
Auto-Deep-Research
Your Fully-Automated Personal AI Assistant, and Open-Source & Cost-Efficient Alternative to OpenAI's Deep Research
Stars: 163

Auto-Deep-Research is an open-source and cost-efficient alternative to OpenAI's Deep Research, based on the AutoAgent framework. It offers high performance, universal LLM support, flexible interaction, cost-efficiency, file support, and one-click launch. Users can seamlessly integrate with various LLMs, handle file uploads, and start instantly with a simple command. The tool aims to provide a fully-automated and personalized AI assistant at a lower cost, catering to community needs and showcasing the potential of AutoAgent for practical AI applications.
README:
Welcome to Auto-Deep-Research! Auto-Deep-Research is a open-source and cost-efficient alternative to OpenAI's Deep Research, based on AutoAgent framework.
- π High Performance: Ranks the #1 spot among open-sourced methods, delivering comparable performance to OpenAI's Deep Research.
- π Universal LLM Support: Seamlessly integrates with A Wide Range of LLMs (e.g., OpenAI, Anthropic, Deepseek, vLLM, Grok, Huggingface ...)
- π Flexible Interaction: Supports both function-calling and non-function-calling interaction LLMs.
- π° Cost-Efficient: Open-source alternative to Deep Research's $200/month subscription with your own pay-as-you-go LLM API keys.
- π File Support: Handles file uploads for enhanced data interaction
- π One-Click Launch: Get started instantly with a simple
auto deep-research
command - Zero Configuration needed, truly out-of-the-box experience.
π Own your own personal assistant with much lower cost. Try π₯Auto-Deep-Researchπ₯ Now!
- [2025, Feb 16]: Β ππWe've cleaned up the codebase of AutoAgent, removed the irrelevant parts for Auto-Deep-Research and released the first version of Auto-Deep-Research.
- β¨ Features
- π₯ News
- π§ Why to release Auto-Deep-Research?
- β‘ Quick Start
- βοΈ Todo List
- π Documentation
- π€ Join the Community
- π Acknowledgements
- π Cite
After releasing AutoAgent (previously known as MetaChain) for a week, we've observed three compelling reasons to introduce Auto-Deep-Research:
-
Community Interest We noticed significant community interest in our Deep Research alternative functionality. In response, we've streamlined the codebase by removing non-Deep-Research related components to create a more focused tool.
-
Framework Extensibility Auto-Deep-Research serves as the first ready-to-use product built on AutoAgent, demonstrating how quickly and easily you can create powerful Agent Apps using our framework.
-
Community-Driven Improvements We've incorporated valuable community feedback from the first week, introducing features like one-click launch and enhanced LLM compatibility to make the tool more accessible and versatile.
Auto-Deep-Research represents our commitment to both the community's needs and the demonstration of AutoAgent's potential as a foundation for building practical AI applications.
conda create -n auto_deep_research python=3.10
conda activate auto_deep_research
git clone https://github.com/HKUDS/Auto-Deep-Research.git
cd Auto-Deep-Research
pip install -e .
We use Docker to containerize the agent-interactive environment. So please install Docker first. You don't need to manually pull the pre-built image, because we have let Auto-Deep-Research automatically pull the pre-built image based on your architecture of your machine.
Create a environment variable file, just like .env.template
, and set the API keys for the LLMs you want to use. Not every LLM API Key is required, use what you need.
You can run auto deep-research
to start Auto-Deep-Research. Some configuration of this command is shown below.
-
--container_name
: Name of the Docker container (default: 'deepresearch') -
--port
: Port for the container (default: 12346) -
COMPLETION_MODEL
: Specify the LLM model to use, you should follow the name of Litellm to set the model name. (Default:claude-3-5-sonnet-20241022
) -
DEBUG
: Enable debug mode for detailed logs (default: False) -
API_BASE_URL
