Open-source alternatives to ChatGPT
ChatGPT is OpenAI's hosted chat interface to its models. The list below is every catalog tool tagged Generative Artificial Intelligence (GenAI), which is the closest the catalog gets to the same job; none of them has been checked feature by feature against ChatGPT.
| Tool | Stars |
|---|---|
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models. MIT · released 2026-09-05 | 180,418 |
User-friendly AI Interface, supports Ollama, OpenAI API. BSD-3-Clause · released 2026-08-31 | 151,260 |
Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifacts / Thinking. ⊘ Proprietary · released 2026-09-07 | 82,297 |
All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more. MIT · released 2026-08-27 | 65,748 |
Run your AI models locally and generate images and audio (alternative to OpenAI and Claude). MIT · released 2026-08-20 | 48,963 |
Enhanced ChatGPT-compatible AI chat interface supporting multiple AI providers, with multi-user auth, message search, and plugin support. MIT · released 2026-09-03 | 42,902 |
Your AI second brain. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI. AGPL-3.0 · released 2026-03-26 | 37,186 |
AI-powered search engine (alternative to Perplexity AI). MIT · released 2026-04-10 | 36,674 |
Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more. MIT · released 2026-09-05 | 31,964 |
AI-powered deep research tool with multi-source search (arXiv, PubMed, web), PDF text extraction, and encrypted local storage. MIT · released 2026-08-28 | 9,054 |
LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering. MIT · released 2026-09-07 | 4,728 |
Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI. Apache-2.0 · released 2026-09-07 | 3,209 |
AI gateway written in Go with a unified OpenAI-compatible API for multiple LLM providers, USD cost tracking, budgets, usage analytics, guardrails, caching, and an admin dashboard. MIT · released 2026-09-06 | 1,116 |
Kubernetes operator for self-hosted LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), multi-GPU sharding, NVIDIA CUDA + Apple Silicon Metal support, and OpenAI-compatible API. Apache-2.0 · released 2026-09-05 | 208 |
All mapped products · data from awesome-selfhosted, CC BY-SA 3.0