Local text, image, video, music and 3D from one CLI, no Python
Hi HN! I'm the author of mere.run a local first inference runtime built around an installable CLI. I believe that whenever possible we should use the stuff we already own (like our Mac laptops, decent machines gathering dust, our gaming PC) and the limited electrical power we have easy access to, like the socket in the wall next to most of us. We shouldn't have to send our data to the cloud hoping some T&C will prevent it from being used in a way that we'd regret. Most of the local AI solutions are technical, involved, and land a curious body in some package hell. People are optimizing for…
In plain words
Mere.run is a command-line tool for running AI inference locally on personal devices without sending data to the cloud. It supports text, images, video, music, and 3D models through a single CLI interface that requires no Python installation. Designed for users who want privacy and control, it aims to simplify local AI by working across different systems and eliminating common setup complications that plague existing solutions.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! I'm the author of mere.run a local first inference runtime built around an installable CLI. I believe that whenever possible we should use the stuff we already own (like our Mac laptops, decent machines gathering dust, our gaming PC) and the limited electrical power we have easy access to, like the socket in the wall next to most of us. We shouldn't have to send our data to the cloud hoping some T&C will prevent it from being used in a way that we'd regret. Most of the local AI solutions are technical, involved, and land a curious body in some package hell. People are optimizing for one system and not another, the fun stuff is on PC if you own a Mac, and on Mac if you own a PC. So mere.run was my choice to begin to patch many of those things that I saw as problematic. Text, chat, code, image gen, speech tts+asr, vision (caption/ground/segment/track/pose/depth/face/OCR/etc), music, sfx, video, 2d->3d, persistent worlds, lora training plus a few more things I am probably forgetting all in one place to work the way you work, with a scriptable CLI, an openAI compatible serve, and optionally a native app on Mac. It's native swift on MLX, no python, PyTorch, diffusers for inference. For text lanes with GGUF it uses llama.cpp and for a/v muxing its FFmpeg. Most upstream releases that don't have an MLX variant are converted offline and hosted on huggingface. All release packages are built for arm64 (Mac & Cuda) plus x86. They're signed and ship SHA256SUMS. No windows at the moment. > mere.run model capabilities --recommended # That inspects your machine before recommending to prevent pulling models that don't fit your spec There's a workflow layer with typed, validated graphs so you can create immutable job bundles and run them locally, over an ssh executor or using a fleet of machines and the relay service. (It's hosted at relay.mere.run and is currently invite only while I test, but its also totally open MIT so you can set it up yourself) The whole runtime is MIT along with the companion packages, models carry their own licenses and the CLI makes it clear when something has specific terms. Once you've pulled the models, everything works fully offline. I've been working on a (hopefully) comprehensive docs -> https://docs.mere.run No account, no API key, no analytics or phone home. Any network calls in the source are all at your request only like huggingface.co (models), GitHub.com (Pi install). I'm just getting started, but it's finally at the point I'd love feedback, contributions, and just folks to generally find it useful. I hope it helps you make things and explore what's possible with the stuff you've already got in your home. Would love any thoughts, questions, ideas and maybe a star if you do that kinda thing. -Kyle
Does the same job
all alternatives →
- TCThink, CL tool that makes AI your command line copilot (written in Go)2023 · github.com · ▲14
Hi HN, I'm thrilled to share with you think, a command-line tool that I developed while diving back into the programming scene. For the past few years, my focus had shifted from hands-on programming to managerial roles, my last one being at Affirm (I started Affirm's Polish office). However, I recently left my job to revisit my passion for coding and see if I could still write code that works. Not to mention that with what is currently going on in AI if you are a developer this probably the best possible time for a sabbatical in human history :) My first attempt was with LangChain, but I…
- HAHm – a task runner with a Python DSL, growing into a CI/CD systemMay 2026 · github.com · ▲12
Hi HN! My name is Marko and I am working on a CI/CD system at harmont.dev, a CI/CD system that sucks slightly less. As I've been working on the cloud, I realized that the CLI might be generally useful as a task runner, even if you don't care for our CI/CD, and that's what I'm sharing here! Every CI system I've used at Tesla, Bun, and mesa.dev has had the same problems: stateless and slow (GHA), or stateful and horizontally unscalable (Jenkins), with YAML on top of either. The straw that broke the camel's back for me was the realization that all my Claudes are waiting upwards…
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, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
