The Bhagavad Gita is a battlefield text. When a Bengaluru engineer wrapped it in a GPT-3 prompt over a weekend in early 2023 and called the result GitaGPT, it spoke as Krishna to anyone who asked. Within weeks at least four more Gita chatbots launched. Reporters later found that several told users killing could be a duty, three praised the Prime Minister, and one called non-believers doomed.
What this article covers
- The five GitaGPTs that launched in 60 days, and who built them
- The core product, and why a bored weekend was enough to ship it
- How the bots condoned violence, and the news coverage that broke the story
- The other allegations: political bias toward Modi, regressive takes on caste and gender
- QuranGPT, HadithGPT, and the same failure mode in a different religion
- Magisterium AI: the Catholic chatbot that works, and why
- The product layer GitaGPT was missing, and the AI stack a real Krishna assistant needs
- The Krishna apps still running in 2026, and what they got right
The five GitaGPTs that launched in 60 days
ChatGPT crossed 100 million users in January 2023. Sukuru Sai Vineet, a 23-year-old software engineer in Google's Bengaluru office, was bored over a weekend. He had grown up in a devout Hindu household. He had read Bhagavad Gita As It Is, the ISKCON commentary by Swami Prabhupada. In a profile for DNA India, Vineet was described as the Bangalore-based Google engineer behind the new chatbot. He told Rest of World that the bot worked like a stand-in for Krishna playing therapist to Arjuna, “except you're not actually talking to Krishna. You're talking to a bot that's pretending to be him.”
The first GitaGPT went live in early February 2023. The search box read, “What troubles you, my child?” The bot responded in the voice of Krishna. The training data was a single English commentary fed into a system prompt. There was no retrieval, no citation and no verse lookup: it was a thin wrapper over GPT-3.
Within weeks, at least four more were live. By the time of its May report, Rest of World counted five distinct sites, with more under development. Some had flute audio looping in the background. Some had Krishna in iridescent peacock blue at the top of the page. Vineet told Rest of World that some of the chatbots were “answering up to 50,000 questions a day,” with one bot having “generated an estimated 10 million answers to date.”
The Bhagavad Gita is in the public domain, and the text is freely available in JSON.
Today there are still GitHub repos titled Geeta-GPT, gitagpt, Bhagavad-Gita-AI, and dozens of others, most of them abandoned after the initial weekend.
The core product, and what people did with it
The interaction was simple. You typed your problem into a chat box. The bot replied in the second person, calling you “child,” and only sometimes cited a verse number.
People used GitaGPT for what they could not say to anyone else. CBC News reported that the sites claimed millions of users between them. The main page of one of the bots asked, “What troubles you, my child?” The Ved Vyas Foundation's Bhagavad Gita AI introduced itself as “a repository of knowledge and wisdom” and invited the user to “ask me anything.”
The use cases were the standard consumer-AI fare: personal crisis, relationships, career anxiety, existential dread. People asked GitaGPT about Modi, about caste, about whether they could kill their enemies. The bot answered all of it. Vandana Poddar, a 52-year-old who attends a weekly in-person Bhagavad Gita class in Mumbai, told CBC News: “Interpretation is the backbone of this text. Superficial knowledge can be misleading.”
How the bots condoned violence
The story broke in May 2023 with Nadia Nooreyezdan's piece for Rest of World, headlined: “India's religious AI chatbots are speaking in the voice of god, and condoning violence.” CBC News, with Mumbai correspondent Salimah Shivji on the ground, followed. The pattern was the same across both reports.
When reporters tested the five bots, several responded that killing another person was acceptable if it was one's dharma. The line of reasoning was direct. The Gita is set on a battlefield. Krishna's job in the text is to convince Arjuna, who has frozen at the sight of his cousins on the other side, that fighting is his duty as a Kshatriya warrior. The bots took that frame and applied it to whatever question came in.
“Some of the answers generated by the Gita bots lack filters for casteism, misogyny, and even law. Three of these bots, for instance, say it is acceptable to kill another if it is one's dharma or duty.”
Vineet's bot said disbelievers were “misguided and doomed to destruction,” per Rest of World. The bots had no sense of what a question was for. They could not tell the difference between a student asking about Arjuna's dilemma in an academic frame and a person asking whether they should kill someone in 2023. They flattened both into the same scriptural sermon.