: The base URL for the LLM provider (default: None) -
FN_CALL
: Enable function calling (default: None). Most of time, you could ignore this option because we have already set the default value based on the model name.
We will show you how easy it is to start Auto-Deep-Research with different LLM providers.
- set the
ANTHROPIC_API_KEY
in the.env
file.
ANTHROPIC_API_KEY=your_anthropic_api_key
- run the following command to start Auto-Deep-Research.
auto deep-research # default model is claude-3-5-sonnet-20241022
- set the
OPENAI_API_KEY
in the.env
file.
OPENAI_API_KEY=your_openai_api_key
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=gpt-4o auto deep-research
- set the
MISTRAL_API_KEY
in the.env
file.
MISTRAL_API_KEY=your_mistral_api_key
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=mistral/mistral-large-2407 auto deep-research
- set the
GEMINI_API_KEY
in the.env
file.
GEMINI_API_KEY=your_gemini_api_key
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=gemini/gemini-2.0-flash auto deep-research
- set the
HUGGINGFACE_API_KEY
in the.env
file.
HUGGINGFACE_API_KEY=your_huggingface_api_key
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=huggingface/meta-llama/Llama-3.3-70B-Instruct auto deep-research
- set the
GROQ_API_KEY
in the.env
file.
GROQ_API_KEY=your_groq_api_key
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=groq/deepseek-r1-distill-llama-70b auto deep-research
- set the
OPENAI_API_KEY
in the.env
file.
OPENAI_API_KEY=your_api_key_for_openai_compatible_endpoints
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=openai/grok-2-latest API_BASE_URL=https://api.x.ai/v1 auto deep-research
We recommend using OpenRouter as LLM provider of DeepSeek-R1 temporarily. Because official API of DeepSeek-R1 can not be used efficiently.
- set the
OPENROUTER_API_KEY
in the.env
file.
OPENROUTER_API_KEY=your_openrouter_api_key
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=openrouter/deepseek/deepseek-r1 auto deep-research
- set the
DEEPSEEK_API_KEY
in the.env
file.
DEEPSEEK_API_KEY=your_deepseek_api_key
- run the following command to start Auto-Deep-Research.
COMPLETION_MODEL=deepseek/deepseek-chat auto deep-research
You can import the browser cookies to the browser environment to let the agent better access some specific websites. For more details, please refer to the cookies folder.
More features coming soon! π Web GUI interface under development.
Auto-Deep-Research is continuously evolving! Here's what's coming:
- π₯οΈ GUI Agent: Supporting Computer-Use agents with GUI interaction
- ποΈ Code Sandboxes: Supporting additional environments like E2B
- π¨ Web Interface: Developing comprehensive GUI for better user experience
Have ideas or suggestions? Feel free to open an issue! Stay tuned for more exciting updates! π
A more detailed documentation is coming soon π, and we will update in the Documentation page.
If you think the Auto-Deep-Research is helpful, you can join our community by:
- Join our Slack workspace - Here we talk about research, architecture, and future development.
- Join our Discord server - This is a community-run server for general discussion, questions, and feedback.
- Read or post Github Issues - Check out the issues we're working on, or add your own ideas.
Rome wasn't built in a day. Auto-Deep-Research is built on the AutoAgent framework. We extend our sincere gratitude to all the pioneering works that have shaped AutoAgent, including OpenAI Swarm for framework architecture inspiration, Magentic-one for the three-agent design insights, OpenHands for documentation structure, and many other excellent projects that contributed to agent-environment interaction design. Your innovations have been instrumental in making both AutoAgent and Auto-Deep-Research possible.
@misc{AutoAgent,
title={{AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents}},
author={Jiabin Tang, Tianyu Fan, Chao Huang},
year={2025},
eprint={202502.05957},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2502.05957},
}
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for Auto-Deep-Research
Similar Open Source Tools

