OpenFork.video
Why AI video workflows should be packaged like apps.
What it does
I’m building OpenFork because I kept running into the same boring wall when testing new AI video/audio/image workflows: CUDA issues, Python packages fighting each other, and the fear of breaking a ComfyUI setup. It’s an opensource desktop client and python client + web workspace that runs AI media workflows in prebuilt Docker containers. The goal is simple: pick a workflow, let the client pull the right image, run it on your NVIDIA GPU, and send back into your project. No configuration needed.
Does a similar job
all alternatives →- OSOpen-source app builder for comfy workflows2024 · github.com · ▲59
Hey, we’ve been working on an open-source project built on top of Comfy for the last few weeks. It is still very much a work in progress, but I think it is at a place where it could start to be useful. The idea is that you can turn a workflow into a web app with an easy-to-use UI. Currently, it should work with any workflows that take images and text as input and return images. We are aiming to add video support over the next few days. Feedback and contributions are more than welcome!
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