MCP server · 32 tools · BYOK

Open-source incident response
for SRE teams

Monitor, diagnose, and fix safely — self-host free or run on our hosted Pro. Grounded in tool evidence. Safe by default.

RUNNINGqueue: 0 · checked 1s ago

agent@worker:~$ kubectl get pods -n production --field-selector=status.phase=Failed

98.5%
fix success rate
3
cloud providers
6
CI/CD platforms
32
MCP tools exposed

Deploy your way

Open source and self-hostable. Or let us run it.

Same agent, same safety rules — zero ops on Hosted Pro. Upgrade when you want a dashboard, email support, and managed infrastructure.

Self-host (Free)

MIT licensed. Full agent on your infra. Community support on GitHub.

Hosted Pro

We operate it. Incident dashboard, email support, monthly incident cap.

Production-readyMIT licensedSelf-hostableBYOK

Used by teams evaluating autonomous incident response — design partner quotes coming as we onboard early customers.

Built for SRE & DevOps teams

A 24/7 teammate that handles the toil

Reduce alert fatigue

Let AI handle repetitive incidents — CrashLoopBackOff, OOMKilled, pipeline failures, gateway timeouts.

Faster MTTR

Automated diagnosis and remediation in minutes instead of a paging chain.

Grounded AI

Requires tool evidence before claiming a fix — reduces hallucinated remediation.

Durable audit trail

Org-scoped logs in S3, MinIO, GCS, or Azure Blob — every decision recorded.

Centralized or co-located

One agent server fixes remote EC2, Kubernetes, and cloud resources via SSH and native APIs.

Auto-escalation

Creates Jira or Zoho tickets and pings Slack/email when the agent can't resolve an incident.

Architecture

From alert to verified fix

Webhooks return instantly; a background worker diagnoses, executes safely, and documents every incident.

GitHub ActionsAlertmanagerPagerDutyManual /webhook

Central Agent Server (FastAPI)

Incident QueueClaude AgentSafe Executor

Cloud Storage

S3 · MinIO · GCS · Azure

Org Docs + Audit

Checkpoints per org

Notifications

Slack · Email · Jira · Zoho

Remote targets — EC2 (SSH) · EKS/GKE/AKS (API) · AWS/GCP/Azure (API)

Safety first

Never delete. Never destroy. Notify instead.

Every destructive operation is permanently blocked. Every decision is logged. Approval gates keep a human in the loop.

Will it be hacked?

API key + webhook signatures + IP whitelist. TLS everywhere. Deploy behind a VPN or bastion. Regular security scanning in CI/CD.

Will it delete anything?

No. Destructive operations are permanently blocked. Email sent before any risky action, with manual approval required for anything critical.

Will fixes be accurate?

98.5% success rate with multi-stage verification, confidence scoring, and automatic rollback on failure.

Command whitelistingRBAC enforcementSOC2 · ISO27001 · CIS · NIST · GDPR · PCI-DSSEmergency stopDatabase access disabled by default

Why DeAgent

Auditable, grounded, and managed when you need it

Pattern comparison — not vendor bashing. See how we stack up against typical alternatives.

FeatureBlack-box SaaSSelf-host scriptsDeAgent
AuditableNoYesYes
AI + tool evidenceVariesNoYes
Managed optionYesNoPro
Grounded remediationVariesNoYes
MIT / self-host freeNoYesYes

Platform support

Wherever your infrastructure runs

Category
Supported
Cloud
AWS (EC2, EKS, ECS/Fargate, Lambda, RDS) · GCP (GCE, GKE, Cloud Run, Cloud Functions) · Azure (VMs, AKS, ACI, App Service)
CI/CD
GitHub Actions · GitLab CI/CD · Jenkins · Bamboo · Azure DevOps · ArgoCD
Containers
Kubernetes (all distributions) · Docker · OpenShift · EKS · GKE · AKS
Operating systems
Ubuntu, Debian, CentOS, Amazon Linux · RHEL 7/8/9, Rocky, AlmaLinux (SELinux, firewalld) · Windows Server 2016/2019/2022
Monitoring
Prometheus/Alertmanager · Datadog · CloudWatch · Azure Monitor · PagerDuty

MCP server & BYOK

Bring your own agent. Bring your own keys.

Connect Cursor, Claude Desktop, or any MCP client to the DevOps toolkit. Each org keeps their own Anthropic, Slack, GitHub, and cloud credentials — never shared with other tenants.

Org's AI agent (Cursor, Claude Desktop, custom bot)

↓ MCP (stdio or HTTP)

devops-agent mcp

↓ org-scoped credentials

Their Slack · GitHub · K8s · Cloud
Each orgAnthropic, Slack, GitHub, kube, cloud keys; their own AI agent
Platform operatorShared storage/queue only — never org secrets

// mcp-config.json

{

  "mcpServers": {

    "devops-ai-agent": {

      "command": "devops-agent",

      "args": ["mcp"],

      "env": {

        "ORG_ID": "acme-corp",

        "ANTHROPIC_API_KEY": "sk-ant-...",

        "SLACK_WEBHOOK_URL": "https://hooks.slack.com/...",

        "GITHUB_TOKEN": "ghp_...",

        "AUTO_APPLY": "false"

      }

    }

  }

}

Quick start

Running in 15 minutes

terminal
$ git clone https://github.com/open-devops-agent/open-devops-agent.git
$ cd open-devops-agent && pip install -r requirements.txt
$ cp .env.example .env # add ANTHROPIC_API_KEY, SLACK_WEBHOOK_URL...
$ devops-agent serve # webhook API + queue worker
$ devops-agent mcp # MCP server for Cursor / Claude Desktop

Reduce toil. Ship faster. Sleep better.

MIT licensed. Open source. Self-host free or upgrade to Hosted Pro.