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

大猫的无限游戏
大猫的无限游戏
阮一峰的网络日志
阮一峰的网络日志
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
WordPress大学
WordPress大学
博客园 - 叶小钗
Hugging Face - Blog
Hugging Face - Blog
博客园 - 司徒正美
Last Week in AI
Last Week in AI
罗磊的独立博客
量子位
Jina AI
Jina AI
T
Tailwind CSS Blog
Apple Machine Learning Research
Apple Machine Learning Research
IT之家
IT之家
美团技术团队
雷峰网
雷峰网
爱范儿
爱范儿
S
SegmentFault 最新的问题
小众软件
小众软件
月光博客
月光博客
酷 壳 – CoolShell
酷 壳 – CoolShell
人人都是产品经理
人人都是产品经理
The Cloudflare Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报

Show HN

GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal).
AI Time Tracker - Automatic Time Tracking & Daily Work Log
AI Time Tracker · 2026-06-21 · via Show HN

AI Worklogs That Reveal How You Work

Automatically log and journal your work. Track your time on projects and activities and get insights to improve your productivity and work habits with AI.

Have you ever wondered how much work you actually do during a typical workday? Or do you remember what did you done last week?Knowing these metrics can give you great feedback to improve your or your team's productivity and performance.

How It Analyses Your Workday

AI time tracker system works in the background to give you data about your workday.

Step 1

Define Your Context

Provide your project goals and specific objectives. The AI uses this to accurately categorise your work and deliver relevant insights.

Step 2

Background Monitoring

The app runs quietly in the background, capturing periodic screenshots to understand exactly how you're spending your time — no manual input needed.

Step 3

Local AI Analysis

A local LLM analyses your data directly on your device, extracts a structured work journal, and saves logs securely. Your data never leaves your Mac.

Ask Your Work Journal Logs Anything

Get instant insights from your work logs with natural language questions.

Features

Journal and optimise your work time with AI-powered automatic tracking.

Privacy with Local AI

All screen analysis happens locally on your machine using a local LLM (Qwen-3-VL:2b). Your sensitive data and screenshots leave your computer.

Detailed Task Detection

By watching your screen, the AI can detect what you are working. It can detect windows, file names, apps, and tasks you are working on.

Generate detailed daily logs automatically and export them to CSV. Perfect for client billing, internal reporting, or personal productivity analysis.

Provide project and your activity categories as context so the AI intelligently categorises your work and provides statistics reports based on your context.

Starts with your system so your workday is tracked from the first minute, and pauses automatically when your Mac sleeps so idle time is never counted as work.

"I wanted feedback on my productivity and work habits — I wasn't sure what was actually taking my time. Instead of marketing, consuming content and unnecessary activities kept stealing hours. So I built Didon. Now I can understand where my time goes."

Early Access Pricing

  • Lifetime access & updates
  • 1:1 dedicated support (if needed)
  • No extra AI model costs, uses local LLM (Qwen-3-VL:2b)
  • Install on one system only
  • Prompt for productivity and work habits insights
  • Unlimited CSV log exports
  • Smart context & activity categories
  • 100% money back guarantee (refund if not working)
  • Upcoming features (integrations, advanced reports, add notes, etc.)

One-time payment

€89€199

Pay once, own forever

Windows user? Create an account to join the waitlist for early access when it launches.

From the Blog

Tips on productivity, time tracking, and automated reporting

FAQ

Everything you need to know about Didon. If you have other questions, feel free to reach out.

Track Your Work & Journal Your Day with Automatic AI Time Tracking

Most people lose track of where their day goes. Didon is an AI-powered automatic time tracker for macOS that quietly runs in the background and turns your daily activity into a clear, structured work journal — without manual timers or constant check-ins.

Automatic Time Tracking

Traditional trackers rely on you remembering to hit start and stop. Didon observes what you're doing and logs time automatically — whether you're writing code, drafting a proposal, or working in a spreadsheet.

Context, Not Just App Names

Most tools tell you "3 hours in Chrome" — that's not useful. Didon uses lightweight AI analysis to understand what you're actually working on, then maps activity to your projects and goals.

Daily Summaries & Privacy

Didon generates clean daily reports and surfaces weekly trends — peak hours, productive days, and time drains. Everything runs on-device, so your screen activity never touches a server. If you want those insights to actually change your behavior, Didon's upcoming AI productivity coach will hold you accountable for acting on them.