs sync continuously into a searchable view alongside traces, logs, and metrics for unified troubleshooting.
- Air-Gap and BYO-LLM Ready
- Runs fully air-gapped behind corporate firewalls with your own LLM provider; telemetry never leaves your infrastructure, and the MCP endpoint lets external AI agents operate within the platform's safety boundary.
Features
- eBPF Tracing
- Automatic distributed traces for HTTP, gRPC, SQL, Redis, and Kafka calls across all languages including compiled Go via Grafana Beyla; zero sidecars, zero code changes.
- AI Copilot
- BYO-LLM investigation loop with 16 read tools and one guardrailed mutating tool that pauses for human approval before executing cluster changes.
- PromQL on ClickHouse
- Embedded Prometheus query engine running over ClickHouse storage provides familiar PromQL syntax with long-term metric retention and efficient columnar aggregation.
- Live Service Map
- Automatically drawn from real eBPF network traffic with technology logos matched from container images and node health colored by live RED metrics.
- Safe MCP Endpoint
- Guardrailed Model Context Protocol server that exposes read and action tools to external AI agents through the identical safety boundary the browser copilot uses.
- Starlark Workflows
- Complex remediation sequences compose as searchable, forkable Starlark scripts that compile deterministically and execute through the same verified-action pipeline with typed parameters.