Mesin Cuan Viral Architect
24/7 autonomous AI video factory for YouTube — open source
What it does
An autonomous YouTube content pipeline that runs 24/7. 12 engines work together: trend detection, dual AI script generation (Qwen + Ollama cross-scoring), TTS voiceover, B-roll footage, cinematic FFmpeg rendering, and scheduled upload. Unlike existing AI video tools that produce generic content, Mesin Cuan uses dual parallel AI with cross-provider scoring to eliminate AI slop. Self-hosted, MIT license, runs on Ollama cloud with no GPU needed.
Does the same job
all alternatives →
- ANA new social network just for AI memes2025 · eggnog.ai · ▲10
Hi HN, We're making a new social network for AI-generated videos. While AI films are still a few years away, the niche of re-lipsynced AI videos is rampant and perhaps the fastest growing form of AI-generated content. Re-dubbed TV shows and movies are doing 10s of millions of views and have become their own new meme-format. In the last 7 days, videos made on the app did 1.1m views! We made eggnog.ai/remix for this reason. You can use the product to make funny videos to send to friends (cartoon remixes take < 20s to make) and live-action take 1-2 minutes (no sign-up required to make…
- IMI made a YouTube Documentary using only open source models on one GPU [video]2024 · youtube.com · ▲5
I wanted to explore different open source Gen AI tools and brought them together to generate this youtube video: voice, music, image and text. All processed on a single RTX3090. The text for the video is generated using the wikipedia article on Octopus as a source.
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 · 19d 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