OSS Tanbou
View on GitHubProject website

protect AI credentials for iOS apps behind a server-side proxy

OSS scale score Not calculatedOSS health 30
About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
8
Primary language
TypeScript
License
AGPL-3.0
Repository last updated
Jan 15, 2026
On this page

Overview

Proxed.AI is an AI proxy backend for iOS applications. It keeps LLM API keys off the client and adds Apple DeviceCheck verification, rate limiting, model control, and structured response schemas on the server side.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Key features

Keep LLM API keys out of the mobile client

Provider credentials stay behind the proxy instead of being embedded in an iOS application.

Sources: [2]

Combine DeviceCheck with structured AI responses

Apple DeviceCheck validates requests while a visual schema builder constrains JSON response structures.

Sources: [2]

Best fit

Fits iOS apps that need controlled AI integration

It is useful when mobile apps need centralized rate limiting, usage monitoring, and secret protection for LLM calls.

Sources: [2]

Before adoption

Local setup assumes Bun, Docker, and Supabase

The official setup guide lists Bun, Docker, and Supabase as prerequisites and runs the monorepo with bun dev.

Sources: [3]

Check both the README and LICENSE wording

The LICENSE file contains AGPL-3.0 text, while the README also describes the project as AGPL-3.0 'for non-commercial use'. Verify current project guidance rather than assuming the terms are identical.

Sources: [2][4]

Official sources

  1. [1]nech-ai/proxed repository(2026-09-30)
  2. [2]Proxed README(2026-09-30)
  3. [3]Proxed local setup guide(2026-09-30)
  4. [4]Proxed AGPL-3.0 license file(2026-09-30)
Supplemental curator note

Proxed.AI keeps LLM API keys behind a proxy and adds DeviceCheck verification, rate limits, and response schemas for iOS clients. The LICENSE file contains AGPL-3.0 text, while the README also says 'for non-commercial use'; verify the project's current licensing terms directly before commercial use or redistribution.

Try it in 3 steps

  1. 1

    Clone the repository

    Get the Proxed.AI monorepo.

    git clone https://github.com/nech-ai/proxed.git && cd proxed
  2. 2

    Install dependencies and create local config

    Install Bun dependencies and create the root environment file. Docker and Supabase are also prerequisites.

    bun install && cp .env.example .env
  3. 3

    Start development mode

    Run the API, portal, and related monorepo services in development mode.

    bun dev
Check the official README

Growth

Growth trends · Last 30 days

8 Stars

Trend data is still being collected.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • devicech
  • ios
  • nextjs
  • supabase
Stars
8
Forks
0
Watchers
0
Open issues
0
Owner type
Organization
Primary language
TypeScript
License
AGPL-3.0
Repository last updated
Jan 15, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.

After reading this page, do you know what to do next?