Tracer-Cloud/opensre

🚧 Public Alpha: Core workflows are usable for early exploration, though not yet fully stable. The project is in active development, and APIs and integrations may evolve.

Make sure you have:

• A terminal open in a code project
• A Git repository (recommended for the full workflow demonstration)

macOS or Linux:

curl -fsSL https://install.opensre.com | bash -s -- -gh

Windows (PowerShell):

& ([scriptblock]::Create((irm https://install.opensre.com/install.ps1))) -gh

Then start OpenSRE:

opensre

Windows details: Windows.

The installer fetches the latest build from main without requiring sudo. If opensre is not found, follow the PATH instructions printed by the installer or open a new terminal.

For supported platforms and troubleshooting, see Install locally.

• Before you begin
• Install and start opensre
• Why OpenSRE?
• Quick Start
• Deployment
• How OpenSRE Works
• Capabilities & integrations
• Contributing & development
• Security
• Telemetry
• License
• Citations

When something breaks in production, the evidence is scattered across logs, metrics, traces, runbooks, and Slack threads. OpenSRE is an open-source framework for AI SRE agents that resolve production incidents, built to run on your own infrastructure.

We do that because SWE-bench¹ gave coding agents scalable training data and clear feedback. Production incident response still lacks an equivalent.

Distributed failures are slower, noisier, and harder to simulate and evaluate than local code tasks, which is why AI SRE, and AI for production debugging more broadly, remains unsolved.

OpenSRE is building that missing layer:

an open reinforcement learning environment for agentic infrastructure incident response, with end-to-end tests for realistic production failures

We do that by:

• building easy-to-deploy, customizable AI SRE agents for production operations and incident response
• running real-world end-to-end tests across cloud-backed scenarios (tests/e2e)
• keeping semantic test-catalog naming so e2e vs unit and local vs cloud boundaries stay obvious (tests/README.md)

Our mission is to build AI SRE agents on top of this, scale it to thousands of realistic infrastructure failure scenarios, and establish OpenSRE as the benchmark and training ground for AI SRE.

¹ https://arxiv.org/abs/2310.06770

Contributors: start at main.py for the process entrypoint map.

Run opensre to sign in and get started. The first launch activates the hosted model.

opensre

Webapp contributors can run opensre setup --dev to authenticate through http://localhost:3000.

Interactive shell — with no subcommand, opensre validates your account and starts a REPL (TTY required). You can exit and stay signed out, but the shell only opens for an active account. Describe incidents in plain language, watch the agent work, and use slash commands for session control (/help, /status, /cost, /sessions, /resume, /compact, /new, /exit) and integrations (/integrations list, /integrations verify). Ctrl+C cancels an in-flight turn without losing session state. See interactive shell commands for the full reference.

Headless CLI — run one agent turn non-interactively from a terminal, script, or CI job:

opensre ask "why is checkout-api slow?"

See Headless CLI for stdin prompts, JSON output, and tool approvals.

From Python — drive the agent in-process from your own code (source checkout required):

from bootstrap.embedded import start_embedded_session

session = start_embedded_session()
result = session.chat("why is checkout-api slow?")
if result.answered:
    print(result.primary_response_text)

See Python API for sessions, conversations, and custom output sinks.

For your team's daily loop: embed OpenSRE in the Python services and automations your teammates already use. Start with the in-repo Python API guide, then use it every day to make incident response repeatable.

Other useful commands:

opensre integrations setup
opensre update
opensre uninstall   # remove opensre and all local data

An OpenSRE Cloud managed gateway, an AWS EC2 path, and a general self-hosted option:

• OpenSRE Cloud managed gateway: an organization admin provisions it in the web app; signed-in shell users can check, start, or stop it without handling infrastructure credentials locally.
• Gateway (AMI + systemd): make build-gateway-image then make deploy-gateway — Telegram gateway only, no Docker; the gateway is installed into a server image that new servers start from.
• Self-hosted container (Railway / ECS / Vercel): deploy the repo Dockerfile, select MODE, and set LLM_PROVIDER plus its API key. Use DATABASE_URL only when the gateway needs shared Postgres-backed state, such as Slack Events API replicas.

Full deployment steps and prerequisites → DEPLOYMENT.md

When you ask a question or an alert arrives, OpenSRE automatically:

1. Fetches the relevant context and correlated logs, metrics, traces, and recent deploys
2. Masks sensitive identifiers (optional) before external LLM calls
3. Reasons across your connected systems to test hypotheses in a tool-calling loop
4. Answers with an evidence-linked response in the conversation
5. Suggests next steps and, optionally, executes remediation actions
6. Posts a summary directly to Slack, PagerDuty, or Telegram — no context switching needed

For the current code-level agent architecture after removing the old graph and chain framework layers, see AGENTS.md.

OpenSRE connects to 60+ tools across LLMs, observability, cloud infrastructure, data platforms, incident management, and MCP. The full matrix (with roadmap links) lives in the product docs; a detailed catalog is also maintained in-repo as the project grows.

OpenSRE connects to 60+ tools and services across the modern cloud stack, from LLM providers and observability platforms to infrastructure, databases, and incident management.

Category	Integrations	Roadmap
AI / LLM Providers	Anthropic · OpenAI · OpenAI Codex · Ollama · Google Gemini · OpenRouter · TrustedRouter · NVIDIA NIM · Bedrock
Observability	Grafana (Loki · Mimir · Tempo · annotations) · Datadog · Honeycomb · Coralogix · groundcover · CloudWatch · Sentry · Elasticsearch · Better Stack · Splunk · Victoria Logs · SignOz · OpenObserve · OpenSearch · Azure Monitor · New Relic
Infrastructure	Kubernetes · AWS (S3 · Lambda · EKS · EC2 · CloudTrail · Bedrock) · Azure · ArgoCD · Helm
Database	MongoDB · ClickHouse · PostgreSQL · MySQL · MariaDB · MongoDB Atlas · Azure SQL · Snowflake · Redis · RDS · Supabase
Data Platform	Apache Airflow · Apache Kafka · Prefect · RabbitMQ · Dagster · Temporal
Dev Tools	GitHub · GitHub MCP · Bitbucket · GitLab · Jenkins
Incident Management	PagerDuty · Opsgenie · Jira · Alertmanager · incident.io · ServiceNow · Trello (client helpers only)	Linear
Communication	Slack · Google Docs · Discord · Telegram · Rocket.Chat · WhatsApp · Buzz	Notion · Teams · Confluence
Agent Deployment	Vercel · EC2 · ECS · Railway
Protocols	MCP

OpenSRE is community-built. Looking for a safe first contribution? Browse good first issue tickets or see the Good First Issues guide. See CONTRIBUTING.md for the full workflow.

Local environment: SETUP.md (all platforms, Windows, MCP).

Developing in this repo: docs/DEVELOPMENT.md (install from source, CI parity checks, dev container, deployment detail, telemetry reference).

Thanks goes to these amazing people:

OpenSRE is designed with production environments in mind: structured and auditable LLM prompts, local transcript handling by default, and no silent bulk export of raw logs. See SECURITY.md for responsible disclosure.

First-party product analytics and Sentry (errors) are opt-out. Quick disable:

export OPENSRE_NO_TELEMETRY=1

Full matrix, DSN override, and local event logging → docs/DEVELOPMENT.md

Apache 2.0 — see LICENSE.

¹ https://arxiv.org/abs/2310.06770