# Giltsch/cadtokens

> Pure-Python tool that reads semantic GD&T (PMI) from STEP AP242 files, checks them for errors, and produces inspection characteristic lists and ballooned PDF reports. Runs fully locally and includes an MCP server for AI agents.

- Magnitude: 0.2 out of 10 — Quiet
- Stars: 1 total · +0 stars measured 2026-10-24, 13:19–18:49 UTC, ≈ 0 by evening
- Star trust: star growth looks organic
- Category: Hardware, IoT & robotics · Language: Python · License: Apache-2.0 · Created: 2026-10-14 · Last push: 2026-10-14
- GitHub: https://github.com/Giltsch/cadtokens · Page: https://gitnova.dev/en/r/Giltsch/cadtokens

## Useful for

- Extract the inspection characteristic list from a STEP file to CSV for an AS9102 Form 3 report
- Generate a ballooned PDF report for incoming inspection of a part
- Connect the MCP server so an AI agent can answer questions about tolerances and datums in the file

## Why it’s here

- Star-counter measurements on 2026-10-24 (UTC), 13:19–18:49: 1 → 1 stars (+0). This is the change over that interval.
- The repository is 10 days old and already has 1 star. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- New listing on glama.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 0 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 11 days (oldest → newest, today is partial)

2026-10-14 … 2026-10-24: 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0

## Magnitude by day, last 7 days

10-18 0.0, 10-19 0.0, 10-20 0.0, 10-21 0.0, 10-22 0.0, 10-23 0.0, 10-24 0.2

## Spotted in now

- New listing on glama

## More in this category

1. **Zagitta/gpu-unlock** — 9.0 · Breakout · Hardware, IoT & robotics · C · +1,755 stars measured 2026-10-24, 00:03–18:40 UTC, ≈ 2,150 by evening
   Linux kernel module that unlocks certain NVIDIA GA102/GA104 GPU features (e.g. RTX 3090) before the nvidia driver binds, using the CMP unlocker technique and UEFI timing. Requires a cold boot and opt-in via the gpu_unlock.targets kernel…
   Full card: https://gitnova.dev/en/r/Zagitta/gpu-unlock.md
2. **oosexgang/hackios-xnu-kernel** — 7.6 · Early signal · Hardware, IoT & robotics · C · +165 stars measured 2026-10-24, 00:03–18:40 UTC, ≈ 222 by evening
   Research project that boots Apple's open-source XNU kernel (iOS 16.5) and the unmodified iOS user space on a POCO X5 Pro 5G Android phone or in QEMU on Linux, using a custom EFI loader, UEFI port and replacements for Apple's closed drivers.
   Full card: https://gitnova.dev/en/r/oosexgang/hackios-xnu-kernel.md
3. **JustAResearcher/gpu-unlock-ada** — 6.2 · Early signal · Hardware, IoT & robotics · C · +216 stars measured 2026-10-24, 16:37–18:41 UTC, ≈ 262 by evening
   A Linux kernel module that applies an SM speed-select override before the stock NVIDIA driver binds, roughly doubling FP16/BF16 tensor throughput with FP32 accumulation on RTX 4090 (AD102) and experimentally on RTX 4070 Ti SUPER (AD103).
   Full card: https://gitnova.dev/en/r/JustAResearcher/gpu-unlock-ada.md
4. **Snapintosh/Snapintosh** — 5.6 · Early signal · Hardware, IoT & robotics · Python · +109 stars measured 2026-10-24, 00:03–18:41 UTC, ≈ 140 by evening
   Experimental EL2 hypervisor and toolchain that boots macOS 27 on an ASUS Zenbook A16 (Snapdragon X2 Elite), with an Adreno Metal/IOGPU driver stack. Requires the exact laptop model and a Mac host over USB-C.
   Full card: https://gitnova.dev/en/r/Snapintosh/Snapintosh.md
5. **pollen-robotics/microduck** — 5.1 · Breakout · Hardware, IoT & robotics · Rust · +340 stars measured 2026-10-24, 00:03–18:41 UTC, ≈ 428 by evening
   Firmware and system software for Microduck, a tiny biped duck robot on a Rockchip RK3566 that walks, rolls and gets up using neural policies. The repo contains daemons for motor control, updates, Bluetooth, gamepad and camera.
   Full card: https://gitnova.dev/en/r/pollen-robotics/microduck.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-24 18:51 UTC, updated every 30 minutes.