ADH Multi-Tool AI Chat Assistant

ADH is a multi-tool AI chat assistant built for real productivity, not just conversation. At its core, users can choose between multiple leading open weight language models MiniMax M3, DeepSeek V4, GLM 5, and Kimi K2 (note: models cant be switched in an existing chat started with a different model,ie model can be chnaged while starting a new chat ) all served through Fireworks AI's inference platform, switching models midconversation depending on the task at hand. A custom token slider lets users control the response length directly, from short and quick to long and detailed, giving fine-grained control over output depth. Web Search: powered by the Tavily API, pulling in real-time information from the internet for current events, facts, and anything beyond the model's training data. Code Execution :runs Python code snippets via the Piston API and returns the output inline, letting users verify logic without leaving the chat. File Analysis :reads and summarizes uploaded PDFs (via pdf2json), CSVs, and text files, extracting content for the model to reference. Image Generation creates images on demand from a text prompt using Pollinations AI, rendered directly in the conversation with a one-click download. Voice Input :hands free message dictation using the browser's native Web Speech API, with live transcription as the user speaks Every generated image can be downloaded directly from the chat, and entire conversations can be exported as clean, styled PDFs preserving both user and assistant messages for sharing, documentation, or record-keeping. The frontend is built with React and a custom dark, fully responsive across desktop and mobile. The backend runs on Express, deployed on Railway, handling file uploads, web search queries, code execution, image generation requests, and streaming chat responses via server Sent Events for a smooth, real time typing experience. Chat history persists locally in the browser.