Deep Research – Open-Source Customizable Reasoning Framework for Devs
The first ever AI peer reviewed research article just got approved. It’s kinda crazy how advanced AI have come to replace researchers. I've just been using Deep Research on ChatGPT and Perplexity a lot to write and research complex technical reports for my boss. He loves the reports and it has decreased my workload a ton but I still have some frustrations with it. None of them provide an API that gets me the same quality of output you would with the applications. I wanted something with more control on the LLMs, swappable with the reasoning new models that came out. Not just prompt →…
What it does
In the maker’s words, at launch
The first ever AI peer reviewed research article just got approved. It’s kinda crazy how advanced AI have come to replace researchers. I've just been using Deep Research on ChatGPT and Perplexity a lot to write and research complex technical reports for my boss. He loves the reports and it has decreased my workload a ton but I still have some frustrations with it. None of them provide an API that gets me the same quality of output you would with the applications. I wanted something with more control on the LLMs, swappable with the reasoning new models that came out. Not just prompt → response; I wanted to shape the way the reasoning happened. How prompting was made, the design of the process, how many layers of thinking the models should go through, and what information the LLM should be extracting from the internet. Essentially I wanted the following things: • Choose which LLM models were used and how they were combined • Adjust how deep or broad the exploration went • Specify the report format: token count, structure, even tone • Expose verified sources that were used throughout the process But most of the deep research tools I’ve used don't allow that or has some weird edge case. They are mostly closed system/sources or commercial API’s for end-users - NOT developers. So I built Deep Research - a fully customizable open source deep research framework. It’s designed for devs who want full control over the research process, without building everything from scratch. It supports: • Multi-model orchestration — Plug in your own LLMs or use the defaults (GPT-4.1 is baked in) • Custom depth and breadth — Tune the research from shallow summaries to multi-layered deep dives • Token-level control — Define how long the output should be • Transparent citations — Everything is traceable back to its source • Built-in web search — Integrates JigsawStack’s web search to combine retrieval with reasoning It runs on top of Vercel’s AI SDK making it easily configurable! Here’s a full blog breakdown: https://jigsawstack.com/blog/introducing-jigsawstack-deep-re... Try it out. Would love to hear feedback from fellow hackers! What’s good, what’s bad, what’s ALARMING.
Does the same job
all alternatives →
- AVA visual, knowledge map based interface for deep research/deep dives2025 · proread.ai · ▲8
I found myself jumping between ChatGPT, tabs, and docs, but never building real understanding. This is my attempt at fixing that — for researchers, curious readers, and lifelong learners. Would love your thoughts on the interface, and whether this would be useful in your own work or otherwise.
- WBWe built a powerful and free AI research assistant2024 · join.modularmind.app · ▲7
Hi everyone, We have been developing a platform to enable professionals to build AI assistants to help them through their work. After a few months, we realized people are trying to sell basic functionalities that can be built from scratch in a couple of hours. Due to this, individuals who are not familiar with the current SOTA are misinformed about the potential of generative models. So, we decided to open up some of our most popular templates as standalone tools for free to empower individuals and set a solid standard for what people should expect. We believe the barrier to accessing…
- DODataHub, open source datasets for Artificial Intelligence2017 · ▲14
Hi HN! I am an undergrad student trying to build interesting things with AI. Recently, I was looking for a dataset I could use for a new project. I realized that it is really frustrating to go through all the government websites (with terrible UX) just to find some usable dataset. I set out to build a GitHub for datasets, named DataHub. Right now, we have more than 1000 datasets from Montréal and New York City, with more cities coming soon (and possible government agencies). All of this is wrapped into a powerful search. It's a breeze to find a dataset to work on. I'd be interested to know…
- WOWorking on open-source perplexity AI2024 · omniplex.vercel.app · ▲5
Hey guys, I am think of building an open-source version of Perplexity to let devs play around with it. But with all the existing tools available what features would you want? Anything specific? What is missing? Currently working on - 1. Streaming text 2. Citations sources 3. Image and file upload 4. Chat history and storage 5. Temperature and custom instructions If you are in marketing or growth can anyone help me with what to focus on while building such an app? Also here is a very first version. Probably will break and most of the buttons also don’t work, built it in 3 days using Bing and…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, June 2025
the whole month →- IM
Hey HN! Pilots everywhere are required to keep a logbook of all their flying hours, aircraft, airports, and so on. Since I track everything digitally (some people still just use paper logbooks!), I put together some data visualizations and a few 3D globes to show my flying history. This globe is probably my favourite so far: https://jameshard.ing/pilot/globes/all If you’ve got ideas for other graphs or ways to show this kind of data, I’d love to hear them!
Life & fun · 2025 · jameshard.ing
Stunning presentations with AI. No design skills required.
AI · 2025 · chroniclehq.com
Build native mobile apps for iOS and Android without code.
Dev tools · 2025 · bble.io
All your connections, across all your socials.
AI · 2025 · pally.com
- WC
I was the main contributor to workout.lol, an open-source fitness app to easily build a workout routine. The project had traction (1.4k GitHub stars, 95 forks, ~20K visits/month), but was eventually sold due to video licensing hurdles. The new owner stopped maintaining it, and the repo went abandoned. Over the next 9 months, I sent 15 emails to try to save it : no replies. Feature requests & issues were ignored. The community was left with a "broken" tool let's say. I couldn't just let it die So I built the new version from scratch with the same open-source spirit, but a better…
Dev tools · 2025 · github.com