[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73791":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":14,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":17,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":45,"readmeContent":46,"aiSummary":47,"trendingCount":16,"starSnapshotCount":16,"syncStatus":48,"lastSyncTime":49,"discoverSource":50},73791,"lmnr","lmnr-ai\u002Flmnr","lmnr-ai","Laminar - open-source observability platform purpose-built for AI agents. YC S24.","https:\u002F\u002Flaminar.sh",null,"TypeScript",2994,203,11,32,0,33,122,105.43,"Apache License 2.0",false,"main",true,[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"agent-observability","agents","ai","ai-observability","aiops","analytics","developer-tools","evals","evaluation","llm-evaluation","llm-observability","llmops","monitoring","observability","open-source","rust","rust-lang","self-hosted","ts","typescript","2026-06-12 04:01:11","\u003Ca href=\"https:\u002F\u002Fwww.ycombinator.com\u002Fcompanies\u002Flaminar-ai\">![Static Badge](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FY%20Combinator-S24-orange)\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fx.com\u002Flmnrai\">![X (formerly Twitter) Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Flmnrai)\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FnNFUUDAKub\"> ![Static Badge](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FJoin_Discord-464646?&logo=discord&logoColor=5865F2) \u003C\u002Fa>\n\n![Laminar banner](.\u002Fimages\u002Flaminar-banner.png)\n\n# Laminar\n\n[Laminar](https:\u002F\u002Flaminar.sh) is an open-source observability platform purpose-built for AI agents.\n\n- [x] Tracing. [Docs](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Ftracing\u002Fintroduction)\n    - [x] OpenTelemetry-native powerful tracing SDK - 1 line of code to automatically trace **Vercel AI SDK, Browser Use, Stagehand, LangChain, OpenAI, Anthropic, Gemini, and more**.\n- [x] Evals. [Docs](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Fevaluations\u002Fintroduction)\n    - [x] Unopinionated, extensible SDK and CLI for running evals locally or in CI\u002FCD pipeline.\n    - [x] UI for visualizing evals and comparing results.\n- [x] AI monitoring. [Docs](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Fsignals)\n    - [x] Define events with natural language descriptions to track issues, logical errors, and custom behavior of your agent.\n- [x] SQL access to all data. [Docs](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Fplatform\u002Fsql-editor)\n    - [x] Query traces, metrics, and events with a built-in SQL editor. Bulk create datasets from queries. Available via API.\n- [x] Dashboards. [Docs](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Fcustom-dashboards\u002Foverview)\n    - [x] Powerful dashboard builder for traces, metrics, and events with support of custom SQL queries.\n- [x] Data annotation & Datasets. [Docs](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Fdatasets\u002Fintroduction)\n    - [x] Custom data rendering UI for fast data annotation and dataset creation for evals.\n- [x] Extremely high performance.\n    - [x] Written in Rust 🦀\n    - [x] Custom realtime engine for viewing traces as they happen.\n    - [x] Ultra-fast full-text search over span data.\n    - [x] gRPC exporter for tracing data.\n\n![Traces](.\u002Fimages\u002Ftrace-screenshot.png)\n\n## Documentation\n\nCheck out full documentation here [laminar.sh\u002Fdocs](https:\u002F\u002Flaminar.sh\u002Fdocs).\n\n## Getting started\n\nThe fastest and easiest way to get started is with our managed platform -> [laminar.sh](https:\u002F\u002Flaminar.sh)\n\n### Self-hosting with Docker compose\n\nLaminar is very easy to self-host locally. For a quick start, clone the repo and start the services with docker compose:\n```sh\ngit clone https:\u002F\u002Fgithub.com\u002Flmnr-ai\u002Flmnr\ncd lmnr\ndocker compose up -d\n```\n\nThis will spin up a lightweight but full-featured version of the stack. This is good for a quickstart \nor for lightweight usage. You can access the UI at http:\u002F\u002Flocalhost:5667 in your browser.