Self-host OpenSRE
v1.2.8Memory-first AI SRE for automated incident investigation
- Stars
- 169
- CPU
- 4 vCPUs
- RAM
- 8GB RAM
- Ports
- 3000 (Web UI (Next.js admin console)), 8000 (SRE Agent API (Claude Agent SDK)), 8080 (Config Service API), 5432 (PostgreSQL database), 7474 (Neo4j HTTP/Browser interface), 7687 (Neo4j Bolt protocol), 3978 (Microsoft Teams bot), 4000 (LiteLLM proxy (optional))
- Requires
- Neo4j, PostgreSQL
What is OpenSRE?
OpenSRE is an open-source platform that automates production incident investigation. Its AI agent uses the Claude Agent SDK to load skills dynamically and dispatch subagents that query observability tools such as Kubernetes, Prometheus, Grafana, Datadog, Elasticsearch, Splunk, Jaeger, Sentry, and PagerDuty. Each investigation is stored as an episode in Neo4j, enabling similarity-based recall for future incidents. A Neo4j knowledge graph tracks service dependencies for blast radius analysis. Deployment uses Docker Compose or a Kubernetes Helm chart, with PostgreSQL handling configuration and investigation traces, and Neo4j powering memory and the graph. The web console provides investigation views, a memory browser, and a configuration editor. Users authenticate via token or Microsoft Entra SSO. Optional Slack and Teams bots provide chat-based investigation triggers. The project is licensed under Apache 2.0.
Should you self-host OpenSRE?
OpenSRE scores 48/100 on selfhost.directory (how scoring works) and ranks #52 of 120 in AI Assistant. It has 169 GitHub stars.
It shipped 10 stable releases in the past year. The latest, v1.2.8, came out on 12 October 2026. New versions land roughly every 3 days.
Setup is advanced: plan for several services and some ongoing maintenance. It is Apache-2.0-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is hermes-agent (89/100, 258 015 stars). It scores higher overall, so compare the two before you pick. See OpenSRE vs hermes-agent side by side.
Features
- 51 production skills
- Air-gapped deployment support
- Automated Incident Investigation
- Custom skill authoring
- Episodic memory
- Knowledge Graph
- Microsoft Entra SSO
- Microsoft Teams bot
- Multi-agent architecture
- Multi-Provider LLM Support
- Progressive skill loading
- Real-time SSE streaming
- Slack integration
- Web Console
OpenSRE README
FAQ
What infrastructure does OpenSRE.in need?
OpenSRE.in requires Docker and Docker Compose for local development. In production, it runs on Kubernetes via a Helm chart. Core dependencies are PostgreSQL, Neo4j, and LiteLLM. A small setup runs on 4 vCPUs and 8GB RAM.
How do I set up OpenSRE.in?
Clone the repository, create a .env file with your OPENROUTER_API_KEY, and run make dev. This starts all services including PostgreSQL, Neo4j, the sre-agent, and the web console at http://localhost:3002.
Can OpenSRE.in replace our on-call rotation?
OpenSRE.in augments on-call engineers, not replaces them. It handles the investigation phase autonomously; the on-call engineer validates findings and implements fixes.
What's the cost of running OpenSRE.in?
OpenSRE.in itself is free and open-source. The main costs are infrastructure (PostgreSQL, Neo4j, agent services) and LLM API usage.
Is OpenSRE.in production-ready?
OpenSRE.in is actively used in production environments, runs as Docker Compose services or Kubernetes via Helm chart, and has been tested with real production incident investigation scenarios.
How is OpenSRE.in different from PagerDuty AI or Rootly AI?
OpenSRE.in is open-source (Apache 2.0) and self-hosted, while PagerDuty and Rootly are commercial SaaS. Key differentiators are memory (learns from every incident) and Neo4j knowledge graph (maps service topology for blast radius analysis).
How does OpenSRE.in reduce MTTR?
OpenSRE.in automates the investigation phase — gathering context, forming hypotheses, querying tools — starting the moment an alert fires and running multiple investigation threads in parallel.
How does OpenSRE.in connect to my observability stack?
OpenSRE.in connects via integration configuration in litellm_config.yaml and the config-service. Each integration has a URL and credentials. Agents query these directly during investigations.
Can I add custom investigation skills?
Yes, skills are defined as directories in .claude/skills/ with a SKILL.md describing tools and context, plus executable scripts. Any tool your engineers use can become an investigation skill.
What integrations are supported?
OpenSRE.in integrates with Kubernetes, Prometheus, Grafana, Datadog, New Relic, Elastic/ELK, Splunk, Jaeger, Sentry, PagerDuty, OpsGenie, Slack, GitHub, Confluence, and LLM providers via LiteLLM.
There are two projects named OpenSRE.in — which one is this?
This is OpenSRE.in — the memory-first AI SRE, a self-hosted team platform with team memory, knowledge graph, web console, and Slack/Teams entry points. It is not affiliated with Tracer's OpenSRE at opensre.com.
More in DevOps
OxMgrSelf-hosted Rust process manager replacing PM2 — runs any executable on Linux, macOS, Windows with health checks, resource limits, and a live terminal dashboard.
portabaseSelf-hosted, open-source database backup tool where agents dump PostgreSQL, MySQL, MongoDB and more on a cron, with GFS retention, S3/SFTP storage and restores.
prom-alertmanagerOpen-source Prometheus alert hub: deduplicates, groups, routes and silences alerts to Slack, PagerDuty, email or webhooks; self-hosted with a Docker image or binaries.
ptah-serverSelf-hosted Fair Source PaaS replacing Heroku/Vercel, using Docker Swarm for apps, databases, backups, and SSL. Archived, development paused.
PulumiOpen-source infrastructure-as-code CLI and engine for AWS, Azure, GCP and Kubernetes in TypeScript, Python or Go, with self-hosted state in S3 or PostgreSQL.
rackOpen-source, self-hosted PaaS that runs your apps on a Kubernetes cluster inside your cloud account, adding autoscaling, instant rollbacks, and a Heroku-like CLI.
Red Hat QuaySelf-hosted, open-source container image registry that stores OCI artifacts, scans with Clair, and runs standalone on Podman or on Kubernetes via the Quay Operator.- RhodeCodeRhodeCode is an open-source, self-hosted platform for unified repository management, supporting Git, Mercurial, and Subversion. It provides enterprise-grade security, code review, workflow automation, and permission management for teams.
roterote is a self-hosted, open-source CLI cron replacement that captures stdout/stderr, records exit codes and timing, and provides a live terminal dashboard.
RundeckEnable Self-Service Operations: Give specific users access to your existing tools, services, and scripts
scanopyNetwork diagrams that update themselves
sensu-goSelf-hosted, open-source monitoring with auto-discovery for cloud environments, using service checks and an observability pipeline to collect and transform telemetry.
0 comments