{"id":13624218,"url":"https://github.com/openlit/openlit","last_synced_at":"2026-02-26T11:08:59.515Z","repository":{"id":218862382,"uuid":"747319327","full_name":"openlit/openlit","owner":"openlit","description":"Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.","archived":false,"fork":false,"pushed_at":"2026-01-05T19:07:32.000Z","size":98811,"stargazers_count":2122,"open_issues_count":51,"forks_count":226,"subscribers_count":17,"default_branch":"main","last_synced_at":"2026-01-06T11:57:34.111Z","etag":null,"topics":["ai-observability","amd-gpu","clickhouse","distributed-tracing","genai","gpu-monitoring","grafana","langchain","llmops","llms","metrics","monitoring-tool","nvidia-smi","observability","open-source","openai","opentelemetry","otlp","python","tracing"],"latest_commit_sha":null,"homepage":"https://docs.openlit.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/openlit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":null,"patreon":null,"open_collective":"openlit","ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":null,"thanks_dev":null,"custom":null}},"created_at":"2024-01-23T17:40:59.000Z","updated_at":"2026-01-05T19:19:03.000Z","dependencies_parsed_at":"2024-03-28T06:22:50.331Z","dependency_job_id":"e467fc0e-9e3e-4a61-b529-9859fc449825","html_url":"https://github.com/openlit/openlit","commit_stats":{"total_commits":353,"total_committers":16,"mean_commits":22.0625,"dds":"0.35694050991501414","last_synced_commit":"abc8d48e9160ffa2c2b6008543b9cefebe9e49f3"},"previous_names":["dokulabs/doku","openlit/openlit"],"tags_count":224,"template":false,"template_full_name":null,"purl":"pkg:github/openlit/openlit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openlit%2Fopenlit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openlit%2Fopenlit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openlit%2Fopenlit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openlit%2Fopenlit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/openlit","download_url":"https://codeload.github.com/openlit/openlit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openlit%2Fopenlit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28321263,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-11T18:42:50.174Z","status":"ssl_error","status_checked_at":"2026-01-11T18:39:13.842Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-observability","amd-gpu","clickhouse","distributed-tracing","genai","gpu-monitoring","grafana","langchain","llmops","llms","metrics","monitoring-tool","nvidia-smi","observability","open-source","openai","opentelemetry","otlp","python","tracing"],"created_at":"2024-08-01T21:01:40.162Z","updated_at":"2026-01-12T11:03:35.349Z","avatar_url":"https://github.com/openlit.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"https://github.com/openlit/.github/blob/main/profile/assets/wide-logo-no-bg.png?raw=true\" alt=\"OpenLIT Logo\" width=\"30%\"\u003e\n\n#### Observability, Evaluations, Guardrails, Prompts, Vault, Playground, FleetHub\n\n# Open Source Platform for AI Engineering\n\n**[Documentation](https://docs.openlit.io/) | [Quickstart](-getting-started-with-llm-observability) | [Python SDK](https://github.com/openlit/openlit/tree/main/sdk/python) | [Typescript SDK](https://github.com/openlit/openlit/tree/main/sdk/typescript) |**\n\n**❤️ [Sponsor this project](https://opencollective.com/openlit) ❤️** \n\n[![OpenLIT](https://img.shields.io/badge/OpenLIT-orange)](https://openlit.io/)\n[![License](https://img.shields.io/github/license/openlit/openlit?label=License\u0026logo=github\u0026color=f80\u0026logoColor=white)](https://github.com/openlit/openlit/blob/main/LICENSE)\n[![Downloads](https://static.pepy.tech/badge/openlit/month)](https://pepy.tech/project/openlit)\n[![GitHub Last Commit](https://img.shields.io/github/last-commit/openlit/openlit)](https://github.com/openlit/openlit/pulse)\n[![GitHub