OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Auto Deep Research

Auto Deep Research is an open-source Python personal AI assistant built on the AutoAgent framework to conduct deep research and produce research responses. It supports multiple LLM providers, file uploads, and models that interact with or without function calling.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Auto Deep Research — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to run a self-managed research assistant through its documented command-line launch path and can supply an API key for a chosen LLM provider.

Who it is for

  • People who want an AI assistant to conduct deep research using an LLM provider they select.
  • Developers or technically comfortable users who can install a Python repository and configure provider API keys.

Documented uses

  • Submit a research question to an autonomous assistant and receive a research response.
  • Choose among supported LLM provider ecosystems for the research workflow.
  • Use models with or without function-calling interaction.
Before you choose

Requirements & limits

  • The documented local installation uses Conda, Python 3.10, Git and pip.
  • The chosen LLM provider requires its own API key in an environment file.
  • Docker is required for the documented containerized agent-interactive environment.
  • The README describes file-upload support for additional data interaction.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and configure Auto Deep Research

Set up the repository and configure an LLM provider before launching the assistant.

Before you start

  • Conda and Python 3.10
  • An API key for the LLM provider you plan to use
  • Docker installed if using the documented containerized agent environment

Steps

  1. Create and activate a Conda environment with Python 3.10.

  2. Clone the repository, change into its directory and install it with the command below.

    Documented command
    pip install -e .

  3. Create an environment file based on .env.template and add the key for the provider you intend to use.

  4. Run auto deep-research to start the assistant.

Expected outcome

The documented installation and provider configuration are in place, and the launch command is available to start the assistant.

Guide limitations

  • The README says only the API key for the provider being used is needed.
  • The guide documents setup and launch, not the content or quality of a completed research response.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
HKUDS/Auto-Deep-Research · Official homepage title · retained in its source language
How we review sourcesSuggest a correction