Launch HN: Lucidic (YC W25) – Debug, test, and evaluate AI agents in production

109 points by AbhinavX 1 year ago | 36 comments

Launch HN: Innate (YC F24) – Home robots as easy to program as AI agents

152 points by apeytavin 1 year ago | 63 comments

Launch HN: Cerebrium (YC W22) – Serverless Infrastructure Platform for ML/AI

46 points by za_mike157 2 years ago | 32 comments

Launch HN: AgentHub (YC W24) – A no-code automation platform

140 points by murb 2 years ago | 83 comments

Show HN: Gigacatalyst – Extend your SaaS with an embedded AI builder

46 points by namanyayg 5 months ago | 19 comments

Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

340 points by dhorthy 1 year ago | 187 comments

Launch HN post introducing HumanLayer, a YC F24 API and SDK that lets AI agents request human approvals and input via Slack or email.

Show HN: Real-time AI Voice Chat at ~500ms Latency(github.com)

480 points by koljab 1 year ago | 202 comments

GitHub repository for RealtimeVoiceChat, an open-source project for natural spoken conversation with an AI at low latency.

Show HN: HN.watch – Videos of all Hacker News posts(hn.watch)

193 points by mrborgen 28 days ago | 96 comments

HN.watch is a Hacker News front-page mirror that generates short AI explainer videos for each story, built by Scrimba to demo its Scrimba Explain tool.

Show HN: The fastest browser for AI agents to run browser automation(ego-lite.apposters.com)

8 points by ehurynovich 4 days ago | 0 comments

Landing page for ego lite, a free macOS browser that lets AI agents like Claude Code and Codex run parallel browser automation in isolated Spaces.

Show HN: Infinity – Realistic AI characters that can speak

435 points by lcolucci 2 years ago | 272 comments

Show HN post from Infinity AI introducing a video diffusion transformer driven by audio that generates realistic speaking characters from an image and script.

Homa: The end of TCP for AI clusters [video](youtube.com)

70 points by signa11 21 days ago | 36 comments

AI Engineer World's Fair talk video in which Stanford's John Ousterhout presents Homa, a transport protocol proposed to replace TCP in AI datacenter clusters.

Show HN: I built a sub-500ms latency voice agent from scratch(ntik.me)

531 points by nicktikhonov 7 months ago | 152 comments

Blog post by Nick Tikhonov describing how he built a voice agent with ~400ms end-to-end latency using streaming STT, LLM, and TTS with turn detection.