Contributors](https://img.shields.io/github/contributors/openlit/openlit)](https://github.com/openlit/openlit/graphs/contributors)\n\n[![Slack](https://img.shields.io/badge/Slack-4A154B?logo=slack\u0026logoColor=white)](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ)\n[![X](https://img.shields.io/badge/follow-%40openlit__io-1DA1F2?logo=x\u0026style=social)](https://twitter.com/openlit_io)\n\u003c/div\u003e\n\n---\n\n\u003chttps://github.com/user-attachments/assets/6909bf4a-f5b4-4060-bde3-95e91fa36168\u003e\n\n**OpenLIT** allows you to simplify your AI development workflow, especially for Generative AI and LLMs. It streamlines essential tasks like experimenting with LLMs, organizing and versioning prompts, and securely handling API keys. With just one line of code, you can enable **OpenTelemetry-native** observability, offering full-stack monitoring that includes LLMs, vector databases, and GPUs. This enables developers to confidently build AI features and applications, transitioning smoothly from testing to production.\n\nThis project proudly follows and maintains the [Semantic Conventions](https://github.com/open-telemetry/semantic-conventions/tree/main/docs/gen-ai) with the OpenTelemetry community, consistently updating to align with the latest standards in Observability.\n\n## ⚡ Features\n\n![OpenLIT Banner](https://github.com/openlit/.github/blob/main/profile/assets/openlit-feature-banner.png?raw=true)\n\n- 📈 **Analytics Dashboard**: Monitor your AI application's health and performance with detailed dashboards that track metrics, costs, and user interactions, providing a clear view of overall efficiency.\n\n- 🔌 **OpenTelemetry-native Observability SDKs**: Vendor-neutral SDKs to send traces and metrics to your existing observability tools.\n\n- 💲 **Cost Tracking for Custom and Fine-Tuned Models**: Tailor cost estimations for specific models using custom pricing files for precise budgeting.\n\n- 🐛 **Exceptions Monitoring Dashboard**: Quickly spot and resolve issues by tracking common exceptions and errors with a dedicated monitoring dashboard.\n\n- 💭 **Prompt Management**: Manage and version prompts using Prompt Hub for consistent and easy access across applications.\n\n- 🔑 **API Keys and Secrets Management**: Securely handle your API keys and secrets centrally, avoiding insecure practices.\n\n- 🎮 **Experiment with different LLMs**: Use OpenGround to explore, test and compare various LLMs side by side.\n\n- 🚀 **Fleet Hub for OpAMP Management**: Centrally manage and monitor OpenTelemetry Collectors across your infrastructure using the OpAMP (Open Agent Management Protocol) with secure TLS communication.\n\n## 🚀 Getting Started with LLM Observability\n\n```mermaid\nflowchart TB;\n    subgraph \" \"\n        direction LR;\n        subgraph \" \"\n            direction LR;\n            OpenLIT_SDK[OpenLIT SDK] --\u003e|Sends Traces \u0026 Metrics| OTC[OpenTelemetry Collector];\n            OTC --\u003e|Stores Data| ClickHouseDB[ClickHouse];\n        end\n        subgraph \" \"\n            direction RL;\n            OpenLIT_UI[OpenLIT] --\u003e|Pulls Data| ClickHouseDB;\n        end\n    end\n```\n\n### Step 1: Deploy OpenLIT Stack\n\n1. Git Clone OpenLIT Repository\n\n   Open your command line or terminal and run:\n\n   ```shell\n   git clone git@github.com:openlit/openlit.git\n   ```\n\n2. Self-host using Docker\n  \n   Deploy and run OpenLIT with the following command:\n\n   ```shell\n   docker compose up -d\n   ```\n\n\u003e For instructions on installing in Kubernetes using Helm, refer to the [Kubernetes Helm installation guide](https://docs.openlit.io/latest/openlit/installation#kubernetes).\n\n### Step 2: Install OpenLIT SDK\n\nOpen your command line or terminal and run:\n\n```bash\npip install openlit\n```\n\n\u003e For instructions on using the TypeScript SDK, visit the [TypeScript SDK Installation guide](https://github.com/openlit/openlit/tree/main/sdk/typescript#-installation).\n\n### Step 3: Initialize OpenLIT in your Application\n\nIntegrate OpenLIT into your AI applications by adding the following lines to your code.