Show HN: 143.dev – we open-sourced our internal coding-agent infrastructure
3 comments
Your system's use of gVisor sandboxes for running coding agents is intriguing. If you're considering adding voice capabilities on Linux, Windows, or Android, speech-core (which I maintain) could complement your setup with its C++17 engine and ONNX Runtime support for ASR and TTS. https://github.com/soniqo/speech-core
Fascinating! Hadn't heard of speech-core before, but will check it out if we are thinking about adding voice (though right now are focused on some more core-platform specific things like allowing for multiple changesets in a single session and adding memory across runs)
Reach me on linkedin https://www.linkedin.com/in/ivan-sur/ if you need any help
Coding agents worked well for individual engineers, but the surrounding workflow was a bit of a mess. We generally found that many engineers had different MCP connections and context for their agents, personal automations running that other people couldn’t access, and very little introspection for what a human’s input into the coding agent looked like.
So we built an internal system that converted coding agents into shared team infrastructure.
The system runs Codex, Claude Code, OpenCode, and other agent harnesses in gVisor sandboxes. You can mix and match coding agents to tune your cost and intelligence tradeoff (for example, our team has started to use GLM 5.2 for automation tasks and a combination of Codex/Claude Code for manual tasks). It connects to a bunch of tools like GitHub, Linear, Sentry, Slack, PagerDuty and makes previews easy to generate.
We were inspired by internal systems like Stripe Minions and Ramp Inspect, but wanted an open version other teams could inspect, run, and adapt so we made it MIT-licensed and self-hostable.
Hope you like it!
Website: https://143.dev
Github: https://github.com/assembledhq/143