I like the attempt but mythology is significantly more layered that just the study of their characters at the end. A single perspective of these stories will help you get the lay of the land but you need to be very cautious if you want to use this to draw lessons and conclusions from them. For example, the protagonist and antagonist are different from the perspective of the other characters. Both these epics are all about the nuance and that needs to be captured effectively to do justice to them
Good point. One way to handle this might be to show the same event from multiple character perspectives - like how Karna's story looks completely different depending on whether you enter it from Kunti's node vs Duryodhana's. The graph structure actually lends itself well to this since you could attach different narrative framings to each edge.
1. Is this actually based on any textual analysis or just AI generated? The popular understanding of the epic material is rather poor and the AI is stupid on it.
Eg: Indra would have a much larger role in original versions of mahābhārata and rāmāyana compared to Hindu popular conscience. In Ramayana he defeated kabandha, lent weapons to Rāma, and the hero is frequently compared to him as "Indra among men" - making him technically the most mentioned God in Valmiki's text (https://manasataramgini.wordpress.com/2017/02/12/the-ramaya%...).
In Mahabharata he fights equally with the krishna-arjuna in the burning of khandava episode until a truce is reached (and for reasons beyond the present redactions of the epic and owing to his prominence as ārya national god, the new capital of pāndavas is named.... Indraprastha!).
This kind of stuff is virtually unknown to AI, which reinforces the present pop understanding of the epics, which is to say super shallow and not very interesting.
Feels like you created an Obsidian of the entire Mahābhārata and Rāmāyaṇa... I love the Crimson Dusk theme. I think, for the relationship graph, when the clusters get too overloaded in some places, they should separate out even when I zoom in. When I zoom in, they're still too close to each other which makes it hard to read the bottom right section of Mahabharata.
I’m finding that character dictionaries like this are useful to people who want to engage with ancient texts but are not very familiar with them, but even if one is familiar, they are still quite helpful.
This is a genuinely delightful project. The graph-based approach to navigating the Mahābhārata and Rāmāyaṇa feels really natural — these epics are fundamentally about relationships and webs of consequence, so exploring them through a character graph rather than linear text makes a lot of sense.
The Crimson Dusk theme is a nice touch too. Looking forward to seeing how the data coverage grows over time!
You're Absolutely Right! Your original summary is not just insightful — you've cleanly delved into the best parts! What else can you share with us tonight?
Good attempt. What were the sources for these graphs? Orginals? Valmiki Ramayanam and Vyasa Mahabharata? Looking at Mahabharata's relationship graph on the website - it feels like it is incomplete. There are probably ~400 to 500 active named characters in Mahabharata (among several thousands of named characters overall)
Right now the data isn’t directly modeled from primary sources like the Valmiki Ramayana or the Mahabharata. It’s an MVP built quickly using curated summaries, so the graph is definitely incomplete.
Planning to expand coverage and move towards a more accurate, source-grounded knowledge graph over time.
And where did the stats come from? I find it very amusing & interesting & informative. I'm assuming you had the LLM generate these? That would be so interesting to see the prompts for!!
Good vis. I wasn't sure what to expect, tbh.
A few notes:
- The default vis has very low contrast (despite changing theme colors).. perhaps make the contrast stronger. I find this is the case with most AI-driven websites :-/ Same for some of the standard text ("family lineage", "group connections, etc)
- Pls cite the sources. That would be useful / important
- The dynasty tree looks useful... But is it incomplete? Or is only the visualization capped at some limit?
- Wasn't sure what the "Sections" dropdown on the left does
The challenge for sure is about the sheer number of characters, the number of years/decades in these epics, the complexity.
Would love to see some references, perhaps with quotes in Sankskrit / transliterated to English, at key points. [yes, this is challenging, no doubt]
I like the approach, however, could tell this is done by AI, someone that studied it at the periphery. The characters, if you are automating the creation, should be a lot more in depth, at least that’s what I would expect.
What an incredibly diverse and inclusive UI design. I often find that Indian mythologies tend to be overshadowed, but with the advent of AI generated art and media there's been a resurgence of Indian-centric stories.
The internet being flooded with AI slop masquerading as devotional artwork has been among the most depressing things about GenAI. It has no meaning or intention or devotion behind it, it’s just engagement farming. Nothing of value is added by having Devi with extra fingers on each hand and completely blurred messes for all the affects in her hands. Or pictures of Rama shooting a bansuri out of his bow. It’s just tripe. We could have told the stories with an overlay of open source artwork from Raja Ravi Varma or Gita Press or old Tanjore paintings or Chola bronzes or whatever if we couldn’t afford to hire an artist who knows what items Vishnu is supposed to be holding in each hand.
It’s not a problem just for us Hindus either. I see so much terrible Jesus/angel “artwork” everywhere. It makes me start to wonder if maybe the Wahabbis were onto something with their complete taboo around depictions of God or the prophets.
>Nothing of value is added by having Devi with extra fingers on each hand and completely blurred messes for all the affects in her hands
South Asian religions are in an especially bad position because so many works related to them have never been digitized (and quite frankly, in some cases what's available on the internet is of extremely low quality) [1]. I'd be pretty concerned if someone were to rely on entirely on these models since the probability of hallucinations (or at the very least, erasure of regional/ideological diversity) probably skyrockets because the information was never actually there in the training data to begin with.
Some references have been digitized but “Hinduism” is a broad collection of religious traditions with many different stories and folk practices and depictions of various deities and tales. Many of the depictions are considered “valid” only in the specific context of a particular temple or for a specific community and it becomes completely nonsensical once you start randomly jumbling up elements of all the Gods from across all of India over all of time.
