Token Police

What it does

Stop tab-hopping across six usage pages. Token Police reads your Claude Code, Codex, Cursor, Grok & Gemini quota into one panel — burn rate, reset times, alerts. No keys, all local. Bonus: a cop who goes bald if you sit too long.

A free, open-source Chrome extension that shows how much usage you have left for Claude Code, Codex, Grok, Cursor, Grok Bot and Gemini — with reset times, burn rate and low-quota alerts. No account, nothing leaves your browser.

One side panel shows your remaining usage for Claude Code, Codex, Cursor, Grok, Grok Bot and Gemini — with reset times, burn rate and low-quota alerts. No account linking, no API keys, and nothing leaves your browser. And a little hair mascot that loses hair as you burn quota and makes you stand up now and then. Works in Chrome and other Chromium browsers (Edge, Brave, Arc). The button always points to the newest build on GitHub — you never download an outdated version. Every AI coding tool hides its quota in a different place. This extension reads them all and puts the numbers where you can see them. Weekly and short-term limits for all six agents, plus exactly when each one resets. Pick…from token-police.philosophie.ai

• 
  CavemanApr 2026 · ▲262

  Why use so many token when few do trick?

• 
  StraudeApr 2026 · ▲155

  Strava for Claude Code, the global tokenmaxxing Leaderboard

• 
  Caveman24d ago · caveman.so · ▲161

  why use many token when few do trick

• 
  toktrackFeb 2026 · ▲68

  Track AI CLI spending across Claude, Codex & Gemini in 40ms

• 
  whoburnedmoreJun 2026 · ▲91

  Spotify Wrapped for Claude, Codex & a Public leaderboard.

• 
  Claude Code & Codex Usage Trading Cards by RudelMay 2026 · ▲169

  Get your trading card based on your CC & codex usage

• 
  I trained a 125M model to autocomplete piano on-device▲598

  I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

  AI · 16d ago · simedw.com

• 
  Astute▲585

  Automate your B2B brand going viral, with new media creators

  AI · 18d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 25d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

  AI · 26d ago · cactuscompute.com

• 
  Coldtea.ai▲512

  Make your software self-driving

  AI · 30d ago · coldtea.ai

• 
  Soloop▲472

  Approval-first Agent OS for solo founders

  AI · 30d ago · soloop.io

• 
  Open-Source eInk Bike Computer▲358

  OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.

  Dev tools · 1d ago · opentrailpaper.com

• 
  Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s▲237

  Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API. - carloslfu/slotstream

  Dev tools · 4d ago · github.com

• 
  Weedout – Safari extension that hides YouTube AI-labeled videos▲182

  Weedout is a Safari extension that filters out videos YouTube labels as “Made with AI”.

  AI · 4d ago · masteranza.github.io

• 
  TERMy – A fast terminal assistant that does not use LLMs▲177

  NPC-Forge is a framework for building conversational agents that run on the CPU without relying on machine learning or LLMs. - NPC-Forge/docs/development.md at main · gioblu/NPC-Forge

  AI · 1d ago · github.com

• 
  HN Match Maker – Matching "Who Wants to Be Hired?" With "Who's Hiring?"▲123

  Find your next hire or your next role from Hacker News monthly threads. AI-powered matching between candidates and job postings.

  AI · 4d ago · hnmatchmaker.com

• 
  OwnTime – a chess clock for your day's priorities▲110

  I made OwnTime to balance between competing priorities in my life. The idea is based on two main influences: the concept of "roles" from "The 5 Choices" (2015), and my repeated failure to effectively implement time blocking due to the necessary flexibility in my role. The app allows you to define time budgets, which are not much more than a few mutually exclusive countdown timers. The UX is essentially that of a chess clock for an arbitrary number of players with configurable time. The whole point of the app is to kick you out of the running role/priority when its time is up. One…

  Life & fun · 4d ago · owntime.app