Auto-Deep-Research
Auto-Deep-Research is an open-source and cost-efficient alternative to OpenAI's Deep Research, based on the AutoAgent framework. It offers high performance, universal LLM support, flexible interaction, cost-efficiency, file support, and one-click launch. Users can seamlessly integrate with various LLMs, handle file uploads, and start instantly with a simple command. The tool aims to provide a fully-automated and personalized AI assistant at a lower cost, catering to community needs and showcasing the potential of AutoAgent for practical AI applications.

AutoAgent
AutoAgent is a fully-automated and zero-code framework that enables users to create and deploy LLM agents through natural language alone. It is a top performer on the GAIA Benchmark, equipped with a native self-managing vector database, and allows for easy creation of tools, agents, and workflows without any coding. AutoAgent seamlessly integrates with a wide range of LLMs and supports both function-calling and ReAct interaction modes. It is designed to be dynamic, extensible, customized, and lightweight, serving as a personal AI assistant.

trieve
Trieve is an advanced relevance API for hybrid search, recommendations, and RAG. It offers a range of features including self-hosting, semantic dense vector search, typo tolerant full-text/neural search, sub-sentence highlighting, recommendations, convenient RAG API routes, the ability to bring your own models, hybrid search with cross-encoder re-ranking, recency biasing, tunable popularity-based ranking, filtering, duplicate detection, and grouping. Trieve is designed to be flexible and customizable, allowing users to tailor it to their specific needs. It is also easy to use, with a simple API and well-documented features.

pear-landing-page
PearAI Landing Page is an open-source AI-powered code editor managed by Nang and Pan. It is built with Next.js, Vercel, Tailwind CSS, and TypeScript. The project requires setting up environment variables for proper configuration. Users can run the project locally by starting the development server and visiting the specified URL in the browser. Recommended extensions include Prettier, ESLint, and JavaScript and TypeScript Nightly. Contributions to the project are welcomed and appreciated.

Devon
Devon is an open-source pair programmer tool designed to facilitate collaborative coding sessions. It provides features such as multi-file editing, codebase exploration, test writing, bug fixing, and architecture exploration. The tool supports Anthropic, OpenAI, and Groq APIs, with plans to add more models in the future. Devon is community-driven, with ongoing development goals including multi-model support, plugin system for tool builders, self-hostable Electron app, and setting SOTA on SWE-bench Lite. Users can contribute to the project by developing core functionality, conducting research on agent performance, providing feedback, and testing the tool.

UNav-Sim
UNav-Sim is an open-source underwater robotics simulator tool that leverages the power of Unreal Engine 5 (UE5) and AirSim to provide highly detailed rendering and simulation capabilities. With UNav-Sim, you can explore underwater terrains, design and test autonomous underwater vehicles (AUVs), and accelerate your learning and experimentation process in the field of underwater robotics.

felafax
Felafax is a framework designed to tune LLaMa3.1 on Google Cloud TPUs for cost efficiency and seamless scaling. It provides a Jupyter notebook for continued-training and fine-tuning open source LLMs using XLA runtime. The goal of Felafax is to simplify running AI workloads on non-NVIDIA hardware such as TPUs, AWS Trainium, AMD GPU, and Intel GPU. It supports various models like LLaMa-3.1 JAX Implementation, LLaMa-3/3.1 PyTorch XLA, and Gemma2 Models optimized for Cloud TPUs with full-precision training support.

copywriterproai-backend
CopywriterProAI is the world's first open-source AI writing platform for SEO and Ad Copy. The backend repository powers the AI capabilities and manages content processing for smooth operation. It provides an AI writing assistant that works behind the scenes to assist users in content creation.

ai2-kit
A toolkit for computational chemistry research, featuring tools to facilitate automated workflows. Includes tools for NMR prediction, dynamic catalysis research, proton transfer analysis, amorphous oxides structure analysis, reweighting, and more. Users can install 'ai2-kit' via pip and explore various domain-specific and general tools for processing system data and filtering structures by model deviation.

ProX
ProX is a lm-based data refinement framework that automates the process of cleaning and improving data used in pre-training large language models. It offers better performance, domain flexibility, efficiency, and cost-effectiveness compared to traditional methods. The framework has been shown to improve model performance by over 2% and boost accuracy by up to 20% in tasks like math. ProX is designed to refine data at scale without the need for manual adjustments, making it a valuable tool for data preprocessing in natural language processing tasks.

resume-job-matcher
Resume Job Matcher is a Python script that automates the process of matching resumes to a job description using AI. It leverages the Anthropic Claude API or OpenAI's GPT API to analyze resumes and provide a match score along with personalized email responses for candidates. The tool offers comprehensive resume processing, advanced AI-powered analysis, in-depth evaluation & scoring, comprehensive analytics & reporting, enhanced candidate profiling, and robust system management. Users can customize font presets, generate PDF versions of unified resumes, adjust logging level, change scoring model, modify AI provider, and adjust AI model. The final score for each resume is calculated based on AI-generated match score and resume quality score, ensuring content relevance and presentation quality are considered. Troubleshooting tips, best practices, contribution guidelines, and required Python packages are provided.

Neurite
Neurite is an innovative project that combines chaos theory and graph theory to create a digital interface that explores hidden patterns and connections for creative thinking. It offers a unique workspace blending fractals with mind mapping techniques, allowing users to navigate the Mandelbrot set in real-time. Nodes in Neurite represent various content types like text, images, videos, code, and AI agents, enabling users to create personalized microcosms of thoughts and inspirations. The tool supports synchronized knowledge management through bi-directional synchronization between mind-mapping and text-based hyperlinking. Neurite also features FractalGPT for modular conversation with AI, local AI capabilities for multi-agent chat networks, and a Neural API for executing code and sequencing animations. The project is actively developed with plans for deeper fractal zoom, advanced control over node placement, and experimental features.

