Skip to content

Repository files navigation

ReGraph

ReGraphLicenseStatus

Decentralized AI Compute Marketplace

WebsiteDocumentationAPI ReferenceStatus


🚀 Overview

ReGraph is a decentralized AI compute marketplace that connects hardware providers with developers who need inference and training resources. Our platform democratizes access to AI computing power by creating a global network of distributed compute nodes.

Why ReGraph?

  • Cost Effective: Up to 80% cheaper than traditional cloud providers
  • Decentralized: No single point of failure, powered by a global network
  • Easy Integration: OpenAI-compatible API, drop-in replacement for existing workflows
  • Multi-Model Support: Access to GPT-5, Gemini, Claude, Llama, and 50+ models
  • Pay-as-you-go: Only pay for what you use, no commitments

📊 Pricing Comparison

ProviderGPT-4 EquivalentLlama 70BImage Generation
ReGraph$0.002/1K tokens$0.0008/1K tokens$0.02/image
OpenAI$0.03/1K tokensN/A$0.04/image
AWS Bedrock$0.008/1K tokens$0.00265/1K tokens$0.05/image
Google Cloud$0.00125/1K tokens$0.0009/1K tokens$0.04/image

🛠️ Quick Start

Installation

# Clone the repository
git clone https://github.com/ildu00/ReGraph.git
# Navigate to project directorycd ReGraph
# Install dependencies
npm install
# Start development server
npm run dev

API Usage

ReGraph provides an OpenAI-compatible API. Simply replace your API endpoint:

importopenaiclient=openai.OpenAI(
api_key="your-regraph-api-key",
base_url="https://api.regraph.tech/v1"
)
response=client.chat.completions.create(
model="gpt-5",
messages=[
{"role": "user", "content": "Hello, ReGraph!"}
]
)
print(response.choices[0].message.content)

cURL Example

curl -X POST https://api.regraph.tech/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "gpt-5", "messages": [{"role": "user", "content": "Hello!"}] }'

🖥️ For Hardware Providers

Earn passive income by contributing your unused compute resources to the ReGraph network.

Supported Hardware

  • GPU: NVIDIA RTX, Tesla, A100, H100
  • TPU: Google TPU v2, v3, v4
  • NPU: Intel Movidius, Apple Neural Engine
  • CPU: x86_64, ARM64
  • Mobile: Android/iOS devices with neural accelerators

Quick Setup

Linux/macOS:

curl -fsSL https://regraph.tech/install.sh | bash

Windows (PowerShell):

irm https://regraph.tech/install.ps1 | iex

Docker:

docker run -d --gpus all regraph/provider:latest

📚 API Reference

Endpoints

EndpointMethodDescription
/v1/chat/completionsPOSTChat completions (streaming supported)
/v1/completionsPOSTText completions
/v1/embeddingsPOSTGenerate embeddings
/v1/images/generationsPOSTImage generation
/v1/audio/transcriptionsPOSTAudio transcription
/v1/modelsGETList available models

Authentication

All API requests require authentication via Bearer token:

Authorization: Bearer YOUR_API_KEY

Get your API key at regraph.tech/dashboard.

🏗️ Architecture

+------------------------------------------------------------------+
| ReGraph Platform |
+------------------------------------------------------------------+
| |
| +-----------+ +-----------+ +-----------+ |
| | API GW | | Load Bal | | Auth | |
| +-----------+ +-----------+ +-----------+ |
| |
+------------------------------------------------------------------+
| |
| +----------------------------------------------------------+ |
| | Inference Router | |
| | | |
| | +---------+ +---------+ +---------+ | |
| | | Model A | | Model B | | Model C | ... | |
| | +---------+ +---------+ +---------+ | |
| +----------------------------------------------------------+ |
| |
+------------------------------------------------------------------+
| |
| +---------+ +---------+ +---------+ +---------+ |
| | GPU #1 | | GPU #2 | | TPU #1 | | NPU #1 | ... |
| |Provider | |Provider | |Provider | |Provider | |
| +---------+ +---------+ +---------+ +---------+ |
| |
+------------------------------------------------------------------+

🔧 Technology Stack

  • Frontend: React, TypeScript, Tailwind CSS, Vite
  • Backend: Supabase Edge Functions, PostgreSQL
  • Infrastructure: Distributed compute network
  • Authentication: JWT-based with API keys

📈 Features

For Developers

  • ✅ OpenAI-compatible API
  • ✅ 50+ AI models available
  • ✅ Streaming responses
  • ✅ Batch processing
  • ✅ Fine-tuning support
  • ✅ Usage analytics dashboard
  • ✅ Crypto & fiat payments

For Providers

  • ✅ Easy one-click setup
  • ✅ Automatic earnings
  • ✅ Real-time monitoring
  • ✅ Multi-device support
  • ✅ Crypto payouts
  • ✅ Competitive rates

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Links


Built with ❤️ by the ReGraph Team

About

The world's cheapest AI inference & training marketplace. Pay up to 80% less than traditional cloud providers.

Topics

Resources

Stars

1 star

Watchers

3 watching

Forks

Releases

Packages

Contributors

Languages