What is AI-powered incident management?

AI-powered incident management uses intelligent agents to automate incident response tasks like alert triage, runbook execution, root cause analysis, and team notifications. Instead of relying solely on on-call engineers, AI agents can handle initial diagnosis and remediation steps 24/7, reducing MTTR and on-call burnout.

Is Akmatori open source?

Yes, Akmatori is an Apache 2.0 open-source project. You can inspect the code, run it on your own infrastructure using Docker or Kubernetes, and keep complete control over your data and incident workflows.

What LLM providers does Akmatori support?

Akmatori supports multiple LLM providers including OpenAI (GPT-4), Anthropic (Claude), Google (Gemini), and OpenRouter. You can also use on-premise models like Mistral, GLM, Kimi, or Minimax for data sovereignty requirements.

How does Akmatori integrate with PagerDuty?

Akmatori integrates with PagerDuty via webhooks and the PagerDuty API. When an incident is triggered, Akmatori's AI agents can automatically acknowledge alerts, gather context from your observability stack, execute diagnostic runbooks, and post updates to incident channels.

Can Akmatori reduce on-call burnout?

Yes. Akmatori handles routine incidents autonomously, filters alert noise, and only escalates to human engineers when necessary. This significantly reduces the number of pages during off-hours and allows SRE teams to focus on high-impact work instead of repetitive troubleshooting.

What observability tools does Akmatori work with?

Akmatori ingests alerts from Prometheus Alertmanager, Grafana, Datadog, Zabbix, and PagerDuty, and can monitor Slack channels. AI agents reach your infrastructure through real tools such as SSH and Kubernetes to diagnose issues.

November 8, 2026

Akmatori vs HolmesGPT: Which Open-Source AI SRE Agent Fits Your Team?

Akmatori vs HolmesGPT: Open-Source AI SRE Agents

HolmesGPT and Akmatori are both open-source AI agents that investigate production incidents on infrastructure you control. Both are Apache-2.0, both read your metrics, logs and clusters through tools, and both keep risky actions behind human approval. The difference is in the shape of the product: HolmesGPT is an investigation engine with a CLI, an HTTP API and an in-cluster operator, while Akmatori is a complete incident service with alert intake, a web dashboard, Slack, runbooks and memory in one install.

We build Akmatori, so read this with that in mind. We have tried to state what HolmesGPT does better as clearly as what we do better. All HolmesGPT facts below come from its GitHub repository and documentation as of November 2026. For a full introduction, see our earlier post on HolmesGPT as a CNCF SRE agent.

At a Glance

	HolmesGPT	Akmatori
License	Apache-2.0	Apache-2.0
Governance	CNCF Sandbox (since October 2025)	Single vendor (Akmatori team, powered by Gcore)
Community	About 3.8k GitHub stars, very active	Young project, first release in 2026
How you run it	CLI, HTTP server, Kubernetes operator	Docker Compose service with web UI
Alert intake	Alertmanager via Robusta or CLI; PagerDuty, OpsGenie, Jira, GitHub via CLI	Webhooks for Alertmanager, Grafana, PagerDuty, Datadog, Zabbix; Slack channel monitoring; cron jobs
Investigation tools	38+ built-in toolsets, MCP, custom REST toolsets	SSH, Kubernetes, Zabbix, Grafana, VictoriaMetrics, PagerDuty, NetBox, databases, HTTP connectors, remote MCP
Models	OpenAI, Anthropic, Azure, Bedrock, Gemini, Vertex, OpenRouter, OpenAI-compatible; Ollama experimental	OpenAI, Anthropic, Google, OpenRouter, NVIDIA NIM, MiniMax, any OpenAI-compatible endpoint
Write actions	Read-only by default; optional remediation MCP with human approval	Read-only SSH by default; risky actions become proposals approved in UI or Slack
Slack	Third-party bot via Robusta	Built in
Web UI	Not part of the open-source project	Built in
Memory	Not a core feature	Runbook search and cross-incident memory

Where HolmesGPT Is Stronger

Neutral governance and a bigger community. HolmesGPT is a CNCF Sandbox project, and its README names Microsoft as a major contributor. If your company only adopts open source with foundation governance, that settles the question.

Toolset breadth. HolmesGPT ships more than 38 toolsets, including Datadog, New Relic, Splunk, Elasticsearch, Tempo, cloud providers, ArgoCD, Kafka and Zabbix. If your stack is wide, you may find more of it covered out of the box.

Embedding. A CLI and an HTTP API make HolmesGPT easy to put inside your own tools: call it from a script, a chatbot or an internal portal. The operator mode runs scheduled health checks inside the cluster.

Where Akmatori Is Stronger

It is the whole incident loop, not only the investigation. Akmatori receives alerts directly from Alertmanager, Grafana, PagerDuty, Datadog and Zabbix, groups related alerts into one incident, runs the investigation, posts to Slack, and tracks the incident until the source resolves it. With HolmesGPT, the intake, the UI and the Slack bot come from Robusta or from your own glue code.

Memory across incidents. Before Akmatori touches infrastructure, the agent searches your runbooks and what it learned from earlier incidents, and it writes durable lessons back after each one. The second time a disk fills on the same host, the agent starts from the previous answer.

Built for mixed estates. Akmatori's first-class tools include read-only SSH, Zabbix and NetBox, which matters for teams with many Linux servers and not only Kubernetes.

Measured models. We run SRE Bench, 12 real incidents on a fresh Akmatori install per model, so you can pick a model by measured root-cause accuracy and cost per solved incident instead of by guess.

The Robusta Question

HolmesGPT was created by Robusta, and Robusta's commercial platform provides its alert intake, UI and Slack bot. On October 28, 2026, Freshworks announced it acquired Robusta to bring it into Freshservice. The announcement does not mention HolmesGPT. The open-source project continues under CNCF with its own repository, but if you planned to use Robusta around it, check the roadmap before you commit. We cover Robusta separately in Akmatori vs Robusta.

How to Choose

Choose HolmesGPT if:

You want CNCF governance and the largest open-source community in this category.
You will build your own interface around an investigation engine.
Your stack needs a toolset that only HolmesGPT has today.

Choose Akmatori if:

You want alerts in, root cause out, with a dashboard and Slack, from one docker compose up.
You run Linux servers, Zabbix or NetBox next to Kubernetes.
You want the agent to remember past incidents and follow your runbooks.

You can also try both on the same alert. Both are free, both run on your infrastructure, and both can use the same model key.

Conclusion

HolmesGPT is a strong, well-governed investigation engine. Akmatori is a complete self-hosted incident agent with intake, approvals, Slack and memory included. The right choice depends on whether you want a component to build on or a service to run. To see Akmatori on a real HTTP 502 incident, watch the 3-minute demo or start with the getting started guide.

If your team wants AI-assisted incident workflows on your own infrastructure, Akmatori helps SRE teams investigate alerts, coordinate response, and automate safe infrastructure actions. Powered by Gcore for global infrastructure reliability.

Akmatori team