Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 88 additions & 0 deletions content/integrations/other/langfuse-board.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,88 @@
---
title: "CEO Dashboard for Langfuse"
sidebarTitle: langfuse-board
description: "Open-source executive dashboard that turns your Langfuse data into a CEO-friendly view of AI costs, usage, and quality."
category: Integrations
---

# langfuse-board

> **What is langfuse-board?**: [langfuse-board](https://github.com/cocolocow/langfuse-board) is an open-source dashboard that plugs into your Langfuse instance and presents your LLM data in a format non-technical stakeholders can read. Costs, usage, quality — one screen, no traces, no jargon.

> **What is Langfuse?**: [Langfuse](https://langfuse.com/) is an open-source LLM engineering platform. It helps teams trace LLM applications, debug issues, evaluate quality, and monitor costs in production.

## What Can This Integration Do?

langfuse-board reads your Langfuse data via the API and presents it in a clean executive dashboard:

- **Cost Overview** — Total spend, daily trends, monthly projections, breakdown by model and provider
- **Usage Analytics** — Active users, requests per day, token consumption, top users
- **Quality Metrics** — Average and P95 latency, error rates, quality scores
- **Live Feed** — Real-time stream of traces with status, cost, and latency
- **Custom Dimensions** — Break down data by any Langfuse metadata field (user, account, feature, plan)

## How It Works

```
┌─────────┐ ┌───────────┐ ┌─────────────────┐ ┌──────────────┐
│ Your App │────▶│ Langfuse │────▶│ langfuse-board │────▶│ CEO-friendly │
│ (LLMs) │ │ (tracking) │ │ (dashboard) │ │ screen │
└─────────┘ └───────────┘ └─────────────────┘ └──────────────┘
```

1. Your application sends traces to Langfuse as usual
2. langfuse-board connects to your Langfuse instance via the API
3. It caches responses with smart TTLs to stay within rate limits (works on the free plan)
4. Non-technical stakeholders see costs, trends, and quality at a glance

## Quick Start

<Steps>

### Prerequisites

- A Langfuse account ([cloud](https://cloud.langfuse.com) or [self-hosted](/self-hosting)) with API keys
- Node.js 20+ and pnpm, or Docker

### Clone and configure

```bash
git clone https://github.com/cocolocow/langfuse-board.git
cd langfuse-board
cp .env.example .env
```

Edit `.env` with your Langfuse credentials:

```env
LANGFUSE_HOST=https://cloud.langfuse.com
LANGFUSE_PUBLIC_KEY=pk-lf-your-key
LANGFUSE_SECRET_KEY=sk-lf-your-key
```

### Start the dashboard

```bash
pnpm install
pnpm dev
```

Open http://localhost:3000 to see your dashboard.

Alternatively, use Docker:

```bash
docker compose up
```

### Try with mock data (no Langfuse needed)

Set `LANGFUSE_MOCK=true` in `.env` to see the dashboard with realistic demo data.

</Steps>

## Resources

- [GitHub Repository](https://github.com/cocolocow/langfuse-board)
- [Website](https://langfuse-board-landing.vercel.app)
- [Contributing Guide](https://github.com/cocolocow/langfuse-board/blob/main/CONTRIBUTING.md)
1 change: 1 addition & 0 deletions content/integrations/other/meta.json
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
"firecrawl",
"gradio",
"inferable",
"langfuse-board",
"librechat",
"mcp-use",
"milvus",
Expand Down
Loading