Doctor Droid
AI SRE agent that investigates incidents with full infrastructure context — plus open-source tooling.
About
DrDroid (drdroid.io) is an AI SRE agent for incident response and root-cause analysis. Its core idea: before the first investigation, it connects to your existing tools and builds a complete context graph — services, repositories, deployments, dependencies, clusters, logs, metrics, traces, and team ownership — so the agent investigates the way your best engineer would, correlating across signals instead of bouncing between dashboards. Any engineer can run a senior-level RCA; proactive checks can be written in plain English and scheduled on cron to catch cross-signal degradation no single alert would fire on. Notably, it open-sources key pieces: droidctx (an infrastructure context builder for Claude Code and coding agents) and Playbooks (github.com/droidops/playbooks), and its agent keeps a continuous learning layer that remembers past incidents per entity.
The honest picture: the 'context graph first, agent second' architecture is the right shape for this problem, and open-sourcing droidctx is a genuine contribution. As with all RCA agents, output quality tracks input coverage — thin integrations mean thin conclusions — and the vendor is early, so enterprise proof points are still accumulating.
What it can do
- Infrastructure context graph across services, repos, deploys, and ownership
- Natural-language incident investigations with evidence trails
- Plain-English proactive checks on cron for silent failures
- Open source: droidctx context builder + Playbooks repo
- Continuous learning layer remembering past incidents per entity
Setup
Sign up at drdroid.io and connect your tools (Kubernetes, GitHub, Datadog, Grafana, ArgoCD, etc.) read-only. The context graph builds automatically; ask questions in natural language or schedule plain-English proactive checks.
Prerequisites
Read-only access to your observability and infra tools; a DrDroid account.
Use cases
Works with
Trust score — 6/10
Scored 6/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 58; Trending score 62/100 from researcher assessment.
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.