EasyInstruct
EasyInstruct is a Python package proposed as an easy-to-use instruction processing framework for Large Language Models (LLMs) like GPT-4, LLaMA, ChatGLM in your research experiments. EasyInstruct modularizes instruction generation, selection, and prompting, while also considering their combination and interaction.

langmanus
LangManus is a community-driven AI automation framework that combines language models with specialized tools for tasks like web search, crawling, and Python code execution. It implements a hierarchical multi-agent system with agents like Coordinator, Planner, Supervisor, Researcher, Coder, Browser, and Reporter. The framework supports LLM integration, search and retrieval tools, Python integration, workflow management, and visualization. LangManus aims to give back to the open-source community and welcomes contributions in various forms.

RooFlow
RooFlow is a VS Code extension that enhances AI-assisted development by providing persistent project context and optimized mode interactions. It reduces token consumption and streamlines workflow by integrating Architect, Code, Test, Debug, and Ask modes. The tool simplifies setup, offers real-time updates, and provides clearer instructions through YAML-based rule files. It includes components like Memory Bank, System Prompts, VS Code Integration, and Real-time Updates. Users can install RooFlow by downloading specific files, placing them in the project structure, and running an insert-variables script. They can then start a chat, select a mode, interact with Roo, and use the 'Update Memory Bank' command for synchronization. The Memory Bank structure includes files for active context, decision log, product context, progress tracking, and system patterns. RooFlow features persistent context, real-time updates, mode collaboration, and reduced token consumption.

julep
Julep is an advanced platform for creating stateful and functional AI apps powered by large language models. It offers features like statefulness by design, automatic function calling, production-ready deployment, cron-like asynchronous functions, 90+ built-in tools, and the ability to switch between different LLMs easily. Users can build AI applications without the need to write code for embedding, saving, and retrieving conversation history, and can connect to third-party applications using Composio. Julep simplifies the process of getting started with AI apps, whether they are conversational, functional, or agentic.
For similar tasks

Azure-Analytics-and-AI-Engagement
The Azure-Analytics-and-AI-Engagement repository provides packaged Industry Scenario DREAM Demos with ARM templates (Containing a demo web application, Power BI reports, Synapse resources, AML Notebooks etc.) that can be deployed in a customerβs subscription using the CAPE tool within a matter of few hours. Partners can also deploy DREAM Demos in their own subscriptions using DPoC.

sorrentum
Sorrentum is an open-source project that aims to combine open-source development, startups, and brilliant students to build machine learning, AI, and Web3 / DeFi protocols geared towards finance and economics. The project provides opportunities for internships, research assistantships, and development grants, as well as the chance to work on cutting-edge problems, learn about startups, write academic papers, and get internships and full-time positions at companies working on Sorrentum applications.

tidb
TiDB is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads. It is MySQL compatible and features horizontal scalability, strong consistency, and high availability.

zep-python
Zep is an open-source platform for building and deploying large language model (LLM) applications. It provides a suite of tools and services that make it easy to integrate LLMs into your applications, including chat history memory, embedding, vector search, and data enrichment. Zep is designed to be scalable, reliable, and easy to use, making it a great choice for developers who want to build LLM-powered applications quickly and easily.

telemetry-airflow
This repository codifies the Airflow cluster that is deployed at workflow.telemetry.mozilla.org (behind SSO) and commonly referred to as "WTMO" or simply "Airflow". Some links relevant to users and developers of WTMO: * The `dags` directory in this repository contains some custom DAG definitions * Many of the DAGs registered with WTMO don't live in this repository, but are instead generated from ETL task definitions in bigquery-etl * The Data SRE team maintains a WTMO Developer Guide (behind SSO)

mojo
Mojo is a new programming language that bridges the gap between research and production by combining Python syntax and ecosystem with systems programming and metaprogramming features. Mojo is still young, but it is designed to become a superset of Python over time.

pandas-ai
PandasAI is a Python library that makes it easy to ask questions to your data in natural language. It helps you to explore, clean, and analyze your data using generative AI.

databend
Databend is an open-source cloud data warehouse that serves as a cost-effective alternative to Snowflake. With its focus on fast query execution and data ingestion, it's designed for complex analysis of the world's largest datasets.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.