Your household gets one private chat front door for the models you already run, local or hosted, with voice, search, and coding agents included from the same server. Point it at Ollama, vLLM, llama.cpp, SGLang, or LM Studio, then add OpenAI, Anthropic, Gemini, DeepSeek, Bedrock, or OpenRouter beside them. Models that support tools can answer with charts, tables, forms, and follow-up buttons instead of plain paragraphs. Ask for a live conversation and speak, hear the reply, cut in mid-sentence, and keep going; Parakeet handles recognition and Kokoro speaks back on CPU or GPU. Documents open beside the chat for drafting and revising Markdown, code, web pages, SVG, and Mermaid diagrams. Attach spreadsheets, PDFs, images, Word, Excel, CSV, or source files and run Python on them in an offline sandbox that returns charts, cleaned data, or finished documents. Search the web through bundled SearXNG or Brave, read pages with inline citations, connect MCP servers, and set thinking controls per local model. Replies keep streaming after you close the tab, full-text search finds old answers, and read-only links share a conversation. Coding agents run on your machines or over SSH and stay reachable from browser, desktop, Android, or iOS. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

One chat window, every model you already pay for, and a history that stays in your own browser unless you decide otherwise. Neo Chat connects to Google, OpenAI, Anthropic, and any OpenAI-compatible gateway, so switching models mid-project takes one click. Agent mode runs multi-step tool workflows, and Deep Research drafts a plan for approval before producing a cited report that can be resumed if it stops. Attach files, build a knowledge base for retrieval, and let memory carry preferences between conversations. Browse a market of ready-made assistants and text skills, add OpenAPI plugins or remote MCP servers, and search the web through a configurable service. Answers render Markdown, math, diagrams, and charts, plus editable artifacts and interactive checklists, quizzes, flashcards, and calculators. Voice input and read-aloud sit beside the composer, and optional encrypted sync moves settings between devices. An access password can protect a shared deployment, and a health page checks that everything is configured. Switch models mid-conversation, keep one history, and stop juggling a tab for every provider. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.