\n\nYou will also need to properly configure the SDK, with `baseUrl` and correct ports. See [guide on self-hosting](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Fhosting-options#self-hosted-docker-compose).\n\nFor production environment, we recommend using our [managed platform](https:\u002F\u002Flaminar.sh) or `docker compose -f docker-compose-full.yml up -d`.\n\n### Enabling the Signals feature\n\nTo enable [Signals \u002F AI monitoring](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Fsignals) in self-hosted mode, set the `GOOGLE_GENERATIVE_AI_API_KEY` environment variable in your `.env` file. This key is required by both the app-server and the frontend.\n\n```sh\n# In .env at the repo root\nGOOGLE_GENERATIVE_AI_API_KEY=your_key_here\n```\n\n## Contributing\n\nFor running and building Laminar locally, or to learn more about docker compose files,\nfollow the guide in [Contributing](\u002FCONTRIBUTING.md).\n\n## TS quickstart\n\nFirst, [create a project](https:\u002F\u002Flaminar.sh\u002Fprojects) and generate a project API key. Then,\n\n```sh\nnpm add @lmnr-ai\u002Flmnr\n```\n\nIt will install Laminar TS SDK and all instrumentation packages (OpenAI, Anthropic, LangChain ...)\n\nTo start tracing LLM calls just add\n```typescript\nimport { Laminar } from '@lmnr-ai\u002Flmnr';\nLaminar.initialize({ projectApiKey: process.env.LMNR_PROJECT_API_KEY });\n```\n\nTo trace inputs \u002F outputs of functions use `observe` wrapper.\n\n```typescript\nimport { OpenAI } from 'openai';\nimport { observe } from '@lmnr-ai\u002Flmnr';\n\nconst client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });\n\nconst poemWriter = observe({name: 'poemWriter'}, async (topic) => {\n  const response = await client.chat.completions.create({\n    model: \"gpt-4o-mini\",\n    messages: [{ role: \"user\", content: `write a poem about ${topic}` }],\n  });\n  return response.choices[0].message.content;\n});\n\nawait poemWriter();\n```\n\n## Python quickstart\n\nFirst, [create a project](https:\u002F\u002Flaminar.sh\u002Fprojects) and generate a project API key. Then,\n\n```sh\npip install --upgrade 'lmnr[all]'\n```\nIt will install Laminar Python SDK and all instrumentation packages. See list of all instruments [here](https:\u002F\u002Flaminar.sh\u002Fdocs\u002Finstallation)\n\n\nTo start tracing LLM calls just add\n```python\nfrom lmnr import Laminar\nLaminar.initialize(project_api_key=\"\u003CLMNR_PROJECT_API_KEY>\")\n```\n\nTo trace inputs \u002F outputs of functions use `@observe()` decorator.\n\n```python\nimport os\nfrom openai import OpenAI\n\nfrom lmnr import observe, Laminar\nLaminar.initialize(project_api_key=\"\u003CLMNR_PROJECT_API_KEY>\")\n\nclient = OpenAI(api_key=os.environ[\"OPENAI_API_KEY\"])\n\n@observe()  # annotate all functions you want to trace\ndef poem_writer(topic):\n    response = client.chat.completions.create(\n        model=\"gpt-4o\",\n        messages=[\n            {\"role\": \"user\", \"content\": f\"write a poem about {topic}\"},\n        ],\n    )\n    poem = response.choices[0].message.content\n    return poem\n\nif __name__ == \"__main__\":\n    print(poem_writer(topic=\"laminar flow\"))\n```\n\n## Client libraries\n\nTo learn more about instrumenting your code, check out our client libraries:\n\n \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@lmnr-ai\u002Flmnr\"> ![NPM Version](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F%40lmnr-ai%2Flmnr?label=lmnr&logo=npm&logoColor=CB3837) \u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Flmnr\u002F\"> ![PyPI - Version](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Flmnr?label=lmnr&logo=pypi&logoColor=3775A9) \u003C\u002Fa>\n","Laminar 是一个专为AI代理设计的开源可观测性平台。它提供了强大的追踪功能，支持通过一行代码自动追踪Vercel AI SDK、LangChain、OpenAI等工具；具备灵活的评估SDK和CLI，可以在本地或CI\u002FCD管道中运行评估，并通过UI可视化比较结果；能够使用自然语言定义事件来跟踪问题和逻辑错误；还支持通过内置SQL编辑器查询所有数据。此外，Laminar采用Rust编写，具有极高的性能，包括实时引擎、超快全文搜索等功能。该平台适用于需要对AI系统进行深度监控、调试及优化的各种场景，特别是那些依赖复杂AI工作流的企业级应用。",2,"2026-06-11 03:47:23","high_star"]