superflows  by Superflows-AI

Open-source toolkit for building an AI copilot for SaaS products

created 2 years ago
616 stars

Top 54.3% on sourcepulse

GitHubView on GitHub
Project Summary

Superflows is an open-source toolkit designed to help developers integrate AI-powered copilot capabilities into SaaS products. It enables natural language interaction for users to query data, perform actions via API calls, and analyze information, serving as an alternative to OpenAI's Assistants API.

How It Works

Superflows leverages a multi-LLM architecture supporting models like GPT-4 and Mixtral, combined with Retrieval Augmented Generation (RAG) for knowledge retrieval. It allows for API endpoint integration via OpenAPI specifications, enabling the AI to interact with a product's backend. The system includes a developer dashboard for configuration, testing, and debugging, along with stateful streaming and optional React UI components for seamless integration.

Quick Start & Requirements

  • Local Setup: Requires git, docker, docker compose, and npm. Local development necessitates a running Supabase instance.
    • Install dependencies: npm i, npm install supabase --save-dev.
    • Start Supabase: npx supabase start.
    • Configure .env file (from .env.example).
    • Run development mode: make run or npm run dev.
  • Docker Setup:
    • Clone repository, navigate to docker/development.
    • Make init.sh executable (chmod +x init.sh) and run it.
    • Configure .env with API keys (e.g., OPENAI_API_KEY).
    • Start containers: docker compose up -d build or docker-compose up -d build.
  • Cloud Version: Available at https://dashboard.superflows.ai.
  • Docs: https://docs.superflows.ai/
  • Demo: https://superflows.ai/crm-demo

Highlighted Details

  • Supports multiple LLMs (GPT-3.5, GPT-4, Mixtral, Llama2).
  • Features a developer dashboard for configuration and debugging.
  • Provides out-of-the-box React UI components for integration.
  • Allows API specification uploads for rapid setup.

Maintenance & Community

Licensing & Compatibility

  • The repository does not explicitly state a license in the README. Compatibility for commercial use or closed-source linking is undetermined.

Limitations & Caveats

Self-hosting instructions are not yet fully documented, requiring direct contact with the team. The project's licensing status is unclear, which may impact commercial adoption.

Health Check
Last commit

1 year ago

Responsiveness

1 week

Pull Requests (30d)
0
Issues (30d)
0
Star History
9 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems) and Travis Fischer Travis Fischer(Founder of Agentic).

pezzo by pezzolabs

0.2%
3k
Open-source LLMOps platform for streamlining AI workflows
created 2 years ago
updated 1 month ago
Feedback? Help us improve.