News for hackers. Stuff that matters.

patethegreat

That’s an interesting angle. I’ve been thinking about Lich as aiming to be the minimum thing for orchestrating the dev stack itself so not really like an alternative to what you’re doing. I would think they’d compose well if you chose to use both actually.

Show HN: Lich, start a dev stack per coding agent in parallel

https://github.com/RPate97/lich

Hey HN, Lich is a worktree aware local dev stack orchestrator. Simply put, it allows you to run multiple copies of your development stack from different worktrees with different code in parallel without going insane. I built Lich because I’ve found myself increasingly using multiple parallel coding agents for development work. I wanted my coding agents to each have independent copies of my...

( Read More... | 2 comments | on HN )

Segment for LLM Traces? Seeking Feedback on an Open Source LLM Log Router

Hey everyone, I’m considering starting a new open source project and wanted to see if anyone else thinks the idea could be useful. The concept is simple: an open source LLM log router that works like Segment—but specifically for LLM logs. It would let you easily route logs to different analytics, eval, monitoring, and data warehouse platforms (think LangFuse, Gentrace, Lattitude, etc.) so you...

( Read More... | 2 comments | 6 points | on HN )

Show HN: Jay - Fully programmable, fully hosted AI voice agents

https://www.jay.so/

Hey everyone, we’re excited to announce Jay, a platform for building voice agents that hosts all of the agent’s infra while giving you full control over how the agent responds. Our goal is to give developers a Vercel-like experience for building voice agents.Currently, voice frameworks are either fully hosted with limited customizability (e.g. Vapi, Retell), or fully customizable while...

( Read More... | 2 comments | 3 points | on HN )
Hey everyone, today we're launching the closed beta of voice_dev, the only fully programmable platform for building voice agents that scale. We created voice_dev after struggling with other solutions that either lacked the flexibility we needed to build our agent or forced us to manage our own infrastructure.

We wanted a platform that provides all the infrastructure to run a voice agent while being fully programmable in Python. Every platform we tried either lacked some of the necessary infrastructure to run an agent (forcing us to host Docker containers and handle scaling ourselves) or provided all the infrastructure but had limited customization options. They might let you bring your own voice model or LLM, for example, but you can’t easily program the agent to fit your specific use case in a normal language like Python unless you also host some or all of it yourself.

voice_dev solves these problems by offering a complete platform for deploying and running AI voice agents. The platform includes all of the necessary infrastructure to run your agent while also being fully programmable in python, ensuring you’re always free to customize your agent any way you want.

Check it out and request access if you’re interested in being one of the first developers to build on the platform! We'd love to hear your feedback.