# chenglou/handwired

> Turns regular JavaScript code into a differentiable neural net: if-else, loops and state are compiled into matrix multiplications and ReLU with no training. Runs on JS or WebGPU.

- Magnitude: 5.6 out of 10 — Early signal
- Stars: 162 total · +67 stars measured 2026-10-15, 06:44–08:13 UTC, ≈ 110 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: TypeScript · License: MIT · Created: 2026-10-15 · Last push: 2026-10-15
- GitHub: https://github.com/chenglou/handwired · Homepage: https://chenglou.me/handwired/ · Page: https://gitnova.dev/en/r/chenglou/handwired

## Useful for

- Compile existing JS code into a differentiable form to train its weights
- Speed up search over 100k JSON documents using GPU parallelism
- Attach a frozen program to a neural net and train them end-to-end

## Why it’s here

- Star-counter measurements on 2026-10-15 (UTC), 06:44–08:13: 95 → 162 stars (+67). This is the change over that interval.
- Estimated end-of-day forecast: about +110 stars, using observed gains and the previous day.
- The repository is 0 days old and already has 162 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #104.
- About 43 forks a day — people are taking the code.

## 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: 10
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 110 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 45

## Stars per day, last 1 day (oldest → newest, today is partial)

2026-10-15 … 2026-10-15: 67

## Spotted in now

- Top new repositories this week: #104

## More in this category

1. **BaruqueRodrigues/llm-legislativo** — 5.8 · Early signal · Language models · Python · +32 stars measured 2026-10-15, 00:23–08:12 UTC, ≈ 126 by evening
   Large-scale Brazilian legislative corpus and a causal Transformer language model trained from scratch in pure PyTorch without pretrained weights or closed APIs.
   Full card: https://gitnova.dev/en/r/BaruqueRodrigues/llm-legislativo.md
2. **prabanta-dev/janas** — 5.1 · Early signal · Language models · C · +10 stars measured 2026-10-15, 00:20–08:13 UTC, ≈ 42 by evening
   Janas is a family of AI tools in C with no dependencies. Janas-LLM runs large MoE models (up to 80B, 48 GB) on a 32 GB laptop by streaming experts from NVMe SSD, and outperforms llama.cpp on all 13 tested models.
   Full card: https://gitnova.dev/en/r/prabanta-dev/janas.md
3. **Niko1221/Strata** — 4.6 · Steady · Language models · C++ · +315 stars measured 2026-10-15, 00:21–08:13 UTC, ≈ 894 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
4. **cdcailf/cjkfold** — 4.5 · Early signal · Language models · Python · +22 stars measured 2026-10-15, 00:24–08:13 UTC, ≈ 74 by evening
   Python library that folds look-alike CJK glyphs (Kangxi radicals and CJK radical supplements) back to the Han characters they render as, so text extracted from PDFs matches in search and comparison. Zero-dependency, pure functions.
   Full card: https://gitnova.dev/en/r/cdcailf/cjkfold.md
5. **Edge0-AI/Edge0** — 4.4 · Peaking · Language models · Python · +142 stars measured 2026-10-15, 00:22–08:13 UTC, ≈ 349 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 2026-10-15 08:28 UTC, updated every 30 minutes.