# astroautomata/PySR

> PySR is a symbolic regression library for Python and Julia that searches for interpretable analytic expressions fitting a dataset, instead of a black-box neural network.

- Magnitude: 2.2 out of 10 — Steady
- Stars: 4,135 total · +2 stars measured 2026-10-24, 19:21–20:07 UTC, ≈ 3 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2020-09-14 · Last push: 2026-10-22
- GitHub: https://github.com/astroautomata/PySR · