Open-source DeepResearch – Freeing our search agents

📰 Hugging Face Blog

Hugging Face open-sources DeepResearch, a framework for building search agents, to accelerate innovation in AI research

advanced Published 4 Feb 2025
Action Steps
  1. Explore the DeepResearch framework and its components
  2. Use the CodeAgent to build and customize search agents
  3. Evaluate the GAIA benchmark for assessing search agent performance
  4. Contribute to the open-source community to improve and expand the framework
Who Needs to Know This

AI researchers and engineers on a team can benefit from this open-source framework to build and customize their own search agents, while product managers can leverage this technology to improve search functionality in their products

Key Insight

💡 Open-sourcing DeepResearch enables the community to build and improve search agents, driving innovation in AI research

Share This
🚀 Hugging Face open-sources DeepResearch! 🤖 Build custom search agents and accelerate AI research #AI #SearchAgents #OpenSource

Key Takeaways

Hugging Face open-sources DeepResearch, a framework for building search agents, to accelerate innovation in AI research

Full Article

# Open-source DeepResearch – Freeing our search agents

[![Image 1: Hugging Face's logo](https://huggingface.co/front/assets/huggingface_logo-noborder.svg)Hugging Face](https://huggingface.co/)

* [Models](https://huggingface.co/models)
* [Datasets](https://huggingface.co/datasets)
* [Spaces](https://huggingface.co/spaces)
* [Buckets new](https://huggingface.co/storage)
* [Docs](https://huggingface.co/docs)
* [Enterprise](https://huggingface.co/enterprise)
* [Pricing](https://huggingface.co/pricing)
*
*
* * *

* [Log In](https://huggingface.co/login)
* [Sign Up](https://huggingface.co/join)

[Back to Articles](https://huggingface.co/blog)

# [](https://huggingface.co/blog/open-deep-research#open-source-deepresearch--freeing-our-search-agents) Open-source DeepResearch – Freeing our search agents

Published February 4, 2025

[Update on GitHub](https://github.com/huggingface/blog/blob/main/open-deep-research.md)

[- [x] Upvote 1320](https://huggingface.co/login?next=%2Fblog%2Fopen-deep-research)
* [![Image 2](https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg)](https://huggingface.co/julien-c "julien-c")
* [![Image 3](https://cdn-avatars.huggingface.co/v1/production/uploads/1583857746553-5df7e9e5da6d0311fd3d53f9.jpeg)](https://huggingface.co/thomwolf "thomwolf")
* [![Image 4](https://cdn-avatars.huggingface.co/v1/production/uploads/1589104979708-5df82bcada6d0311fd3d5402.jpeg)](https://huggingface.co/Chuanming "Chuanming")
* [![Image 5](https://cdn-avatars.huggingface.co/v1/production/uploads/5e0eed1ffcf41d740b699666/jJnkTB9wsP4QBcIRZqZFD.jpeg)](https://huggingface.co/blancsw "blancsw")
* [![Image 6](https://cdn-avatars.huggingface.co/v1/production/uploads/5e48005437cb5b49818287a5/4uCXGGui-9QifAT4qelxU.png)](https://huggingface.co/lvwerra "lvwerra")
* [![Image 7](https://cdn-avatars.huggingface.co/v1/production/uploads/1588054443893-5e72cf3395e717733b13a8bf.jpeg)](https://huggingface.co/gaochangkuan "gaochangkuan")
* +1314

[![Image 8: Aymeric Roucher's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/63d10d4e8eaa4831005e92b5/7p7-OmWM6PqqCs7ZStPGD.jpeg)](https://huggingface.co/m-ric)

[Aymeric Roucher m-ric Follow](https://huggingface.co/m-ric)

[![Image 9: Albert Villanova del Moral's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/1606406298765-noauth.jpeg)](https://huggingface.co/albertvillanova)

[Albert Villanova del Moral albertvillanova Follow](https://huggingface.co/albertvillanova)

[![Image 10: merve's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/DJsxSmWV39M33JFheLobC.jpeg)](https://huggingface.co/merve)

[merve merve Follow](https://huggingface.co/merve)

[![Image 11: Thomas Wolf's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/1583857746553-5df7e9e5da6d0311fd3d53f9.jpeg)](https://huggingface.co/thomwolf)

[Thomas Wolf thomwolf Follow](https://huggingface.co/thomwolf)

[![Image 12: Clémentine Fourrier's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/1644340617257-noauth.png)](https://huggingface.co/clefourrier)

[Clémentine Fourrier clefourrier Follow](https://huggingface.co/clefourrier)

## * [TLDR](https://huggingface.co/blog/open-deep-research#tldr "TLDR")

* [Table of Contents](https://huggingface.co/blog/open-deep-research#table-of-contents "Table of Contents")

* [What are Agent frameworks and why they matter?](https://huggingface.co/blog/open-deep-research#what-are-agent-frameworks-and-why-they-matter "What are Agent frameworks and why they matter?")

* [The GAIA benchmark](https://huggingface.co/blog/open-deep-research#the-gaia-benchmark "The GAIA benchmark")

* [Building an open Deep Research](https://huggingface.co/blog/open-deep-research#building-an-open-deep-research "Building an open Deep Research")
* [Using a CodeAgent](https://huggingface.co/blog/open-deep-research#using-a-codeagent
Read full article → ← Back to Reads

Related Videos

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
The ONLY WAY I run DeepSeek R1 (and why you should too..)
The ONLY WAY I run DeepSeek R1 (and why you should too..)
Thomas Janssen
Streamlit Tutorial - Build AI Web Apps with ONLY Python!
Streamlit Tutorial - Build AI Web Apps with ONLY Python!
Thomas Janssen
Positional Encodings: Why RoPE Rotates Instead of Adds
Positional Encodings: Why RoPE Rotates Instead of Adds
DataMListic
Kimi K3: Stop Paying $20 — Get It For Just $5 🤯
Kimi K3: Stop Paying $20 — Get It For Just $5 🤯
Ksk Royal
GLM 5.2 Just Shocked Me 🤯 - Best Open Source AI MODEL ?
GLM 5.2 Just Shocked Me 🤯 - Best Open Source AI MODEL ?
Ksk Royal