# Latitude — AI Agent Engineering Platform

> Open-source platform for building, evaluating, and monitoring AI agents in production. Observability, prompt playground, LLM-as-judge evals, experiment comparison. LGPL-3.0, 4,000+ stars.

## Install

Save as a script file and run:

## Quick Use

1. Try Latitude Cloud at [latitude.so](https://latitude.so)

2. Or self-host with Docker:
```bash
git clone https://github.com/latitude-dev/latitude-llm.git
cd latitude-llm
docker compose up -d
```

3. Connect your AI application and start monitoring prompts, responses, and performance.

---

## Intro

Latitude is an open-source AI agent engineering platform with 4,000+ GitHub stars. It provides full observability for LLM applications — capturing prompts, inputs/outputs, tool calls, and performance metrics. Features a prompt playground for iteration, dataset curation for testing, LLM-as-judge evaluations, experiment comparison across models, and automated evaluation guards. Best for teams building production AI applications who need visibility into how their agents perform and tools to improve them.

Explore more AI development tools on [TokRepo AI Open Source](https://tokrepo.com/en/@AI%20Open%20Source).

---

## Latitude — Build, Evaluate, Monitor AI Agents

### The Problem

Building AI agents is easy. Making them work reliably in production is hard. You need to see what prompts are sent, what responses come back, how tool calls behave, and whether quality is improving or degrading over time.

### The Solution

Latitude gives you full visibility into your AI pipeline with tools to evaluate and improve agent performance.

### Key Features

| Feature | Description |
|---------|------------|
| **Observability** | Capture prompts, I/O, tool calls, latency, costs |
| **Prompt Playground** | Iterate on prompts with instant feedback |
| **Datasets** | Curate test data for consistent evaluation |
| **Evaluations** | LLM-as-judge, custom metrics, automated grading |
| **Experiments** | Compare performance across models and providers |
| **Annotations** | Label and cluster issues in agent responses |
| **Guards** | Automated evaluation checks before responses ship |

### Integration

```typescript
import { Latitude } from "@latitude-data/sdk";

const latitude = new Latitude("your-api-key");

// Log a prompt-response pair
await latitude.log({
  prompt: "Summarize this document...",
  response: "The document discusses...",
  model: "claude-sonnet-4-20250514",
  duration_ms: 1200,
  tokens: { input: 500, output: 150 }
});
```

### Evaluation Example

```typescript
// Run LLM-as-judge evaluation
const result = await latitude.evaluate({
  input: userQuery,
  output: agentResponse,
  criteria: [
    "relevance",
    "accuracy",
    "helpfulness"
  ],
  judge_model: "gpt-4o"
});
```

### FAQ

**Q: What is Latitude?**
A: An open-source platform for building, evaluating, and monitoring AI agents in production. It provides observability, prompt management, LLM evaluations, and experiment comparison.

**Q: Is Latitude free?**
A: The self-hosted version is free under LGPL-3.0. Latitude Cloud has a free tier for smaller projects.

**Q: How is Latitude different from LangFuse?**
A: Latitude focuses on the full agent engineering lifecycle — from prompt iteration to evaluation to monitoring — with built-in LLM-as-judge capabilities and experiment comparison.

---

## Source & Thanks

> Created by [Latitude](https://github.com/latitude-dev). Licensed under LGPL-3.0.
>
> [latitude-llm](https://github.com/latitude-dev/latitude-llm) — ⭐ 4,000+

Thanks to the Latitude team for making AI agent engineering more transparent and reliable.

---

<!-- ZH -->

## 快速使用

1. 在 [latitude.so](https://latitude.so) 试用云版

2. 或 Docker 自托管：
```bash
git clone https://github.com/latitude-dev/latitude-llm.git
cd latitude-llm && docker compose up -d
```

3. 连接你的 AI 应用，开始监控提示词、响应和性能。

---

## 简介

Latitude 是开源 AI Agent 工程平台，GitHub 4,000+ star。为 LLM 应用提供完整可观测性 — 捕获提示词、输入输出、工具调用和性能指标。支持提示词 Playground、数据集策划、LLM-as-judge 评估、跨模型实验对比和自动评估守卫。适合构建生产级 AI 应用的团队。

---

## Latitude — 构建、评估、监控 AI Agent

### 核心功能

- **可观测性** — 捕获提示词、I/O、工具调用、延迟、成本
- **Prompt Playground** — 即时反馈迭代提示词
- **数据集** — 策划测试数据
- **评估** — LLM-as-judge、自定义指标
- **实验** — 跨模型对比性能
- **自动守卫** — 响应发送前的自动检查

### FAQ

**Q: Latitude 是什么？**
A: 开源 AI Agent 工程平台，提供可观测性、评估和监控。

**Q: 和 LangFuse 有什么区别？**
A: Latitude 覆盖完整 Agent 工程生命周期，内置 LLM-as-judge 和实验对比。

---

## 来源与感谢

> Created by [Latitude](https://github.com/latitude-dev). Licensed under LGPL-3.0.
>
> [latitude-llm](https://github.com/latitude-dev/latitude-llm) — ⭐ 4,000+


---
Source: https://tokrepo.com/en/workflows/f0b521ab-33e5-11f1-9bc6-00163e2b0d79
Author: AI Open Source