HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
dzhng
deep-research
TypeScript2025–2025
dzhng / deep-research

deep-research

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

4Distinct people
4Mentions
0Explicit recommenders
19.9KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 7:27:27 AM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day4 dated mentions

Observed mentions: 2025-02-07 16:51:40 UTC to 2025-02-26 12:17:23 UTC.

012025-02-07 00:00:00 UTC to 2025-02-08 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsFeb 72025-02-08 00:00:00 UTC to 2025-02-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-09 00:00:00 UTC to 2025-02-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-10 00:00:00 UTC to 2025-02-11 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2025-02-11 00:00:00 UTC to 2025-02-12 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-12 00:00:00 UTC to 2025-02-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-13 00:00:00 UTC to 2025-02-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-14 00:00:00 UTC to 2025-02-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-15 00:00:00 UTC to 2025-02-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-16 00:00:00 UTC to 2025-02-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsFeb 162025-02-17 00:00:00 UTC to 2025-02-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-18 00:00:00 UTC to 2025-02-19 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-19 00:00:00 UTC to 2025-02-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-20 00:00:00 UTC to 2025-02-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-21 00:00:00 UTC to 2025-02-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-22 00:00:00 UTC to 2025-02-23 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2025-02-23 00:00:00 UTC to 2025-02-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-24 00:00:00 UTC to 2025-02-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-25 00:00:00 UTC to 2025-02-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-02-26 00:00:00 UTC to 2025-02-27 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsFeb 26

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Feb 72025-02-07 00:00:00 UTC2025-02-08 00:00:00 UTC110
Feb 82025-02-08 00:00:00 UTC2025-02-09 00:00:00 UTC000
Feb 92025-02-09 00:00:00 UTC2025-02-10 00:00:00 UTC000
Feb 102025-02-10 00:00:00 UTC2025-02-11 00:00:00 UTC110
Feb 112025-02-11 00:00:00 UTC2025-02-12 00:00:00 UTC000
Feb 122025-02-12 00:00:00 UTC2025-02-13 00:00:00 UTC000
Feb 132025-02-13 00:00:00 UTC2025-02-14 00:00:00 UTC000
Feb 142025-02-14 00:00:00 UTC2025-02-15 00:00:00 UTC000
Feb 152025-02-15 00:00:00 UTC2025-02-16 00:00:00 UTC000
Feb 162025-02-16 00:00:00 UTC2025-02-17 00:00:00 UTC000
Feb 172025-02-17 00:00:00 UTC2025-02-18 00:00:00 UTC000
Feb 182025-02-18 00:00:00 UTC2025-02-19 00:00:00 UTC000
Feb 192025-02-19 00:00:00 UTC2025-02-20 00:00:00 UTC000
Feb 202025-02-20 00:00:00 UTC2025-02-21 00:00:00 UTC000
Feb 212025-02-21 00:00:00 UTC2025-02-22 00:00:00 UTC000
Feb 222025-02-22 00:00:00 UTC2025-02-23 00:00:00 UTC110
Feb 232025-02-23 00:00:00 UTC2025-02-24 00:00:00 UTC000
Feb 242025-02-24 00:00:00 UTC2025-02-25 00:00:00 UTC000
Feb 252025-02-25 00:00:00 UTC2025-02-26 00:00:00 UTC000
Feb 262025-02-26 00:00:00 UTC2025-02-27 00:00:00 UTC101

What Hacker News says

1 sources
As of now—literally today they announced—OpenAI gives 10 queries of Deep Research per month for Plus users. I wanted to create an alternative, so I took inspiration from this repository https://github.com/dzhng/deep-research but didn’t want to pay for the Firecrawl API too. Instead, I used algorithm from that repository. Here’s the result: https://github.com/jolovicdev/shandu. It’s still rough around the edges—things like proxy support for rate limits aren’t fully implemented yet—but it’s functional! You can try it out with a model you’re running in LM Studio. I’m not entirely sure if this is the best way to build something like this (arch wise, especially since I haven’t worked with LangChain or LangGraph), but here it is - built with a little help from Grok and DeepSeek! Compared to dzhng/deep-research, which relies on the Firecrawl API
Read the rest
(and its costs), Shandu skips that entirely and uses the same core algorithm in a simpler, free setup (integrated scraper). It’s less polished and missing some features (like proper rate limit handling), but it’s a lightweight option you can run locally without subscriptions. I’d love for you to check it out, maybe give it a star if you like it, or drop some feedback if you’ve got suggestions, because there are probably some community tools that I could have used, or some other direction generally. I think it’s a solid starting point.
In Open Source DeepResearch

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.