Logo
Deploy Now

SaaS Alternative

ChatGPT Plus Poe Claude.ai Google Gemini TypingMind

Categories

Self-Hosted Productivity AI LLM Chat Assistant ChatGPT Interface

Stars

88394

Forks

59505

Watchers

482

Developer links

Last Updated: 07-06-2026 06:57 PM (UTC)

NextChat

Thirteen-plus LLM providers, one unified client: NextChat (formerly ChatGPT-Next-Web) is an open-source AI chat interface built on Next.js that spans OpenAI GPT-4, Anthropic Claude, Google Gemini, DeepSeek, Groq, Azure endpoints, and self-hosted backends like Ollama, LocalAI, and RWKV-Runner. Its defining trait is minimalism - the first screen loads in about 100 KB, the desktop client is roughly 5 MB, and there is no database or user system to operate; chat history lives locally in the browser with optional WebDAV or UpStash Redis sync. The Mask system saves reusable prompt-template personas you can share and debug, long conversations auto-compress to fit context windows, and Markdown rendering covers LaTeX, Mermaid diagrams, and code highlighting with streaming responses. Plugins add web search and calculators, MCP support enables external tool calling, and Artifacts previews generated content in a separate pane. Ships as a web app, Docker image, and Tauri desktop builds for Windows, macOS, and Linux, translated into 20+ languages. MIT-licensed.

NextChat
NextChat
NextChat
NextChat
NextChat

Benefits

  • Pay Per Token, Not Per Month
  • Bring your own API keys and pay raw usage rates instead of a $20-per-month ChatGPT Plus subscription, while switching freely between GPT-4, Claude, and Gemini in one window.
  • Nothing to Operate
  • No database, no user system, no background workers - the app is a single-page client, so hosting it is as close to maintenance-free as a self-hosted service gets.
  • Conversations Stay Local
  • Chat history is stored in the browser rather than a vendor's cloud, with optional encrypted sync via WebDAV or UpStash if you want cross-device continuity.
  • Fast Everywhere
  • A ~100 KB first paint and a ~5 MB desktop binary make it responsive on weak hardware and slow connections where heavier chat UIs lag.

Features

  • 13+ LLM Providers
  • OpenAI, Anthropic, Google, DeepSeek, Groq, and Azure endpoints, plus self-hosted Ollama, LocalAI, and RWKV backends behind one provider abstraction.
  • Mask Persona System
  • Create, save, share, and debug prompt-template characters that bundle system prompts and model settings into reusable chat tools.
  • Auto-Compressed History
  • Long conversations summarize automatically to stay within context windows while preserving continuity.
  • Rich Markdown Rendering
  • LaTeX math, Mermaid diagrams, syntax-highlighted code, and streaming responses, with dark mode and PWA support.
  • Plugins, MCP, and Artifacts
  • Web search and calculator plugins, Model Context Protocol for external tool calling, and an Artifacts pane for previewing and sharing generated content.
  • Cross-Platform Clients
  • Responsive web app, Docker image, and Tauri desktop builds for Windows, macOS, and Linux, localized into 20+ languages.