I do research in AI safety for healthcare and life sciences. And while I was using Claude Code to reason on a couple of things, I realised a pattern. Claude or any other AI agent is very linear.
Theres a strong reason why - the thinking pattern of almost all LLMs from 2024 follow Chain-of-thoughts where AI is programmed to go deep unilaterally.
But researchers or creativity-intensive works do not need to go unilateral but do divergent.
That's the whole base of my paper - ADHD - Parallel Divergent Ideation for Coding Agents.
My thesis is that if we disregard the default chain-of-thoughts and consider a tree-of-thoughts, then we can empanel divergent thinking in our models. thus, giving us the much needed scope of connecting dots from different thinking points.
Its a lot inspired by how the mind of someone with ADHD works- think in a lot of directions and go deep in a few, and there, we add our our critic layer, that judged and scores all this thinking.
Limitation : It shoots cost by ~5x and time to output by ~10x but enables instant novel thinking. Good for brainstorming and planning, not for coding.
Give me your feedback, I am happy to learn how you find it and what's the scope to improve.
Also, its completely opensource so you can just clone it or contribute to it.
Most documentation on the web is written for humans. HTML pages, navigation, prose, repetition. Interface artifacts.
AI agents don’t need any of that.
When agents “learn from docs”, they’re reasoning over a rendering format, not the underlying technical truth. That’s why context breaks and hallucinations show up. Not a model problem. A substrate problem.
At Brane, we’ve been working on agent memory and coordination. One conclusion kept repeating. The real bottleneck isn’t intelligence. It’s context and memory infrastructure.
So we built Moltext.
Moltext is a documentation compiler for agentic systems. It doesn’t chat with docs or summarize them. It compiles the legacy web into deterministic, agent-native context that agents can reason over directly.
Infrastructure stays dumb. Models do the thinking.
Ig it's a good fit for SuperDocs.cloud. Maybe we can partner to give all of the products launched here.. their own proper managed product documentations.
a. You don't need to let any LLM index your code.
b. I am focused more on the consumer facing product side.. Yes, right now it scans codes but my goal is to soon use computer use to work on the interface-side user flow (like onboarding, etc.). Maybe, create an agent for your customers to never get stuck coz of UX again.
c. I made it public, you can check out docs, demos, etc.. Maybe I will also just open source this version once I am done with the CUA stuff..
Bonus stuff- I just built a CLI version so no interface needed at all, just 2 terminal command and get your docs ready.
I lowkey agree to this. But this is like a starter kit for people who are just mindlessly building and exhausting their credits on apps like Cursor or Replit.
Plus, having a dedicated stack that is you can functionally depend on, will help you scale much easily and accumulate very less technical debt overhead.
If you build an app mindlessly with Replit, chances there, you have a mock or hardcoded DB or auth and when you ship the v2, all data will vanish..
So, it's less of a good thing and more of a bad thing for people starting out.
But yes, you are truly right that this is also very inconsistent to rely on credits. I appreciate you raising this up!
True somehow but this is the typical Silicon Valley style where most of the stuff is so democratised that for people to start off, it has become a big fallback.
Like if you are a student or planning to switch career, then take what's free.. build and learn and ship!!!
So much true.
I have been a developer in past so I understand my bias towards convectional frameworks. For me, the biggest dealbreaker for Replit was the scale cost.
I the technical debt that I was incurring per project. It is still my go-to option for prototyping and quick tests but this was just the regular stack I am using to ship stuffs.
Also, yes, there a a lot of alternatives (great ones) that I missed and understand that the list is not complete.
Would love to know what stacks you use so I can also try them out.
Access here -
- AI SDK - Antigravity- https://antigravity.google/
- AI Documentation - SuperDocs - https://superdocs.cloud/
- Database - Supabase - https://supabase.com
- Auth - StackAuth - https://stack-auth.com
- LLM/AI Model - Gemini by AI Studio (aistudio.google.com) or Self-trained Unsloth Model (https://unsloth.ai) or Openrouter for testing (openrouter.ai)
- Deployment - Vercel (Vercel.com) or CloudFare Pages.
- Analytics - PostHog (posthog.com) or Microsoft Clarity
Really cool project! AI is definitely reducing the friction of outbound sales. In parallel, I'm working on solving the other side of the funnel: what happens when someone lands on your site and wants to learn more. We've built Exthalpy (https://exthalpy.com/early), an AI powered sales agent that lives on your website. It engages visitors 24/7, qualifies leads, schedules demos right on your calendar and supports over 30 languages. Instead of acting like a generic chatbot, it's designed to handle end‑to‑end conversations and integrates directly with your sales stack. Would love to hear about your experience building this and see how you handle personalization — maybe we can swap notes!
I do research in AI safety for healthcare and life sciences. And while I was using Claude Code to reason on a couple of things, I realised a pattern. Claude or any other AI agent is very linear.
Theres a strong reason why - the thinking pattern of almost all LLMs from 2024 follow Chain-of-thoughts where AI is programmed to go deep unilaterally.
But researchers or creativity-intensive works do not need to go unilateral but do divergent.
That's the whole base of my paper - ADHD - Parallel Divergent Ideation for Coding Agents.
My thesis is that if we disregard the default chain-of-thoughts and consider a tree-of-thoughts, then we can empanel divergent thinking in our models. thus, giving us the much needed scope of connecting dots from different thinking points.
Its a lot inspired by how the mind of someone with ADHD works- think in a lot of directions and go deep in a few, and there, we add our our critic layer, that judged and scores all this thinking.
Limitation : It shoots cost by ~5x and time to output by ~10x but enables instant novel thinking. Good for brainstorming and planning, not for coding.
Give me your feedback, I am happy to learn how you find it and what's the scope to improve.
Also, its completely opensource so you can just clone it or contribute to it.
Update : the oss repo hit 200+ stars.