DEV Community

Cover image for Show DEV: Stop Tab-Hopping at 2am — Open-Source APM With an AI Agent Squad
databufflabs
databufflabs

Posted on • Edited on • Originally published at github.com

Show DEV: Stop Tab-Hopping at 2am — Open-Source APM With an AI Agent Squad

#opensource #showdev #devops #opentelemetry

2:14am. Checkout P99 is on fire. Slack wants a root cause in 10 minutes.

You open Grafana. Jaeger. Logs. Topology. Notes doc. Twenty minutes later you think you know — but you're still not sure if it's order-service, MySQL, or that sketchy downstream RPC.

Metrics didn't fail you. The workflow did.

We built DataBuff — open-source, OpenTelemetry-native APM — to fix that: one question in, evidence-backed root cause out. Not a chat box glued to dashboards. An AI Brain that dispatches specialists (metrics, traces, topology, inspection) and merges real telemetry into an incident-ready answer.

DataBuff demo — AI chat, services, and topology

Try it first (5 minutes) 

curl -fsSL https://databuff.ai/databuff/ai-apm-install.sh | bash
curl -fsSL https://databuff.ai/databuff/ai-apm-demo-install.sh | bash
Enter fullscreen mode Exit fullscreen mode

Open http://YOUR_HOST:27403 — login admin / Databuff@123 — add LLM key under Settings → AI model.

Paste this:

Which services had errors in the last hour? For the slowest one,
show me a typical trace, the slowest span, and what I should do first.
Enter fullscreen mode Exit fullscreen mode

That's the product. Below: architecture, agent squad, and a real demo output.

Before vs after

Before (tab safari)

  • 5–6 tools, zero shared context
  • You translate the question into 12 queries
  • Senior engineer stitches the story by hand
  • Slack gets guesses and screenshots

After (DataBuff)

  • One UI, unified Doris storage
  • You ask in plain English
  • AI Brain + agents query live metrics, traces, topology
  • Slack gets root cause, TraceId, P0/P1 actions

You already pay for observability. You're still paying in human attention at 2am.

AI-native ≠ ChatGPT on Grafana

Most "AI observability" in 2024:

  • Only sees what you paste
  • Cannot query your trace store
  • Guesses under incident pressure

DataBuff agents call real tools. Every claim should trace to evidence.

The agent squad

  • AI Brain — plans, dispatches, synthesizes
  • Smart query — P99, error rate, QPS from Doris
  • Trace analyst — slow traces, hottest spans
  • Topology — upstream/downstream blast radius
  • Inspection — sustained pain vs one-off spikes
  • Report — incident summary you can forward

Apache 2.0 · self-hosted · data stays on your network.

Architecture: 3 components, not 13

Data flow: OTLP apps → Ingest (4317/4318) → Apache Doris → Web UI (:27403) + AI Brain

DataBuff architecture — Ingest, Doris, Platform + AI Brain

Legacy stack vs DataBuff

  • Components: 10+ → 3
  • RAM: 16 GB+ → ~8 GB
  • First deploy: 1–2 days → ~5 min (one install script)
  • Storage: siloed → unified Doris
  • AI: bolt-on chat → multi-agent native

OpenTelemetry in. Unified storage. Agents on top.

Product at a glance

OpenTelemetry APM and AI-native capabilities

Demo walkthrough

After demo install you get service-a → service-b with real traces.

1. Service health

Service list with traffic-light health status

2. Ask the hard question

Analyze why service-a calls slowed in the last 30 minutes.
Find highest-P99 endpoint, a typical slow trace, slowest span,
root cause (app vs DB vs downstream), impact, and P0 fixes.
Enter fullscreen mode Exit fullscreen mode

3. Watch agents work in parallel

AI natural language query

Multi-agent collaboration and dispatch

4. Real demo output

Smart query
  service-a GET /demo/checkout ~240ms avg (17 reqs)
  service-b HTTP 100ms + Dubbo 80ms ~ 75% of latency

Inspection
  Sustained slowness, not a spike; service-a JVM/errors normal

Trace 12e3a078bdbe183d567a2f7e888fe7b3
  Slowest span: service-b -> MySQL SELECT demo_order (~45ms)

Root cause
  Downstream service-b + slow SQL (not service-a)

P0: dedupe service-b double calls; fix MySQL slow queries
P1: fix InsufficientStockException on inventory path
Enter fullscreen mode Exit fullscreen mode

5. Topology proof

Global service topology

6. Call graph

Service call flow graph

vs SigNoz / Datadog

DataBuff wins on: multi-agent AI RCA built-in, OTel-native, self-host in minutes, you own the data.

SigNoz wins on: mature classic OSS APM, huge community.

Datadog wins on: SaaS polish, enterprise integrations.

We're betting the next moat is orchestrated agents on OTel data — for teams without a 24/7 SRE bench.

Who should try this?

  • Running OTel but still living in 5 tabs during incidents
  • Self-hosting (finance, gov, privacy-sensitive)
  • Want agents that use tools, not vibes
  • Apache 2.0 you can audit

Your turn 

curl -fsSL https://databuff.ai/databuff/ai-apm-install.sh | bash
curl -fsSL https://databuff.ai/databuff/ai-apm-demo-install.sh | bash
Enter fullscreen mode Exit fullscreen mode

GitHub: https://github.com/databufflabs/databuff

  1. What would you ask the agent squad first? (comment below)
  2. What OTel signals are we missing?
  3. Star the repo if 2am tab-hopping should die.

Top comments (0)