ccfos/huatuo

Health v2 · maintenance only

Adoption not part of the score

1107 stars · 130 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

HUATUO is an eBPF-based Linux kernel observability agent that provides kernel-wide metrics, event-driven context capture, autotracing, and continuous profiling with under 1% overhead. Open-sourced by Didi and listed in the CNCF Landscape, it supports cloud-native, AI infrastructure, and bare-metal deployments with Kubernetes awareness.

Use cases

• diagnose linux kernel performance issues with ebpf
• continuous profiling of cpu memory and io on production servers
• automatically trace cpu idle drops and io latency spikes
• monitor kubernetes containers with kernel-level metrics
• troubleshoot system jitter and load average spikes
• profile multi-language applications like java and go with low overhead

When to choose

• you need kernel-wide observability on linux with minimal overhead
• you want automatic tracing and context snapshots without manual instrumentation
• you run large-scale kubernetes or bare-metal fleets and need deep system insight

When to avoid

• you need application-level APM traces rather than kernel/system metrics
• your target platform is not linux
• you only need simple host metrics already covered by standard exporters

Facets

service · maturity active

monitoring tracing benchmarking monitoring cloud-computing operating-systems self-hosted go ebpf kernel-observability autotracing continuous-profiling kubernetes low-overhead cncf-landscape devops containers linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ccfos/huatuo")