# deepflowio/deepflow

eBPF Observability - Distributed Tracing and Profiling

Repository: https://github.com/deepflowio/deepflow
Canonical: https://ross.abutalabs.com/products/deepflow
Homepage: https://deepflow.io
Language: Go
License: Apache-2.0
License Family: permissive
Topics: opentelemetry, kubernetes, wasm, apm, gpu, llm, zero-code
Last push: 2026-08-26T09:47:52+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 97, longevity 100
- inputs: {"age_days": 1690, "days_push": 7, "days_rel": 20, "gap_med": 18, "n_releases_24m": 22}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4244, forks 482 (observed 2026-08-28T04:08:40.338000+00:00)

## What it is
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
- artifact type: service
- maturity: active
- function: monitoring, tracing, logging, benchmarking
- domain: monitoring, cloud-computing, microservices
- platform: cloud, self-hosted, go
- tags: ebpf, apm, opentelemetry, continuous-profiling, zero-instrumentation, distributed-tracing, gpu-profiling, wasm-plugins, prometheus, observability, devops, containers, linux, kubernetes, docker

## Member repositories
- deepflowio/deepflow (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:40.338000+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:12.936961+00:00, confidence not recorded.
  - readme: https://github.com/deepflowio/deepflow (fetched 2026-08-28T04:08:40.338000+00:00, sha e3c8dbe31b68)
  - homepage: https://deepflow.io (fetched 2026-08-29T09:11:59.827809+00:00, sha 3e665af65b47)
  - site_page: https://deepflow.io/docs (fetched 2026-08-29T09:11:59.858373+00:00, sha 1ff476a46762)
- Data as of 2026-08-30T08:39:29.467469+00:00.