u14app/neo-chat

A local-first AI chat workspace for models, agents, skills, plugins, search, RAG, voice, memory, and artifacts.

What it solves

Neo Chat provides a self-hostable, local-first workspace that centralizes multiple AI model providers, knowledge management, and complex agentic workflows into a single interface. It eliminates the need to switch between different AI platforms while giving users control over their data and model choices.

How it works

Users connect their own API keys from providers like Google, OpenAI, and Anthropic. The platform operates as a local-first application where conversation history is stored in the browser by default, with optional encrypted sync via WebDAV or S3. It integrates various capabilities including a RAG-based knowledge base, an Agent mode for tool-based workflows, and a Deep Research mode for generating cited reports. It also supports extensibility through OpenAPI plugins, Text Skills, and Model Context Protocol (MCP) servers.

Who it’s for

It is designed for users who want a private, customizable AI workspace that supports multiple models and advanced research capabilities without relying on a single proprietary chat interface.

Highlights

  • Multi-Model Support: Compatible with Google, OpenAI, Anthropic, and OpenAI-compatible endpoints.
  • Agentic Workflows: Includes an Agent mode for multi-step tool use and a Deep Research mode with reviewable plans and cited reports.
  • Knowledge Management: Features file attachments, local search, memory, and knowledge-base retrieval.
  • Extensible Architecture: Supports OpenAPI plugins, remote MCP servers, and a Docker bridge for local MCP tools.
  • Intelligent UI: Renders interactive elements like charts, calculators, quizzes, flashcards, and borderless HTML interfaces.
  • Local-First Privacy: Browser-based storage by default with ZIP backups and end-to-end encrypted synchronization.

Related

  • Project
    hAcKlyc/MyAgents

    An open-source desktop workspace that integrates AI agents with local files, terminals, and a task management system to enable continuous, local-first AI workflows.

  • Project
    holaboss-ai/holaOS

    An agentic workspace that integrates AI agents side-by-side with real applications and chat tools, featuring local-first memory and shared tool access.

  • Project
    kamjin3086/chatless

    A local-first desktop AI chat client that supports cloud and local models, featuring local RAG for document-based knowledge retrieval and MCP protocol integration.

  • Project
    LibreChat-AI/LibreChat

    A self-hosted, open-source AI chat platform that unifies multiple AI providers into a single, privacy-focused interface with support for agents, code execution, and multi-user management.