Desktop AI Gateway · Open Source

One OpenAI-Compatible Gateway for Every AI Model

Web2AI API Desktop bundles a local OpenAI-compatible gateway, multi-profile load balancing, saved chat history, and a floating Desktop Pet in a single native app.

Web2AI API App Logo
POST http://127.0.0.1:8088/v1/chat/completionsSSE Stream
curl http://127.0.0.1:8088/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-Session-Id: my-thread-1" \
  -d '{
    "model": "deepseek:deepseek-chat",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'
Floating Desktop Pet

5 pixel-art companions (Guitarist Fox, Vocalist Bot, Flutist Neko, Maestro Owl, Drummer Shiba) with live chat & local history.

Inside Web2AI API Desktop

Manage provider profiles, test completions in the Playground, or chat directly from the floating Desktop Pet.

Provider Profiles & Load Balancing
Web2AI API Provider Profiles
API Playground
Web2AI API Playground
Pet Store — 5 Pixel-Art Companions
Web2AI Pet Store
Floating Desktop Pet & Quick Chat
Web2AI Floating Desktop Pet Chat

Built for Local AI Workflows

Everything runs locally on your machine with zero Python runtime required.

OpenAI-Compatible Local Gateway

Drop-in /v1/chat/completions and /v1/models on http://127.0.0.1:8088 with SSE streaming, reasoning_content, and X-Session-Id continuity.

Round-Robin Profile Load Balancing

Register multiple provider accounts and rotate requests automatically with cooldown handling on auth or rate-limit errors.

Interactive Floating Desktop Pet

Codex-inspired always-on-top pixel companion with 5 customizable pets, instruments, 11 reactive expressions, and instant quick chat.

Local History & Sessions

Profiles, API keys, chat sessions, Pet Store selection, and pet chat history are saved locally on your device.

Local API Keys & Playground

Create and revoke local sk-... access keys and test streaming or multi-turn chats directly from the built-in Playground.

Lightweight & Auto-Updating

Fast native desktop app with a built-in local gateway and automatic background updates.

Use with any OpenAI SDK

Point base_url to http://127.0.0.1:8088/v1 in Cursor, Continue, OpenCode, or your own scripts.

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8088/v1", api_key="local")
resp = client.chat.completions.create(
    model="deepseek:deepseek-reasoner",
    messages=[{"role": "user", "content": "Summarize today's tasks in 3 bullet points."}],
)
print(resp.choices[0].message.content)

Download Web2AI API

Automated multi-platform builds published via GitHub Releases with built-in auto-updates.

.dmg

macOS (Apple Silicon)

M1 / M2 / M3 / M4 Macs

.dmg

macOS (Intel)

x86_64 Macs

.msi / .exe

Windows

Windows 10 & 11 (64-bit)

.AppImage

Linux (AppImage)

Universal portable binary

.deb

Linux (Debian / Ubuntu)

x86_64 .deb package