agent-dd

Datadog triage CLI for AI agents

Language
Go
Version
0.3.3
License
MIT
Category
CLI Tool
View on GitHub

A Datadog CLI designed for AI agent investigation workflows — monitors, logs, metrics, traces, incidents, and SLOs. Structured output with classified errors so agents can self-correct, and multi-org support for switching between Datadog organizations.

Features

01

Token-efficient output — NDJSON for lists, JSON for single items, YAML available

02

Structured error classification — every error includes fixable_by: agent|human|retry

03

Triage-focused — only the commands you need during an investigation

04

Multi-org support — switch between Datadog organizations with --org

05

Self-documenting — agent-dd llm-help for agent-friendly reference

06

Single compiled Go binary — no runtime dependencies

Install

Homebrew

>_ 
$ brew install shhac/tap/agent-dd

AI Agent Skill

>_ 
$ npx skills add shhac/agent-dd

GitHub Release (macOS)

>_ 
$ curl -L https://github.com/shhac/agent-dd/releases/latest/download/agent-dd-darwin-arm64.tar.gz | tar xz

Go Install

>_ 
$ go install github.com/shhac/agent-dd/cmd/agent-dd@latest

Build from Source

>_ 
$ git clone https://github.com/shhac/agent-dd.git && cd agent-dd && make build

Getting Started

agent-dd needs Datadog API and application keys before it can query anything. Store credentials per organization for easy multi-org switching.

01 · Add your Datadog organization

>_ 
$ agent-dd org add prod --api-key YOUR_API_KEY --app-key YOUR_APP_KEY --site datadoghq.com

Keys are stored in macOS Keychain when available. Use --site for EU or other Datadog regions.

02 · Test the connection

>_ 
$ agent-dd org test

03 · List monitors

>_ 
$ agent-dd monitors list

Returns NDJSON by default for token-efficient streaming.

Usage

>_ List triggered monitors 
$ agent-dd monitors list --status triggered
>_ Search logs 
$ agent-dd logs search "service:api status:error" --from 1h
>_ Query a metric 
$ agent-dd metrics query "avg:system.cpu.user{env:prod}" --from 1h
>_ List active incidents 
$ agent-dd incidents list
>_ Get SLO status 
$ agent-dd slo list
>_ Search traces 
$ agent-dd traces search "service:checkout @duration:>5s"