LocalGPT lets users chat with documents on their local device using GPT models.
Open source
24 alternativesPrivate Gpt
PrivateGPT provides an API layer for private AI applications using local models, retrieval, tools, and MCP.
About Private Gpt
PrivateGPT is an open-source API layer for building AI applications on local models. It does not run models itself. Instead, it connects to an OpenAI-compatible inference server, such as Ollama, llama.cpp, or vLLM, through the OPENAI_API_BASE setting. Developers can use it to add retrieval, tools, file ingestion, and database access to an application without writing those backend components from scratch. The API follows the Anthropic API specification, and the built-in tools mirror the Claude API.
The project is designed to keep models local, but its privacy depends on how it is configured. Its built-in web search and web fetch tools access external web content, and it lists integrations with applications such as Claude Desktop, Claude for Microsoft 365, and n8n. Pricing is not stated in the source. The repository is listed as open source. Installation commands are given for macOS, Linux, and Windows.
Key features
- Retrieval with citations and agentic RAG
- File and artifact ingestion
- Custom tools and MCP connectors
- Structured access to databases and CSVs
- Built-in web search, web fetch, and code execution tools
- Messages API with streaming, async, and token counting
Best for: Developers who want to build private AI applications on locally hosted models and need a backend API with retrieval and tool support.
Good for
- Open source, with a repository on GitHub
- Works with any OpenAI-compatible inference server
- The source states that it powers Zylon, an on-premise AI platform
Watch out for
- Does not run models itself and requires a separate OpenAI-compatible LLM server
- The built-in workbench UI is described as a demonstrator, not the core product
- The example setup requires large model downloads, about 24 GB for the LLM
Private Gpt at a glance
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Private Gpt alternatives
Tools and sites you could use instead, ranked by how closely they match.
py-vectara-agentic is a Python library for creating AI assistants with Vectara using agentic retrieval-augmented generation.
Open source
24 alternatives
Intelli builds chatbots and agents from user-defined intents and model choices.
Open source
24 alternatives
OpenChatKit provides an open-source base for creating specialized or general-purpose chat models.
Open source
24 alternatives
Petals runs large language models across distributed computers and supports fine-tuning and inference.
Open source
24 alternatives
GPT4All runs language models locally on a range of devices through open-source software.
Open source
24 alternativesPopular in AI Chatbots & Assistants
Well-known listings from the same topic.
Lumolumo.proton.meMicrosoft Copilotcopilot.microsoft.comLearn Aboutlearning.google.com/experiments/learn-aboutEidoloneidolonai.comFlowHuntflowhunt.ioPine AI19pine.ai
Private Gpt FAQ
Does PrivateGPT run AI models on its own?
No. It connects to an OpenAI-compatible inference server, set through the OPENAI_API_BASE variable. The source gives Ollama, llama.cpp, and vLLM as examples.
Is there a user interface?
PrivateGPT includes a built-in workbench UI at /ui for testing and demos. The source states that the API is the main product and that developers are expected to build their own applications on it.
What is the easiest way to get started?
The source describes Ollama as the easiest starting point for the required LLM server.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.