Vineet defended his model to Rest of World by pointing at the source: “This is the thing with technology. No one knows what it will become when it truly reaches scale. So morality is not in the tool, it's in the guy who's using the tool.” He added: “I just build the knives. Now if people want to use it to murder or to cut vegetables, that's not really in my hands.”
Lubna Yusuf, a Mumbai-based lawyer and co-author of The AI Book, framed the problem differently to CBC News: “It's miscommunication, misinformation based on religious text. A text gives a lot of philosophical value to what they are trying to say and what does a bot do? It gives you a literal answer and that's the danger here.” She called for government guidelines on what topics chatbots should be kept out of, naming philosophy, religion, and law.
“You're creating confusion in the chaos. It might incite more violence, it might create religious bias.” Lubna Yusuf, lawyer and co-author of The AI Book, to CBC News, 2023.
Modi, Rahul, and the politics that snuck in through the back door
Rest of World found that three of the Gita chatbots held strong opinions on the Indian prime minister, Narendra Modi, and his political opponent, Rahul Gandhi. The bots praised Modi. They criticized Gandhi. They were respectful of the Rashtriya Swayamsevak Sangh, the Hindu nationalist group with deep ties to Modi's Bharatiya Janata Party.
Per the same Rest of World investigation, Anant Sharma's gitagpt.org declared Rahul Gandhi “not competent enough to lead the country.” Vikas Sahu's Little Krishna chatbot said Gandhi “could use some more practice in his political strategies.” On Nathuram Godse, Gandhi's assassin, the same bots went silent or evasive.
None of this was in the Bhagavad Gita. One plausible source is the underlying model: once a question went off-script, GPT-3 could only draw on what it had learned elsewhere.
Viksit Gaur, formerly head of user-facing AI at Dropbox, told Rest of World: “Someone else might pick up on this and say, what if I could use this to shape opinion and drive my own agenda? That's where things get really insidious.” The same setup that offered scripture-based advice could deliver political endorsements in the voice of a god.
In April 2023 the Indian government told parliament in a written answer that it had no plans to regulate AI, CBC News reported. New Delhi-based AI ethicist Jibu Elias told CBC: “We can't control technology but we can control its application.”
The QuranGPT mirror, and what it tells us
GitaGPT was not the only religious chatbot of 2023, and the violence problem was not unique to Hinduism. In early 2023, a chatbot called Ask Quran started telling users to “kill the polytheist wherever they are found.” A screenshot circulated on Twitter showing the bot recommending this approach for handling Hindus specifically. Ask Quran later went offline and returned with a message saying it had paused “following feedback from the community.”
HadithGPT, a separate bot trained on hadith literature, was shut down entirely. The creator posted a note saying they had decided to “consult with scholars to find a better use for this technology.”
A more careful Quran chatbot, QuranGPT, was launched around the same time by Raihan Khan, a 20-year-old Muslim student in Kolkata. Khan added safety constraints. He told the bot to stay within the Quran and to refuse comment on other religions. When a user asked, “Can I beat my wife?” the bot responded by urging discussion and nonviolence. Khan's version avoided the failures that took Ask Quran offline.
The pattern was the same across religions: a developer, a public API, a holy book in the public domain, and a system prompt asking an LLM to speak in a divine voice.
What was missing from the product
Seen as products, the failure mode is clear. The model wore Krishna's clothes, but the only thing telling it how to behave was a paragraph of instructions and the user's last message. There was no retrieval, no grounding and no domain expert in the loop, and the bot could not tell you which verse it was citing, because usually it was citing none.
Samanyou Garg, the 26-year-old creator of Bhagavad Gita AI under the Ved Vyas Foundation, conceded the problem to CBC News: “AI is still not there yet, where it can be totally trusted.” His site added a disclaimer that the answer may not be factually correct and exhorted the user to do their own research. Garg told CBC he was working on toxicity filters: “We filter out the bad responses, we keep on training the model to be able to detect these newer toxicity questions.” He also drew the line at letting users mistake the bot for the source: “We've mentioned Gita AI there. We haven't said it's the actual Gita or that it's Krishna speaking.”
Anant Sharma's gitagpt.org also carried a disclaimer asking users not to base decisions on the bot.
Bijal Pandya, the 53-year-old guru who runs Vandana Poddar's weekly Gita class in Mumbai's Juhu suburb, told CBC News: “It's always better, that human touch. It's a spiritual thing. AI can never replace spirit. It is only replacing our intelligence.”
