ai-shifu/ChatALL

Provides concurrent prompt execution across 40+ LLM backends with mixed web-scraping and API access, allowing developers to compare model outputs side-by-side for prompt optimization and capability benchmarking. Built as a desktop application (Electron-based) with local chat history storage, quick-prompt queueing to bypass sequential response waiting, and flexible view layouts from single to three-column displays. Supports both commercial APIs (OpenAI, Anthropic, Google) and open-source deployments (Hugging Face spaces, Gradio), with emphasis on web-connected bot reliability caveats due to frequent provider-side breaking changes.

16,315 stars.