# actual-computer/toks

> A C tokenizer library that reproduces Hugging Face tokenizer ids exactly, with hand-written SIMD kernels (AVX2, NEON) and no dependencies. It is made for dropping into inference engines and other performance-critical pipelines.

- Magnitude: 3.5 out of 10 — Early signal
- Stars: 78 total · +1 star measured 2026-10-08, 00:02–01:28 UTC, ≈ 29 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C · License: Apache-2.0 · Created: 2026-10-05 · Last push: 2026-10-08
- GitHub: https://github.com/actual-computer/toks · Homepage: https://actual.inc · Page: https://gitnova.dev/en/r/actual-computer/toks

## Useful for

- Drop into an inference engine to replace the Hugging Face tokenizer at the preprocessing step.
- Tokenize datasets or prompts in Python through the hf-style Tokenizer API at higher throughput.
- Validate parity of token ids against hf tokenizers on a given tokenizer.json before switching.

## Why it’s here

- Star-counter measurements on 2026-10-08 (UTC), 00:02–01:28: 77 → 78 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +29 stars, using observed gains and the previous day.
- The repository is 3 days old and already has 78 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #182.

## 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: 3
- Issues and pull requests: 58
- Watchers: 0
- Average over the last week: 27 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1
- Latest release: v0.3.2 (2026-10-08)

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-04 … 2026-10-08: 0, 0, 47, 31, 1

## Spotted in now

- Top new repositories this week: #182

## More in this category

1. **Niko1221/Strata** — 5.6 · Peaking · Language models · C++ · +64 stars measured 2026-10-08, 00:01–01:27 UTC, ≈ 974 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
2. **deepseek-ai/DeepGEMM** — 4.9 · Peaking · Language models · Cuda · +2 stars measured 2026-10-08, 00:01–01:27 UTC, ≈ 69 by evening
   CUDA tensor core kernel library: GEMM (FP8, FP4, BF16), fused MoE, MQA scoring for the indexer. Kernels compile at runtime via DeepJIT, no CUDA build at install time.
   Full card: https://gitnova.dev/en/r/deepseek-ai/DeepGEMM.md
3. **StayLameBro/backburner** — 4.2 · Cooling · Language models · Python · +5 stars measured 2026-10-08, 00:02–01:27 UTC, ≈ 57 by evening
   A llama.cpp fork that plugs an iPhone into a Mac over USB-C and splits the work: the Mac runs layers 1-40, the iPhone runs 41-64 on its GPU, speeding up prefill and allowing context up to 196k-229k tokens. Aimed at people running…
   Full card: https://gitnova.dev/en/r/StayLameBro/backburner.md
4. **p-e-w/heretic** — 3.8 · Steady · Language models · Python · +7 stars measured 2026-10-08, 00:02–01:27 UTC, ≈ 148 by evening
   A tool for fully automatic removal of censorship (safety alignment) from transformer-based language models using directional ablation and Optuna-based parameter optimization.
   Full card: https://gitnova.dev/en/r/p-e-w/heretic.md
5. **Edge0-AI/Edge0** — 3.7 · Peaking · Language models · Python · +29 stars measured 2026-10-08, 00:03–01:27 UTC, ≈ 178 by evening
   An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run model tiers (35B and…
   Full card: https://gitnova.dev/en/r/Edge0-AI/Edge0.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 2026-10-08 01:38 UTC, updated every 30 minutes.