CoAI

Stale

GitHub TypeScript Apache-2.0

Description

Next Generation Multi-tenant AI One-Stop Solution with built-in admin and billing. Enterprise-grade unified LLM gateway supporting 200+ models and 35+ providers.

Key Features

Unified LLM gateway supporting 200+ models from 35+ providers including OpenAI, Anthropic, and Gemini
Enterprise-grade multi-tenant architecture with built-in admin dashboard and subscription billing system
Beautiful responsive UI compatible with PC/Pad/Mobile, supporting light/dark themes and i18n
Powerful channel management with priority settings, load balancing, and automatic failure retry
Supports text-to-image (DALL-E, Midjourney, Stable Diffusion) and full Markdown rendering including LaTeX
Model caching: identical request parameter hashes return cached results with no billing on cache hits

Use Cases

💡 Internal enterprise AI service platform with independent tenant and quota management per team

💡 AI startups quickly build multi-model aggregation APIs to offer SaaS services externally

💡 Educational institutions deploy unified AI platforms with multi-language and multi-model comparison

💡 Distribute LLM capabilities via OpenAI API-compatible format while running B2B and B2C businesses

💡 Web-search-augmented conversations via SearXNG, combined with OCR and file parsing for RAG applications

Strengths & Limitations

✅ Strengths

• High community interest (9.3k stars)
• Permissive open-source license (Apache-2.0)
• Established track record (3 years in production)
• Responsive to issues, low backlog

Quick Start

1. Clone the repository and navigate to the project directory
2. Configure model provider API keys in the .env file
3. Run docker compose up to start the service
4. Access localhost:3000 to enter the admin dashboard
5. Configure model channels and billing rules in the admin panel
6. Register a user and start testing conversations

Visit GitHub Visit Website

Related Projects

Deep Research Web UI

2.2k · TypeScript

Active A

An AI-powered research assistant web UI that performs iterative, deep research on any topic by combining search engines with LLM reasoning.

typescriptagentllm +3

· Client-side mode with API keys staying locally in the browser for maximum security
· Real-time streaming AI responses with search visualization using tree structure
· Multi-language web search support via Tavily, Firecrawl, and Google PSE providers

View on GitHub

Langchain-Chatchat

38.6k · Python

Stale B

A local knowledge base RAG and Agent application platform built on Langchain with support for ChatGLM, Qwen, Llama and other LLMs, offering conversation, knowledge base management, and agent capabilities.

ragllmpython +3

· Local knowledge base QA — Document loading, text splitting, vectorization and semantic retrieval via Langchain with BM25+KNN hybrid search
· Multi-framework model inference — Supports Xinference, Ollama, FastChat, LocalAI for GLM-4, Qwen2, Llama3 and more
· Agent tool calling — Optimized for ChatGLM3/Qwen with auto tool selection, single tool parameter parsing, and multimodal image chat

View full details → View on GitHub

NextJS Ollama LLM UI

1.4k · TypeScript

Stale C

Fully-featured web interface for Ollama LLMs built with Next.js. Supports local model conversations, multi-model switching, and browser-side persistent storage.

typescriptchatbotllm +2

· Beautiful, intuitive ChatGPT-inspired interface, ready to use out of the box
· Fully local operation with chats stored in browser localStorage, no database needed
· Fully responsive design with consistent experience on mobile and desktop

View on GitHub

Koishi

6.2k · TypeScript