ai-agent

AIClient2API: Unified AI API

Get a single API for multiple AI providers with AIClient2API, used by 8.5k+ GitHub stars. Ideal for founders seeking streamlined AI integration.
8,518 stars1,338 forksJavaScriptGuide quality 8/10Updated 7/24/2026100% free · open source
What it does

AIClient2API acts as a self-hosted proxy to manage and route requests to multiple AI providers, including OpenAI, Claude, and custom providers, with features like smart routing and automatic failover.

When to use it
  • When you need to integrate multiple AI providers into your application
  • When you require more control over the routing and failover of AI requests
  • When you want to convert between different AI protocols, such as Gemini and OpenAI-compatible API
Ready-to-paste prompt
curl -X POST -H "Content-Type: application/json" -d "{"model": "gpt-3.5-turbo", "prompt": "Write a short story about a character who discovers a hidden world."}" http://localhost:3000/v1/completions
Heads up: Make sure you have a valid API key for the desired AI providers, such as OpenAI, and that you have installed the required dependencies, including Node.js 16 or higher, as specified in the README
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/aiclient2api && curl -fsSL https://workflowstacks.com/api/skills/aiclient2api/claude-skill -o ~/.claude/skills/aiclient2api/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How AIClient2API: Unified AI API works
Codeflow
Free to inspect

AIClient2API: Unified AI API is a very large JavaScript project (~89k lines across 134 code files, plus 2 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, GPL-3.0 license, has a test suite.

Size
Very large codebase
~89k lines · 134 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Docker
No API keys detected
JavaScript 86%HTML 7%CSS 7%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    tls-sidecar/main.go
    Where the program starts running
  3. 3
    package.json
    Dependencies and the commands it exposes
  4. 4
    src/auth/index.js
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic125 files
docs/Documentation6 files
configs/Configuration9 files
docker/Deployment / infrastructure4 files
tls-sidecar/Folder3 files
static/Images & static assets80 files
.github/CI / automation (GitHub Actions)2 files
tests/Tests — proof it works2 files
READMEHas testsDocumentedCI checksDocker readyGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
justlovemaki
Language
JavaScript
Category
ai-agent
Published
7/20/2025

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.