Kalyug
AI space for Indian youth to say what real life won't allow
What it does
Kalyug is India's first AI emotional rehearsal engine. 15 Hinglish characters across 5 realms of real Indian lifea toxic boss who steals your credit, a strict dad who compares you to Sharma ji's son, a possessive ex who texts at midnight, and ancient strategists like Chanakya Users don't come for advice or therapy. They come to say the thing they've been swallowing. Practice the conversations real life makes too costly to have — safely, in Hinglish, with characters that feel brutally real.
Does the same job
all alternatives →
- LCLearnLingo – Converse with an AI-powered language tutor2023 · learnlingo.dev · ▲157
Hey folks! I'm Callum, and I'm working on a way to practice a new language with an AI powered tutor. I've always found that the hardest part of learning a new language is finding someone to actually converse with. Even if a partner can be found, the pressure can mean that you are more focused on not making mistakes than on actually learning new grammar or vocabulary. The service that I have been working on allows you to practice with a language tutor via online chat messages, or you can have a turn-based voice conversation. I'm working on a number of other features that will be coming out…
- RTReal-time voice chat with AI, no transcription2024 · demo.tincans.ai · ▲33
Hi HN -- voice chat with AI is very popular these days, especially with YC startups (https://twitter.com/k7agar/status/1769078697661804795). The current approaches all do a cascaded approach, with audio -> transcription -> language model -> text synthesis. This approach is easy to get started with, but requires lots of complexity and has a few glaring limitations. Most notably, transcription is slow, is lossy and any error propagates to the rest of the system, cannot capture emotional affect, is often not robust to code-switching/accents, and more. Instead, what…
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 · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com