GSV – a personal AI computer that unifies your machines
Back in April I left the Agents team at Cloudflare because even though I loved the work, I always had the drive to build the apps rather than the libraries. I felt like nobody was building the ideas that I wanted to exist. My biggest drive was wanting my agents to run fully on “the cloud” yet having them on all my machines at the same time. So I ended up building GSV, fully open source. GSV acts as a cloud computer by having a remote file system and a shell environment and trying very hard to pretend to be something close to Unix. There’s a kernel that handles all the primitive operations,…
What it does
In the maker’s words, at launch
Back in April I left the Agents team at Cloudflare because even though I loved the work, I always had the drive to build the apps rather than the libraries. I felt like nobody was building the ideas that I wanted to exist. My biggest drive was wanting my agents to run fully on “the cloud” yet having them on all my machines at the same time. So I ended up building GSV, fully open source. GSV acts as a cloud computer by having a remote file system and a shell environment and trying very hard to pretend to be something close to Unix. There’s a kernel that handles all the primitive operations, including AI inference and the agent loop. At the same time, your devices (and browser!) can connect your GSV to provide file system and shell access to those same agents too. This allows your agents running on the edge to have access to your local devices. I’ve just released the beta and would love to hear feedback. As of today, it requires a Workers Paid account (~5$/mo) plus your model costs.
Does the same job
all alternatives →
- OSOpen-Source Lovable AlternativeOct 2025 · github.com · ▲7
It uses claude code with GLM-6 model which is cheap yet powerful for most of the cases. for deployment Cloudflare Workers. It is a 2 weeks of hard work! Lemme know what you think!
- ATA tool that turns everyday computers into your own AI cloud2024 · github.com · ▲5
I have a favour to ask. I’ve been working for a while on Kalavai, a project to make distributed AI easy. There are brilliant tools out there to help AI hobbyists and devs on the software layer (shout out to vLLM and llamacpp amongst many others!) but it’s a jungle out there when it comes to procuring and managing the necessary hardware resources and orchestrating them. This has always led me to compromise on the size of the models I end up using (quantized versions, smaller models) to save cost or to play within the limits of my rig. Today I am happy to share the first public version of our…
- WRWe're building a search engine for GCP2022 · listvms.com · ▲9
Hi HN, I previously wore SWE/SRE hats on GCP. Later, I was on the other side, managing thousands of machines. The friction points of onboarding and operating cloud systems are personal problems to me. I’ve found it hard to keep track of all the random cloud resources floating around, especially as my team’s assets proliferated. Occasionally, there is a resource affecting an outage but no one remembers where it is. I am constantly frustrated by existing tooling. APIs can work, after you’ve navigated the byzantine documentation, but I often find myself doing ad-hoc tasks which are best…
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 · 26d ago · cactuscompute.com
Launched alongside, June 2026
the whole month →
Fundraisly▲1,544AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
- H6Homebrew 6.0.0▲1,481
Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
- PU
hope you enjoy
Life & fun · Jun 2026 · vorpus.github.io
- IM
Life & fun · Jun 2026 · hackernewstrends.com