In the Mahābhārata, what's going on with the dynasty tree of the Kurus?
That's a view you get in every single book, and it looks really weird here. I feel like it's important to get this really basic stuff right before doing the cool-looking graph visuals.
Absolutely slick UI and wonderful implementation. As an ardent follower of Santana Dharma I admire OP’s courage and grit to put this piece of work out there. More power to OP and hoping to see more Epics included. Thanks for making and sharing this.
Really cool stuff, but I really don't understand the dynasties viz. For example, Kunti somehow has her sons to the left of, right of, and above her, making the relationship unclear.
I think the real problem isn’t just accessing data, but how fragmented the workflow is. Even with good tools, you still end up context-switching constantly.
it's a novelty to see the connections. One way it will be useful is to connect every character to the stories they're part of - either in the site, or in new tab. this will allow exploring the stories for each one of them. This will make people come to this for more than novelty, imo.
- but there is one point you have not accounted for
- what actually happened may not be what was written
- what was written 5000 yrs ago may not be what you are reading now. lots of people may have created their own versions or modified the original in ways you did not foresee
- the author who originally wrote the books may also have exaggerated for storytelling effect
- the probability of all of the above mathematically speaking is non zero
>- what was written 5000 yrs ago may not be what you are reading now. lots of people may have created their own versions or modified the original in ways you did not foresee
india vedic texts are passed through "oral tradition" where you recite same text backward and forward and through patterned permutations of words, if there is error it shows up, it's like redundant error-correcting encoding / repetition validation
45 comments
Eg: Indra would have a much larger role in original versions of mahābhārata and rāmāyana compared to Hindu popular conscience. In Ramayana he defeated kabandha, lent weapons to Rāma, and the hero is frequently compared to him as "Indra among men" - making him technically the most mentioned God in Valmiki's text (https://manasataramgini.wordpress.com/2017/02/12/the-ramaya%...).
In Mahabharata he fights equally with the krishna-arjuna in the burning of khandava episode until a truce is reached (and for reasons beyond the present redactions of the epic and owing to his prominence as ārya national god, the new capital of pāndavas is named.... Indraprastha!).
This kind of stuff is virtually unknown to AI, which reinforces the present pop understanding of the epics, which is to say super shallow and not very interesting.
I’ve been working on a similar project for biblical texts. For example, here’s a character detail page for David: https://hypr.bible/en/entities/person/david/
I’m finding that character dictionaries like this are useful to people who want to engage with ancient texts but are not very familiar with them, but even if one is familiar, they are still quite helpful.
The Crimson Dusk theme is a nice touch too. Looking forward to seeing how the data coverage grows over time!
Right now the data isn’t directly modeled from primary sources like the Valmiki Ramayana or the Mahabharata. It’s an MVP built quickly using curated summaries, so the graph is definitely incomplete.
Planning to expand coverage and move towards a more accurate, source-grounded knowledge graph over time.
E.g. Laxman Rekha incident is not present in Valmiki Ramayana but is present in societal consciousness.
- The default vis has very low contrast (despite changing theme colors).. perhaps make the contrast stronger. I find this is the case with most AI-driven websites :-/ Same for some of the standard text ("family lineage", "group connections, etc)
- Pls cite the sources. That would be useful / important
- The dynasty tree looks useful... But is it incomplete? Or is only the visualization capped at some limit?
- Wasn't sure what the "Sections" dropdown on the left does
The challenge for sure is about the sheer number of characters, the number of years/decades in these epics, the complexity.
Would love to see some references, perhaps with quotes in Sankskrit / transliterated to English, at key points. [yes, this is challenging, no doubt]
Hope this is useful
Keep up the good work!
It’s not a problem just for us Hindus either. I see so much terrible Jesus/angel “artwork” everywhere. It makes me start to wonder if maybe the Wahabbis were onto something with their complete taboo around depictions of God or the prophets.
>Nothing of value is added by having Devi with extra fingers on each hand and completely blurred messes for all the affects in her hands
South Asian religions are in an especially bad position because so many works related to them have never been digitized (and quite frankly, in some cases what's available on the internet is of extremely low quality) [1]. I'd be pretty concerned if someone were to rely on entirely on these models since the probability of hallucinations (or at the very least, erasure of regional/ideological diversity) probably skyrockets because the information was never actually there in the training data to begin with.
[1] I was able to find a few works of Newari Buddhist iconography recently, so it might be changing: https://web.archive.org/web/20240901130203/https://download..... It still has a few mistakes and doesn't compare to what's out there, though.
That's a view you get in every single book, and it looks really weird here. I feel like it's important to get this really basic stuff right before doing the cool-looking graph visuals.
This with Amar Chitra Katha would be great.
- what actually happened may not be what was written
- what was written 5000 yrs ago may not be what you are reading now. lots of people may have created their own versions or modified the original in ways you did not foresee
- the author who originally wrote the books may also have exaggerated for storytelling effect
- the probability of all of the above mathematically speaking is non zero
>- what was written 5000 yrs ago may not be what you are reading now. lots of people may have created their own versions or modified the original in ways you did not foresee
india vedic texts are passed through "oral tradition" where you recite same text backward and forward and through patterned permutations of words, if there is error it shows up, it's like redundant error-correcting encoding / repetition validation
> Draupadi-- strength 6, wisdom 8
Are you creating RPG characters?
Its clear you used AI to create the whole thing, but did you stop to think if it makes sense?