惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

WordPress大学
WordPress大学
大猫的无限游戏
大猫的无限游戏
B
Blog
阮一峰的网络日志
阮一峰的网络日志
IT之家
IT之家
Hugging Face - Blog
Hugging Face - Blog
博客园 - 【当耐特】
Jina AI
Jina AI
博客园 - 聂微东
T
The Blog of Author Tim Ferriss
宝玉的分享
宝玉的分享
L
LangChain Blog
M
MIT News - Artificial intelligence
Blog — PlanetScale
Blog — PlanetScale
腾讯CDC
酷 壳 – CoolShell
酷 壳 – CoolShell
Y
Y Combinator Blog
F
Fortinet All Blogs
H
Help Net Security
B
Blog RSS Feed
J
Java Code Geeks
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Apple Machine Learning Research
Apple Machine Learning Research
S
SegmentFault 最新的问题

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
Trace: Meeting transcripts that never leave your Mac
AG342 · 2026-06-14 · via Hacker News: Show HN

Meeting transcripts that never leave your Mac.

Trace captures your microphone and system audio, transcribes locally on your Mac, and hands you a markdown transcript with flagged moments inline.

No accounts. No cloud. No meeting bots.

Download on the Mac App Store

Requires macOS 14 or later and Apple silicon.

Out of the way until you need it.

One keystroke brings Trace up over any application: Zoom, Teams, Meet, Slack, anything. No app to open, no window to place.

Mark the moment. Keep talking.

Hit K mid-call, type a short note, hit Enter. The moment lands in your transcript at the exact timestamp. You stay in the meeting, and any AI reading the transcript later sees exactly what mattered.

Catch up without leaving the flow

Missed something? Peek at the last few minutes.

Press ? and the pill grows upward into a live transcript of the last two minutes, interleaved with every key moment you flagged. Runs entirely on-device, same as the final transcript. No uploads, no audio sent anywhere.

Markdown you can paste anywhere.

Into Notion or Obsidian for the vault. Into ChatGPT, Claude, or the AI of your choice if you want it summarised. Trace hands you clean, contextual markdown for whatever comes next.

Every transcript, one click away.

The menu bar keeps a quiet list of your sessions. Copy, reveal in Finder, or re-open without switching apps.

Fast. Private. Out of your way.

On-device only

A local speech model, running on-device. No servers, no accounts, and nothing you record ever leaves your Mac.

Seconds, not minutes

Transcribes meetings in seconds on Apple silicon. No upload, no queue, no spinner while a cloud catches up.

  • RRecord
  • KKey moment
  • ?Recap
  • PPause
  • HHide pill

Keyboard-driven

Record, flag, recap, pause, hide. Every action has a shortcut. Remap any of them to match your muscle memory.

~/Application Support/Trace/2026-04-16-sync-with-alex

  • mic.wav1.2 MB
  • system.wav1.5 MB
  • transcript.md4 KB
  • transcript.json12 KB

Yours, locally

Every session lives in Finder as plain audio and markdown. Move them into your vault, version them in git, or delete them. They're yours.

Flag what matters, live.

Hit K mid-recording to mark a moment. Add a note while the conversation keeps going. Key moments land inline in the transcript exactly where they happened, so you can scan to them in one pass.

**Alex**(36:40)

Sure, does the 15th work for you?

**Speaker 1**(36:44)

Works for me. Lock it in.

36:44·Next meeting date decided

**Speaker 1**(36:48)

Perfect. I'll send a hold now.

Meeting-aware.

Connect your calendar and every recording picks up the event title automatically. A quiet reminder appears one minute before the meeting starts, offering to record. Use your Mac's calendar, on-device and covering any account, or link Google directly. Opt-in, read-only, off by default.

**Speaker 1**[00:08]

Should we ship the Friday build?

**Speaker 2**[00:10]

Yeah, the build succeeds and the tests pass.

Speaker-aware.

Trace identifies who's speaking on the call and gives every participant a unique identifier.

Not another cloud tool.

No servers, API keys, accounts or telemetry. Your audio and your transcripts never touch a machine that isn't yours.

macOS asks for System Audio Recording permission so Trace can capture audio from your other apps. Trace never accesses your screen.

Read our full privacy policy

What you get

A clean, formatted transcript

Key moments that you flag land inline, right where they happened. Your future self, your teammates, and your AI of choice can scan straight to what mattered.

Compare

See how Trace stacks up.

Honest, on-device comparisons for the people who do not want a bot in the call or their audio in the cloud.

Start capturing.

Download on the Mac App Store

No accounts, no cloud, no telemetry.