deepflowio/deepflow

Health v2 · maintenance only

Adoption not part of the score

4244 stars · 482 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

DeepFlow is an open-source eBPF-based observability platform providing zero-code distributed tracing, metrics, request logs, and continuous profiling for cloud-native and AI applications. It correlates full-stack observability data via SmartEncoding and integrates as a storage backend for Prometheus, OpenTelemetry, SkyWalking, and Pyroscope.

Use cases

• add distributed tracing to microservices without instrumenting code
• monitor kubernetes cluster performance with ebpf
• profile cpu and gpu functions in production with low overhead
• build a universal service map of all services and infrastructure
• store opentelemetry and prometheus data in one observability backend
• troubleshoot slow requests across gateways, service meshes, and databases
• observe llm and ai application performance

When to choose

• you want full-stack observability without code instrumentation
• you run kubernetes or cloud-native microservices in any language
• you need tracing, metrics, and profiling correlated in one platform
• you want to profile including kernel and CUDA functions

When to avoid

• you only need simple application-level metrics already covered by your APM
• you cannot run eBPF agents on your hosts or kernel
• you need a lightweight single-host monitoring tool
• your environment is non-Linux without eBPF support

Facets

service · maturity active

monitoring tracing logging benchmarking monitoring cloud-computing microservices cloud self-hosted go ebpf apm opentelemetry continuous-profiling zero-instrumentation distributed-tracing gpu-profiling wasm-plugins prometheus observability devops containers linux kubernetes docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="deepflowio/deepflow")