Self-host docker-chatgpt
v2023.05.29Self-hosted ChatGPT client with multi-model backend
- Stars
- 140
- CPU
- ~1%
- RAM
- ~10MB
- Storage
- ~10MB
- Ports
- 8090 (ChatGPT web client (frontend)), 8091 (Sparrow backend API server)
- Requires
- Sparrow backend
soulteary/chatgpt
What is docker-chatgpt?
docker-chatgpt is a lightweight, self-hosted web client that replicates the ChatGPT interface while letting you plug in multiple AI backends. The frontend (soulteary/chatgpt) is a static Vue application served on port 8090; it talks to a separate Go service called Sparrow (soulteary/sparrow) on port 8091. Sparrow acts as a unified gateway: it can forward requests to the official OpenAI API, to private Midjourney or FlagStudio image-generation endpoints, or to a Claude-compatible WebSocket service. All components are distributed as Docker images and started with a single docker-compose.yml. The project emphasizes privacy — no telemetry, no external calls unless you configure them — and runs in roughly 10 MB of disk and memory. Features include a model switcher, plugin system (browsing, code interpreter), conversation history, i18n, and custom data-source connectors. The code is licensed under WTFPL (client) and Apache-2.0 (backend). The latest release is v2023.05.29 from May 2023; development appears inactive since then.
Should you self-host docker-chatgpt?
docker-chatgpt scores 41/100 on selfhost.directory (how scoring works) and ranks #53 of 69 in AI Chat. It has 140 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 WTFPL-licensed.
Its closest alternative on selfhost.directory is openhands (87/100, 92 105 stars). It scores higher overall, so compare the two before you pick. See docker-chatgpt vs openhands side by side.
Features
- Conversation history
- Custom Data Sources
- Data Control
- Internationalization (I18N)
- Model switcher
- Multi-Model Support
- OpenAI API proxy support
- Plugin System
- Privacy-focused
- Response speed control
docker-chatgpt README
More in AI Chat
EgmaEgma is a self-hosted, open-source platform for simulation testing and production monitoring of voice agents with LiveKit, Pipecat, and Retell support.
EnclaveEnclave is a self-hosted, open-source AI companion platform creating a personal virtual world with expert AI residents and your digital twin.
ENZOENZO is a self-hosted AI workspace for 300+ models using your own API keys. Includes self-drafting agents, research, code generation, music player, encrypted vault.
exllamaOpen-source Python/C++/CUDA runner for 4-bit GPTQ-quantized Llama models on consumer NVIDIA GPUs, with a self-hosted chat web UI you can build and run in Docker.
FastChatSelf-hosted, open-source LLM serving platform: run open chat models behind a Gradio web UI, a CLI, or an OpenAI-compatible REST API.
faster-chatFaster Chat is a self-hosted, open-source AI chat interface for local and cloud LLMs with multi-user auth, encrypted keys, web search, and a fast Preact UI.
Flamehaven-FilesearchSelf-hosted RAG search engine with BM25+semantic hybrid search across 34 formats, multi-LLM support (Gemini, OpenAI, Claude, Ollama) for private document search.
FlowcatFlowcat is an open-source, self-hosted Rust runtime for real-time voice agents — single binary, no hosted control plane, native SIP/RTP/WebRTC, 80+ provider connectors.
frank-botFrank Bot is a self-hosted, open-source RAG chatbot using ChromaDB and Anthropic Claude. Designed for Australian workplaces with 12 industry-tuned vertical personalities.
Free-GPT4-WEB-APISelf-hosted, open-source web API for free, unlimited access to LLMs like GPT-4, Gemini, DeepSeek, and Claude via a single HTTP endpoint with optional web GUI.
fuseaifuseai is a self-hosted, open-source web app to chat with OpenAI's ChatGPT API. Supports single-user and multi-user modes with email auth, uses SQLite, runs via Docker.
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.
0 comments