Zynthian: https://zynthian.org/ Monome: https://monome.org/ Two simply AMAZING synth platforms of the 21st century which push things even further than the mainstream hardware vendors are willing to allow. DIY your thing? The FundamentalFrequency LMN-3 might be up your alley: https://github.com/fundamentalfrequency Runs JUCE plugins, is kind of a cyberpunks’ Teenage Engineering OP1, without the fuss and nonsense... - Source: Hacker News / 6 months ago

Https://vcvrack.com/ and https://www.youtube.com/c/omricohen-music. - Source: Hacker News / 11 months ago

If you want to understand (Subtractive) synthesis. The best way is to get copy of VCV rack and follow a few tutorials. If you patch one subtractive mono synth voice once, you understand 80% of all subtractive synth architecture moving forward. https://vcvrack.com (open source and wonderful). - Source: Hacker News / over 1 year ago

I wonder whether someone already has build away to create modular synthesizer using block with knobs on the table. A line on the top of the knob would signal its position. (In the video I saw some shots that looked like sequencers.) You would also need some mechanism to connect the modules together. I played around with VCV Rack [1], but adjusting knobs with a mouse feels very different than using your hands to... - Source: Hacker News / almost 2 years ago

I have a couple of these to add as well: VCVRack - simply one of the most mind-expanding things a synthesizer-nerd can play with. (https://vcvrack.com/) ZynthianOS - another example of a simple software solution to a problem nobody realized existed, opening the door to an absolutely astonishing array of Audio processing tools (https://zynthian.org/). - Source: Hacker News / about 2 years ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 7 days ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 9 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 11 days ago

Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 19 days ago

If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 20 days ago