[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74042":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":38,"readmeContent":39,"aiSummary":40,"trendingCount":16,"starSnapshotCount":16,"syncStatus":41,"lastSyncTime":42,"discoverSource":43},74042,"opensre","Tracer-Cloud\u002Fopensre","Tracer-Cloud","Build your own AI SRE agents. The open source toolkit for the AI era.","https:\u002F\u002Fopensre.com",null,"Python",6762,901,31,74,0,265,523,1047,795,39.87,"Apache License 2.0",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37],"ai-sre","alerting","datadog","grafana","incident-management","observability","remediation","root-cause-analysis","site-reliability-engineering","slack","sre","2026-06-12 02:03:21","\u003Cdiv align=\"center\">\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Flogo\u002Fopensre-logo-white.svg\" alt=\"OpenSRE\" width=\"360\" \u002F>\n\u003C\u002Fp>\n\n\u003Ch1>OpenSRE v0.1: Build Your Own AI SRE Agents\u003C\u002Fh1>\n\n\u003Cp>The open-source framework for AI SRE agents, and the training and evaluation environment they need to improve. Connect the 60+ tools you already run, define your own workflows, and investigate incidents on your own infrastructure.\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Factions\u002Fworkflows\u002Fci.yml?branch=main\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002FTracer-Cloud\u002Fopensre\u002Fci.yml?branch=main&style=for-the-badge\" alt=\"CI status\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Freleases\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002FTracer-Cloud\u002Fopensre?include_prereleases&style=for-the-badge\" alt=\"GitHub release\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-blue.svg?style=for-the-badge\" alt=\"Apache 2.0 License\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002F7NTpevXf7w\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Us-5865F2?style=for-the-badge&logo=discord&logoColor=white\" alt=\"Discord\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F25889\" target=\"_blank\">\n    \u003Cimg\n      src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F25889\"\n      alt=\"Tracer-Cloud%2Fopensre | Trendshift\"\n      style=\"height: 30px; width: auto;\"\n      height=\"30\"\n    \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cstrong>\n    \u003Ca href=\"https:\u002F\u002Fwww.opensre.com\u002Fdocs\u002Fquickstart\">Quickstart\u003C\u002Fa> ·\n    \u003Ca href=\"https:\u002F\u002Fwww.opensre.com\u002Fdocs\">Docs\u003C\u002Fa> ·\n    \u003Ca href=\"https:\u002F\u002Fopensre.com\u002Fdocs\u002Ffaq\">FAQ\u003C\u002Fa> ·\n    \u003Ca href=\"https:\u002F\u002Ftrust.tracer.cloud\u002F\">Security\u003C\u002Fa>\n  \u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\n---\n\n> 🚧 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\n\n---\n\n## Table of Contents\n\n- [Why OpenSRE?](#why-opensre)\n- [Install](#install)\n- [Quick Start](#quick-start)\n- [Deployment](#deployment)\n- [How OpenSRE Works](#how-opensre-works)\n- [Benchmark](#benchmark)\n- [Capabilities & integrations](#capabilities--integrations)\n- [Contributing & development](#contributing--development)\n- [Security](#security)\n- [Telemetry](#telemetry)\n- [License](#license)\n- [Citations](#citations)\n\n---\n\n## Why OpenSRE?\n\nWhen 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.\n\nWe do that because SWE-bench\u003Csup>1\u003C\u002Fsup> gave coding agents scalable training data and clear feedback. Production incident response still lacks an equivalent.\n\nDistributed 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.\n\nOpenSRE is building _that_ missing layer:\n\n> an open reinforcement learning environment for agentic infrastructure incident response, with end-to-end tests and synthetic incident simulations for realistic production failures\n\nWe do that by:\n\n- building easy-to-deploy, customizable AI SRE agents for production incident investigation and response\n- running scored synthetic RCA suites that check root-cause accuracy, required evidence, and adversarial red herrings [(tests\u002Fsynthetic)](tests\u002Fsynthetic\u002Frds_postgres)\n- running real-world end-to-end tests across cloud-backed scenarios including Kubernetes, EC2, CloudWatch, Lambda, ECS Fargate, and Flink [(tests\u002Fe2e)](tests\u002Fe2e)\n- keeping semantic test-catalog naming so e2e vs synthetic and local vs cloud boundaries stay obvious [(tests\u002FREADME.md)](tests\u002FREADME.md)\n\nOur 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.\n\n\u003Csup>1\u003C\u002Fsup> https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.06770\n\n---\n\n## Install\n\nThe root installer URL auto-detects Unix shell vs PowerShell. Add `--main` when you want the latest rolling build from `main` instead of the latest stable release.\n\nLatest stable release:\n\n```bash\ncurl -fsSL https:\u002F\u002Finstall.opensre.com | bash\n```\n\nLatest build from `main`:\n\n```bash\ncurl -fsSL https:\u002F\u002Finstall.opensre.com | bash -s -- --main\n```\n\nHomebrew:\n\n```bash\nbrew tap tracer-cloud\u002Ftap\nbrew install tracer-cloud\u002Ftap\u002Fopensre\n```\n\nWindows (PowerShell):\n\n```powershell\nirm https:\u002F\u002Finstall.opensre.com | iex\n```\n\n\u003C!--\n```bash\npipx install opensre\n``` -->\n\n---\n\n## Quick Start\n\nConfigure once, then pick how you want to run investigations:\n\n```bash\nopensre onboard\n```\n\n**Interactive shell** — with no subcommand, `opensre` starts a REPL (TTY required). Describe incidents in plain language, stream investigations, and use slash commands such as `\u002Fhelp`, `\u002Fstatus`, `\u002Fclear`, `\u002Freset`, `\u002Ftrust`, `\u002Feffort`, `\u002Fexit`. `\u002Feffort` sets reasoning depth for **OpenAI** and **Codex** providers (`low`, `medium`, `high`, `xhigh`, or `max`; other providers ignore it). Ctrl+C cancels an in-flight investigation without losing session state.\n\n```bash\nopensre\n```\n\n**One-shot investigation** — run the agent once against an alert file:\n\n```bash\nopensre investigate -i tests\u002Fe2e\u002Fkubernetes\u002Ffixtures\u002Fdatadog_k8s_alert.json\n```\n\nOther useful commands:\n\n```bash\nopensre update\nopensre uninstall   # remove opensre and all local data\n```\n\n---\n\n## Deployment\n\nDeploy OpenSRE as a standard Python\u002FFastAPI runtime using the repo `Dockerfile` or a managed app host such as Railway, EC2, ECS, or Vercel. Set `LLM_PROVIDER` plus the matching API key (see [`.env.example`](.env.example)); hosted layouts that need persistence should also configure `DATABASE_URI` and `REDIS_URI`.