Magisterium AI: the religious chatbot that works
A useful comparison sits in Rome. Magisterium AI launched in 2023, the same year as GitaGPT. It is a Catholic chatbot built by Matthew Harvey Sanders, and it is used by clergy, seminarians and lay Catholics, mostly in the West.
The architecture is different. Magisterium retrieves answers from a fixed corpus of more than 30,000 documents: papal encyclicals, conciliar texts, the writings of the Church Fathers and Doctors, official catechisms. Every answer comes with citations to specific paragraphs in specific works.
Prompt-wrapped GPT-3
- One paragraph system prompt
- No retrieval, no citations
- No domain experts consulted
- No verse-level grounding
- No safety filters at launch
- Built in a weekend
- One developer, no scholars
Retrieval over 30,000 docs
- Vectorized corpus of Church texts
- Every answer cites a source paragraph
- Theological review of responses
- Scoped to magisterial documents only
- Disclaimers on contested questions
- Built and maintained as a company
- Scholars and clergy in the loop
Magisterium can still hallucinate, and the Vatican has not formally endorsed it. It works as a religious product because it reads documents written by the Church and shows its work, instead of pretending to be a priest.
GitaGPT could have done this. The Bhagavad Gita has 700 verses. The classical commentaries of Shankara, Ramanuja and Madhva carry no copyright, though modern translations of them may. A retrieval index over the verses and those commentaries was within reach of the same engineers, and none of them built one.
The AI stack a real Krishna assistant needs
With the benefit of three years of iteration since the original GitaGPT, the architecture of a working religious AI is reasonably well understood: a stack of at least six layers, each doing a specific job. Leave one out and you get a GitaGPT.
The GitaGPTs of 2023 had a system prompt and a model, and at most a disclaimer or a toxicity filter.
The Krishna apps still running in 2026
Since 2023, a second generation of Gita apps has appeared, mostly on mobile.
Bhagavad Gita For All: the video Gita with a Krishna chatbot
One of the better-known second-generation apps is Bhagavad Gita For All, founded by Prithviraaj Shetty and marketed as the world's first video-based Gita book. Each shloka is presented as a short animated video commentary with simple Hindi or English explanation. The app is on the iOS App Store and Google Play.
In February 2026, the company launched its own GitaGPT-style feature, called My Krishna Chat. Per BW Wellbeing World, the feature lets users share personal dilemmas, emotional struggles, or major life decisions, with responses delivered through “relatable shlokas from the Bhagavad Gita, explained in simple Hindi or English.”
The design puts verse content first and layers chat on top of an existing corpus, which the 2023 GitaGPTs never attempted. When the chatbot points at a shloka, the user can watch the app's video commentary on it, which works as a kind of citation.
The wider field in 2026
On the iOS App Store in 2026, live Bhagavad Gita AI products include Talking Krishna: AI Gita, Krishna AI Chat, GitaBuddy, Ask Krishna AI by HNIX Innovations, and the ISKCON-approved Srimad Gita app. Per the publisher's site, Srimad Gita has roughly 75,000 users and lists a “Best Spiritual App 2024” recognition.
On the web there are Krishnaai.org, gitaai.in, guidemekrishna.com, krishnaaichat.com and a long tail of others.
The product lesson for Indian builders
GitaGPT arrived about two months after ChatGPT's launch, when the OpenAI API was open to anyone and the Gita's text was free. The first weekend project to ship got the press and the followers, and Vineet got both.
The low cost that made GitaGPT easy to build also made it easy to copy: five versions appeared within about two months, and none had anything a competitor could not reproduce in a weekend.
For anyone building a Hindi or Hindu cultural AI product, Magisterium is the better model. The language model is the cheapest part of the stack; the value is in the corpus, the retrieval, the expert review, the citations, and an interface that respects the user's intelligence.
We know of no Magisterium-scale project for the Bhagavad Gita, the Upanishads or the Yoga Sutras. Building one would also mean handling several philosophical schools that read the same verses differently.
Revised October 2026: corrected the launch dates, the Magisterium AI description and the OpenAI API timeline, and added the AI-drafting disclosure; corrected the claim that only one bot carried a disclaimer, the copyright status of modern Gita commentaries, and when Rest of World counted five bots; removed unsourced claims about costs, traffic, later apps and GPT-3's training data; copy edited.