latitude-llm Agent工作流 是 AI Skill Hub 本期精选Agent工作流之一。已获得 4.0k 颗 GitHub Star,综合评分 8.2 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
latitude-llm Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
latitude-llm Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g latitude-llm # 方式二:npx 直接运行(无需安装) npx latitude-llm --help # 方式三:项目依赖安装 npm install latitude-llm # 方式四:从源码运行 git clone https://github.com/latitude-dev/latitude-llm cd latitude-llm npm install npm start
# 命令行使用
latitude-llm --help
# 基本用法
latitude-llm [options] <input>
# Node.js 代码中使用
const latitude_llm = require('latitude-llm');
const result = await latitude_llm.run(options);
console.log(result);
# latitude-llm 配置说明 # 查看配置选项 latitude-llm --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export LATITUDE_LLM_CONFIG="/path/to/config.yml"
<p align="center"> <img src="docs/assets/readme/readme-banner.png?raw=true" alt="Latitude — issue detection for AI agents" width="100%" /> </p>
<p align="center"> <sub><b>New:</b> <a href="https://docs.latitude.so/getting-started/mcp">Latitude MCP server: connect your AI agent to Latitude →</a></sub> </p>
<p align="center"> Sentry, but for agents and LLMs. </p>
<p align="center"> <a href="https://github.com/latitude-dev/latitude-llm/blob/main/LICENSE"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.github/badges/license.json" alt="License"></a> <a href="https://github.com/latitude-dev/latitude-llm/actions/workflows/deploy.yml"><img src="https://img.shields.io/github/actions/workflow/status/latitude-dev/latitude-llm/deploy.yml?branch=development&label=build" alt="Build"></a> <a href="https://github.com/latitude-dev/latitude-llm/graphs/commit-activity" target="_blank"><img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/latitude-dev/latitude-llm?labelColor=%20%2332b583&color=%20%2312b76a"></a> <a href="https://www.npmjs.com/org/latitude-data"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.github/badges/npm-downloads.json&logo=npm&logoColor=white" alt="npm downloads"></a> <a href="https://pypi.org/project/latitude-telemetry/"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.github/badges/pypi-downloads.json&logo=python&logoColor=white" alt="PyPI downloads"></a> <a href="https://github.com/latitude-dev/latitude-llm"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.github/badges/stars.json&logo=github&logoColor=white" alt="GitHub stars"></a> <a href="https://twitter.com/intent/follow?screen_name=trylatitude" target="_blank"><img src="https://img.shields.io/twitter/follow/trylatitude?logo=X&color=%20%23f5f5f5" alt="Follow on X"></a> </p>
<p align="center"> <a href="https://latitude.so/?utm_source=github_readme" rel="dofollow">Website</a> · <a href="https://docs.latitude.so" rel="dofollow">Docs</a> · <a href="https://latitude.so/changelog" rel="dofollow">Changelog</a> · <a href="https://join.slack.com/t/trylatitude/shared_invite/zt-35wu2h9es-N419qlptPMhyOeIpj3vjzw">Slack</a> · <a href="https://x.com/trylatitude">X</a> </p>
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/readme/gif-ui-dark.gif?raw=true"> <source media="(prefers-color-scheme: light)" srcset="docs/assets/readme/gif-ui-light.gif?raw=true"> <img src="docs/assets/readme/gif-ui-light.gif?raw=true" alt="Demo of the Latitude UI showing LLM observability, issue tracking, and evals" width="800"/> </picture> </p>
npm install @latitude-data/telemetry
This example uses OpenAI; replace it with the LLM SDK your app already imports.
import { Latitude } from "@latitude-data/telemetry";
import OpenAI from "openai";
const latitude = new Latitude({
apiKey: process.env.LATITUDE_API_KEY!,
project: process.env.LATITUDE_PROJECT_SLUG!,
instrumentations: { openai: OpenAI },
});
const client = new OpenAI();
await client.chat.completions.create({
model: "gpt-4o",
messages: [{ role: "user", content: "Hello" }],
});
await latitude.shutdown();
Every supported LLM call now shows up as a trace in Latitude. Use capture() at request, conversation, or agent boundaries when you want to add user IDs, session IDs, tags, or metadata.
Python and any OpenTelemetry-compatible runtime are also supported. Full setup, provider guides, and OTel passthrough are in the Start tracing guide.
You can use Latitude for free, including 20K credits/month, 30-day data retention, and unlimited seats.
Sign up at latitude.so and grab your API key and project slug.
Latitude is provider-agnostic. Telemetry works out of the box with most model providers and frameworks (OpenAI, Anthropic, Bedrock, Vercel AI SDK, LangChain, and more), plus any OTEL-compatible application.
See the full integration list for setup instructions.
Latitude是成熟的AI工作流平台,4k Stars表明社区认可度高。架构清晰、功能完整,适合企业级智能体应用开发。代码维护活跃,文档相对完善。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
⚠️ LGPL 3.0 — 弱 Copyleft,比 GPL 宽松,允许闭源软件通过动态链接使用。
经综合评估,latitude-llm Agent工作流 在Agent工作流赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | latitude-llm |
| 原始描述 | 开源AI工作流:Latitude is the open-source agent engineering platform。⭐4.0k · TypeScript |
| Topics | AI工作流智能体编程开源平台TypeScript工程化 |
| GitHub | https://github.com/latitude-dev/latitude-llm |
| License | LGPL-3.0 |
| 语言 | TypeScript |
收录时间:2026-05-18 · 更新时间:2026-05-19 · License:LGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端