\n\n**[Full deployment steps, Railway notes, and `opensre remote ops` → docs\u002FDEVELOPMENT.md](docs\u002FDEVELOPMENT.md#deployment)**\n\n---\n\n## How OpenSRE Works\n\n\u003Cimg\n  src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F936ab1f2-9bda-438d-9897-e8e9cd98e335\"\n  width=\"1064\"\n  height=\"568\"\n  alt=\"opensre-how-it-works-github\"\n\u002F>\n\nWhen an alert fires, OpenSRE automatically:\n\n1. **Fetches** the alert context and correlated logs, metrics, and traces\n2. **Reasons** across your connected systems to identify anomalies\n3. **Generates** a structured investigation report with probable root cause\n4. **Suggests** next steps and, optionally, executes remediation actions\n5. **Posts** a summary directly to Slack or PagerDuty — no context switching needed\n\nFor the current code-level agent architecture after removing the old graph and chain\nframework layers, see [AGENT_ARCHITECTURE.md](AGENT_ARCHITECTURE.md).\n\n---\n\n## Benchmark\n\nRegenerate numbers with **`make benchmark`**; refresh this table from cached results via **`make benchmark-update-readme`**. See **[docs\u002FDEVELOPMENT.md](docs\u002FDEVELOPMENT.md#benchmark)** for details.\n\n\u003C!-- BENCHMARK-START -->\n\n_No benchmark results yet._\n\n\u003C!-- BENCHMARK-END -->\n\n---\n\n## Capabilities & integrations\n\n|                                          |                                                                                  |\n| ---------------------------------------- | -------------------------------------------------------------------------------- |\n| 🔍 **Structured incident investigation** | Correlated root-cause analysis across all your signals                           |\n| 📋 **Runbook-aware reasoning**           | OpenSRE reads your runbooks and applies them automatically                       |\n| 🔮 **Predictive failure detection**      | Catch emerging issues before they page you                                       |\n| 🔗 **Evidence-backed root cause**        | Every conclusion is linked to the data behind it                                 |\n| 🤖 **Full LLM flexibility**              | Bring your own model — Anthropic, OpenAI, Ollama, Gemini, OpenRouter, NVIDIA NIM |\n\nOpenSRE 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](https:\u002F\u002Fwww.opensre.com\u002Fdocs)**; a detailed catalog is also maintained in-repo as the project grows.\n\n---\n\n## Integrations\n\nOpenSRE connects to 60+ tools and services across the modern cloud stack, from LLM providers and observability platforms to infrastructure, databases, and incident management.\n\n| Category                | Integrations                                                                                                                                                                                                                                                                                                                                           | Roadmap                                                                                                                                                                                                                                                            |\n| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| **AI \u002F LLM Providers**  | Anthropic · OpenAI · Ollama · Google Gemini · OpenRouter · NVIDIA NIM · Bedrock                                                                                                                                                                                                                                                                        |                                                                                                                                                                                                                                                                    |\n| **Observability**       | \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fgrafana.webp\" width=\"16\"> Grafana (Loki · Mimir · Tempo) · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fdatadog.svg\" width=\"16\"> Datadog · Honeycomb · Coralogix · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fcloudwatch.png\" width=\"16\"> CloudWatch · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fsentry.png\" width=\"16\"> Sentry · Elasticsearch · Better Stack Telemetry | [Splunk](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F319) · [New Relic](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F139) · [Victoria Logs](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F126)                                                               |\n| **Infrastructure**      | \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fkubernetes.png\" width=\"16\"> Kubernetes · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Faws.png\" width=\"16\"> AWS (S3 · Lambda · EKS · EC2 · Bedrock) · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fgcp.jpg\" width=\"16\"> GCP · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fazure.png\" width=\"16\"> Azure                                                                        | [Helm](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F321) · [ArgoCD](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F320)                                                                                                                                          |\n| **Database**            | MongoDB · ClickHouse · PostgreSQL · MySQL · MariaDB · MongoDB Atlas · Azure SQL · Snowflake                                                                                                                                                                                                                                                            | [RDS](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F125)                                                                                                                                                                                                          |\n| **Data Platform**       | Apache Airflow · Apache Kafka · Apache Spark · Prefect · RabbitMQ                                                                                                                                                                                                                                                                                      |                                                                                                                                                                                                                                                                    |\n| **Dev Tools**           | \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fgithub.webp\" width=\"16\"> GitHub · GitHub MCP · Bitbucket · GitLab                                                                                                                                                                                                                                                          |                                                                                                                                                                                                                                                                    |\n| **Incident Management** | \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fpagerduty.png\" width=\"16\"> PagerDuty · Opsgenie · Jira · Alertmanager                                                                                                                                                                                                                                                      | [Trello](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F361) · [ServiceNow](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F314) · [incident.io](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F317) · [Linear](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F124) |\n| **Communication**       | \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fslack.png\" width=\"16\"> Slack · Google Docs · Discord · Telegram                                                                                                                                                                                                                                                            | [Notion](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F286) · [Teams](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F138) · [WhatsApp](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F360) · [Confluence](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues\u002F313)     |\n| **Agent Deployment**    | \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fvercel.png\" width=\"16\"> Vercel · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Faws.png\" width=\"16\"> EC2 · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Faws.png\" width=\"16\"> ECS · Railway                                                                                                  |                                                                                                                                                                                                                                                                    |\n| **Protocols**           | \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fmcp.svg\" width=\"16\"> MCP · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Facp.png\" width=\"16\"> ACP · \u003Cimg src=\"docs\u002Fassets\u002Ficons\u002Fopenclaw.jpg\" width=\"16\"> OpenClaw                                                                                                                                                                           |                                                                                                                                                                                                                                                                    |\n\nOpenSRE is community-built. Looking for a safe first contribution? Browse [`good first issue`](https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fissues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) tickets or see the [Good First Issues guide](docs\u002Fgood-first-issues\u002FREADME.md). See **[CONTRIBUTING.md](CONTRIBUTING.md)** for the full workflow.\n\n**Local environment:** **[SETUP.md](SETUP.md)** (all platforms, Windows, MCP\u002FOpenClaw).\n\n**Developing in this repo:** **[docs\u002FDEVELOPMENT.md](docs\u002FDEVELOPMENT.md)** (install from source, CI parity checks, dev container, benchmark, deployment detail, telemetry reference).\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002F7NTpevXf7w\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FJoin%20our%20Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white\" alt=\"Join our Discord\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F#Tracer-Cloud\u002Fopensre&Date\">\n    \u003Cimg src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=Tracer-Cloud\u002Fopensre&type=Date\" alt=\"Star History Chart\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\nThanks goes to these amazing people:\n\n\u003C!-- readme: contributors -start -->\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTracer-Cloud\u002Fopensre\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=Tracer-Cloud\u002Fopensre&max=200\" alt=\"Contributors\" \u002F>\n\u003C\u002Fa>\n\u003C!-- readme: contributors -end -->\n\n---\n\n## Security\n\nOpenSRE 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](SECURITY.md)** for responsible disclosure.\n\n---\n\n## Telemetry\n\nPostHog (product analytics) and Sentry (errors) are **opt-out**. Quick disable:\n\n```bash\nexport OPENSRE_NO_TELEMETRY=1\n```\n\n**[Full matrix, DSN override, and local event logging → docs\u002FDEVELOPMENT.md](docs\u002FDEVELOPMENT.md#telemetry-and-privacy)**\n\n---\n\n## License\n\nApache 2.0 — see [LICENSE](LICENSE).\n\n## Citations\n\n\u003Csup>1\u003C\u002Fsup> https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.06770\n","OpenSRE 是一个用于构建AI SRE代理的开源工具包，旨在帮助用户在自己的基础设施上运行和改进这些代理。它支持与60多种现有工具（如Datadog、Grafana等）的连接，并允许自定义工作流程以进行事件调查和管理。基于Python开发，具备强大的可观测性和根因分析能力，能够有效提升站点可靠性工程中的故障响应效率。适用于需要自动化处理生产环境监控、告警及问题修复的企业级应用场景。",2,"2026-06-11 03:48:33","high_star"]