explaingit

databufflabs/databuff

Analysis updated 2026-05-18

★ 207VueAudience · ops devopsComplexity · 3/5Setup · moderate

TLDR

DataBuff is an open-source AI-native monitoring tool for microservices that uses OpenTelemetry for data collection and lets you troubleshoot production issues with plain-English AI queries.

Mindmap

mindmap
  root((DataBuff))
    Monitoring
      Service traces
      RED metrics
      Service topology
      Alert data
    AI features
      Natural language queries
      Multi-agent coordination
      MCP integration
    Integrations
      OpenTelemetry
      Cursor and Claude
      Prometheus
    Tech stack
      Vue frontend
      Apache Doris
      Docker and K8s
    Setup
      One-line install
      5 min to first trace
      LLM API key required
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Monitor all your microservices with full request tracing and a visual service topology map in one self-hosted tool.

USE CASE 2

Ask an AI assistant questions about your system health and get answers grounded in real traces and metrics.

USE CASE 3

Connect Claude or Cursor to your monitoring data via MCP to investigate production issues from your editor.

USE CASE 4

Deploy a full monitoring platform on Docker or Kubernetes and see traces from a live app in under 5 minutes.

What is it built with?

VueDockerKubernetesOpenTelemetryApache Doris

How does it compare?

databufflabs/databuffhuangdihd/call_me_as_agentw512/texodus
Stars2075025
LanguageVueVueVue
Setup difficultymoderateeasymoderate
Complexity3/52/52/5
Audienceops devopsdevelopergeneral

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 5min

Requires Docker and Docker Compose, you must supply an LLM API key to enable the AI features after installation.

In plain English

DataBuff is an open-source monitoring tool for software teams that run multiple interconnected services, often called microservices. It collects data about how your services behave, how fast they respond, where errors occur, and how they call each other, then uses an AI assistant to help you investigate problems using plain English questions. The monitoring side uses a standard called OpenTelemetry, which many programming frameworks already support. Once your services send data to DataBuff, it builds a visual map of all your services and their connections, tracks request rates and error counts, and records detailed traces of individual requests as they travel through your system. The AI side is designed to query that monitoring data directly rather than through a generic chat interface added on top. You can ask questions like "why is service X slow?" and it will look at the actual traces, metrics, and alerts to give you an answer based on real data. For complex problems it can coordinate multiple AI agents, each investigating a different aspect of the issue at the same time. DataBuff also exposes a connection point called MCP, which lets external AI tools like Cursor and Claude plug in and query your monitoring data directly. The README is primarily in Chinese and links to a live demo site. Installation requires Docker and Docker Compose. A one-line install script sets up the full platform in about 5 minutes, after which you visit the web interface at port 27403 and enter an AI model API key to enable the AI features. Kubernetes installation is also available. The system runs on three components: an ingest layer, Apache Doris as the data store, and a web frontend.

Copy-paste prompts

Prompt 1
How do I install DataBuff with Docker Compose and connect a Java microservice to send OpenTelemetry traces to it?
Prompt 2
Show me how to ask DataBuff's AI assistant why a specific service has a high error rate and what traces it uses to answer.
Prompt 3
How do I expose DataBuff's MCP endpoint so Claude Code can query my service metrics and traces directly?
Prompt 4
What is a service topology map in DataBuff and how do I read it to find which downstream service is causing slow responses?
Prompt 5
Can I add a custom AI skill to DataBuff to query a domain-specific metric without modifying the core code?

Frequently asked questions

What is databuff?

DataBuff is an open-source AI-native monitoring tool for microservices that uses OpenTelemetry for data collection and lets you troubleshoot production issues with plain-English AI queries.

What language is databuff written in?

Mainly Vue. The stack also includes Vue, Docker, Kubernetes.

How hard is databuff to set up?

Setup difficulty is rated moderate, with roughly 5min to a first successful run.

Who is databuff for?

Mainly ops devops.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub databufflabs on gitmyhub

Verify against the repo before relying on details.

Alternatives & similar repos