Building JoyMux · Local Agent Runtime
Local Agent Runtime so agent have a stable environment
What it does
JoyMux is the local control layer for AI coding agents. Shape context, cut wasted tokens, and hard-reset to the same state — so your Mac/linux stays usable while you
JoyMux is the OS for coding agents. Durable execution across Codex, Claude Code, Gemini, OpenCode. Developer trial on macOS. Enterprise for Linux & training ser
JoyMux is the local execution OS under your coding agents — durable state, recovery, replay, and evidence so Codex, Claude Code, Gemini, OpenCode, and whatever you run next share one machine they can return to. Handoff numbers are one frozen fixture — not a universal speed claim. Install JoyMux locally. Give Codex, Claude Code, Gemini, and OpenCode durable execution state — resume after a crash, replay evidence, send the delta. Put JoyMux under the agents on your servers — including training boxes and SSH hosts — so multi-agent work stops flooding the machine and every supported agent shares durable execution state. Without durable execution state, every interruption turns into rediscovery…from joymux.com
Does the same job
all alternatives →
Locofy: design-to-code agentsJun 2026 · ▲112Agentic frontend layer between Figma and Cursor & Claude
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, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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