Self-host fuseai
v0.1.0Self-hosted web app for chatting with OpenAI APIs
- Stars
- 291
- Port
- 3000 (HTTP web interface)
- Requires
- SQLite
bitswired/ai-chat-appWhat is fuseai?
fuseai is a self-hosted web application for interacting with OpenAI's ChatGPT API. It provides a chat interface built with Next.js, React, TypeScript, and the Mantine component library. The app supports two modes: single-user (with a pre-configured admin account) and multi-user (with email-based authentication via SMTP). It uses Prisma with SQLite for data persistence, tRPC for API communication, and NextAuth for authentication. Deployment is via Docker images published as bitswired/ai-chat-app with separate tags for single-user and multi-user modes. The project is in early development (v0.1.0) with a roadmap including Whisper API integration, prompt templates, and mobile improvements.
Should you self-host fuseai?
fuseai scores 37/100 on selfhost.directory (how scoring works) and ranks #59 of 69 in AI Chat. It has 291 GitHub stars.
There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.
Setup is moderate: expect some configuration beyond a single command. An official Docker image is available. It is written mostly in Typescript.
Its closest alternative on selfhost.directory is LibreChat (85/100, 46 424 stars). It scores higher overall, so compare the two before you pick. See fuseai vs LibreChat side by side.
Features
- Chat with OpenAI ChatGPT
- Email authentication
- Multi-User Mode
- Single-User Mode
- Unraid supportCommunity contributed by barnito
fuseai README
More in AI Chat
gemini-web2api-goRun your own OpenAI-compatible endpoint for Google's free Gemini web UI — no API key, no paid tier. Single Go binary or Docker image with dashboard, cookie/proxy pools.
ggrunggrun is a self-hosted terminal UI for discovering, downloading, and running local GGUF models with automatic multi-GPU memory placement and an OpenAI-compatible API.
GPTPortalGPTPortal is a self-hosted, open-source Node.js web app providing a unified chat interface for multiple LLM providers and local endpoints like Ollama.
gpt-researcherSelf-hosted, open-source deep research agent: a planner splits your question, parallel researchers scan 20+ web or local sources, and it writes a cited report.
GuaardvarkSelf-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.
hal0hal0 is a self-hosted, open-source AI inference platform turning a Linux machine into a private OpenAI-compatible appliance.
hermesclawSelf-hosted Python proxy running Hermes Agent, OpenClaw, and OpenCode on one WeChat account via iLink polling, local proxies, and ACP bridge.
hermes-studioEkko Studio unites chat agents and 14 coding CLIs in one self-hosted web console with group chat, visual workflows, profiles, voice, and device sync.
Hermes SuiteSelf-hosted Docker/Podman image combining Hermes AI agent gateway, browser chat WebUI, and monitoring dashboard in one container.
Hermes-WorkspaceHermes Workspace is a self-hosted, open-source web UI command center for AI agents — combining chat, terminal, memory, skills, and multi-agent orchestration.
hivekeepSelf-hosted AI agent team with persistent memory, collaboration, custom tools, and 6 messaging channels — all in one container.
HiveMtkSelf-hosted AI marketing SCRM unifying 10+ channels with ReAct agents (45 tools) and local LLM inference. Zero data egress, AGPL-3.0 licensed.

0 comments