\n\n```python\nimport openlit\n\nopenlit.init()\n```\n\nConfigure the telemetry data destination as follows:\n\n| Purpose                            | Parameter/Environment Variable                   | For Sending to OpenLIT    |\n| ---------------------------------- | ------------------------------------------------ | ------------------------- |\n| Send data to an HTTP OTLP endpoint | `otlp_endpoint` or `OTEL_EXPORTER_OTLP_ENDPOINT` | `\"http://127.0.0.1:4318\"` |\n| Authenticate telemetry backends    | `otlp_headers` or `OTEL_EXPORTER_OTLP_HEADERS`   | Not required by default   |\n\n\u003e 💡 Info: If the `otlp_endpoint` or `OTEL_EXPORTER_OTLP_ENDPOINT` is not provided, the OpenLIT SDK will output traces directly to your console, which is recommended during the development phase.\n\n#### Example\n\n---\n\n\u003cdetails\u003e\n  \u003csummary\u003eInitialize using Function Arguments\u003c/summary\u003e\n\n  Add the following two lines to your application code:\n  \n  ```python\n  import openlit\n  \n  openlit.init(\n    otlp_endpoint=\"http://127.0.0.1:4318\", \n  )\n  ```\n\n\u003c/details\u003e\n\n---\n\n\u003cdetails\u003e\n\n  ---\n\n  \u003csummary\u003eInitialize using Environment Variables\u003c/summary\u003e\n  \n  Add the following two lines to your application code:\n\n  ```python\n  import openlit\n\n  openlit.init()\n  ```\n  \n  Then, configure the your OTLP endpoint using environment variable:\n\n  ```env\n  export OTEL_EXPORTER_OTLP_ENDPOINT = \"http://127.0.0.1:4318\"\n  ```\n\n\u003c/details\u003e\n\n---\n\n### Step 4: Visualize and Optimize\n\nWith the Observability data now being collected and sent to OpenLIT, the next step is to visualize and analyze this data to get insights into your AI application's performance, behavior, and identify areas of improvement.\n\nJust head over to OpenLIT at `127.0.0.1:3000` on your browser to start exploring. You can login using the default credentials:\n\n- **Email**: `user@openlit.io`\n- **Password**: `openlituser`\n\n![](https://github.com/openlit/.github/blob/main/profile/assets/openlit-client-1.png?raw=true)\n![](https://github.com/openlit/.github/blob/main/profile/assets/openlit-client-2.png?raw=true)\n\n## 🛣️ Roadmap\n\nWe are dedicated to continuously improving OpenLIT. Here's a look at what's been accomplished and what's on the horizon:\n\n| Feature                                                                                                                           | Status        |\n| --------------------------------------------------------------------------------------------------------------------------------- | ------------- |\n| [OpenTelemetry-native Observability SDK for Tracing and Metrics](https://github.com/openlit/openlit/tree/text-upgrade/sdk/python) | ✅ Completed   |\n| [OpenTelemetry-native GPU Monitoring](https://docs.openlit.io/latest/features/gpu)                                                | ✅ Completed   |\n| [Exceptions and Error Monitoring](https://docs.openlit.io/latest/features/exceptions)                                             | ✅ Completed   |\n| [Prompt Hub for Managing and Versioning Prompts](https://docs.openlit.io/latest/features/prompt-hub)                              | ✅ Completed   |\n| [OpenGround for Testing and Comparing LLMs](https://docs.openlit.io/latest/features/openground)                                   | ✅ Completed   |\n| [Vault for Central Management of LLM API Keys and Secrets](https://docs.openlit.io/latest/features/vault)                         | ✅ Completed   |\n| [Cost Tracking for Custom Models](https://docs.openlit.io/latest/features/pricing)                                                | ✅ Completed   |\n| [Real-Time Guardrails Implementation](https://docs.openlit.io/latest/features/guardrails)                                         | ✅ Completed   |\n| [Programmatic Evaluation for LLM Response](https://docs.openlit.io/latest/features/evaluations)                                   | ✅ Completed   |\n| [Fleet Hub for OpAMP Management](https://docs.openlit.io/latest/openlit/observability/fleet-hub)                                  | ✅ Completed   |\n| [Auto-Evaluation Metrics Based on Usage](https://github.com/openlit/openlit/issues/470)                                           | 🔜 Coming Soon |\n| [Human Feedback for LLM Events](https://github.com/openlit/openlit/issues/471)                                                    | 🔜 Coming Soon |\n| [Dataset Generation Based on LLM Events](https://github.com/openlit/openlit/issues/472)                                           | 🔜 Coming Soon |\n| [Search over Traces]()                                                                                                            | 🔜 Coming Soon |\n\n## 🌱 Contributing\n\nWhether it's big or small, we love contributions 💚. Check out our [Contribution guide](./CONTRIBUTING.md) to get started\n\nUnsure where to start? Here are a few ways to get involved:\n\n- Join our [Slack](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ) or [Discord](https://discord.gg/rjvTm6zd) community to discuss ideas, share feedback, and connect with both our team and the wider OpenLIT community.\n\nYour input helps us grow and improve, and we're here to support you every step of the way.\n\n[![OpenLIT - One click observability, evals for LLMs \u0026 GPUs | Product Hunt](https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=460690\u0026theme=light)](https://www.producthunt.com/posts/openlit?embed=true\u0026utm_source=badge-featured\u0026utm_medium=badge\u0026utm_souce=badge-openlit)\n\u003ca href=\"https://fazier.com/launches/openlit-2\" target=\"_blank\" rel=\"noopener noreferrer\"\u003e\u003cimg src=\"https://fazier.com/api/v1/public/badges/embed_image.svg?launch_id=779\u0026badge_type=daily\" width=\"270\" alt=\"Example Image\" class=\"d-inline-block mt-3 p-3 rounded img-fluid\" /\u003e\u003c/a\u003e\n\n## 💚 Community \u0026 Support\n\nConnect with OpenLIT community and maintainers for support, discussions, and updates:\n\n- 🌟 If you like it, leave a star on our [GitHub](https://github.com/openlit/openlit/).\n- 🌍 Join our [Slack](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ) or [Discord](https://discord.gg/CQnXwNT3) community for live interactions and questions.\n- 🐞 Report bugs on our [GitHub Issues](https://github.com/openlit/openlit/issues) to help us improve OpenLIT.\n- 𝕏 Follow us on [X](https://twitter.com/openlit_io) for the latest updates and news.\n\n## License\n\nOpenLIT is available under the [Apache-2.0 license](LICENSE).\n\n\n## 🙇‍♂️ Acknowledgments\n\n\u003cp\u003eThis project is proudly supported by:\u003c/p\u003e\n\u003cp\u003e\n    \u003ca href=\"https://www.lambdatest.com/?utm_source=openlit\u0026utm_medium=sponsor\" target=\"_blank\"\u003e\n\t\t\t\t\t\u003cimg src=\"https://www.lambdatest.com/blue-logo.png\" style={{ verticalAlign: 'middle' }} width=\"250\" /\u003e\n\t\t\t\t\u003c/a\u003e\n  \u003ca href=\"https://www.digitalocean.com/\"\u003e\n    \u003cimg src=\"https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_blue.svg\" width=\"201px\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n","funding_links":["https://opencollective.com/openlit"],"categories":["Coding","10. Application Performance Monitoring Solutions (APM)","👁️ Observability \u0026 Tracing","LLMOps","A01_文本生成_文本对话","Python","Prompts","Evaluation and Monitoring","Uncategorized","Platforms","Observability \u0026 Monitoring","Orchestration","Integrations"],"sub_categories":["Developer tools","Anomalies Detection","3. The Enterprise / High-Scale Stack (The 1%)","Observability","大语言对话模型及数据","Uncategorized","Open Source Platforms","Resources","Application Framework","Metrics and Monitoring"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopenlit%2Fopenlit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopenlit%2Fopenlit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopenlit%2Fopenlit/lists"}