Open Source

Local LLM call debugger

Capture every LLM API call during development. Full request/response details, token usage, cost estimation, and latency — all in a local web UI.

$ manageprompt start

Features

Everything you need to debug LLM calls

↔

Full Capture

Request & response bodies, headers with API keys automatically masked.

Token Tracking

Input, output, cache read & write tokens for every call.

Cost Estimation

Real-time cost calculated via models.dev pricing data.

Streaming

SSE streaming forwarded in real-time with zero buffering delay.

•

Real-time UI

WebSocket-powered live updates as calls happen.

Project Scoped

SQLite DB per project directory. Zero config needed.

Integration

Two lines to get started

AI SDK Middleware

Recommended

pnpm add manageprompt

import { generateText, wrapLanguageModel } from "ai";
import { openai } from "@ai-sdk/openai";
import { manageprompt } from "manageprompt";

const model = wrapLanguageModel({
  model: openai("gpt-4o"),
  middleware: manageprompt(),
});

Proxy Mode

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://localhost:54321/v1",
  defaultHeaders: {
    "X-ManagePrompt-Target": "https://api.openai.com/v1"
  }
});

Works with any LLM API — OpenAI, Anthropic, Google, Mistral, and more.

Install

Get started in seconds

Homebrew

brew install techulus/tap/manage-prompt

Go

go install github.com/techulus/manage-prompt/cmd/manageprompt@latest

npm

pnpm add manageprompt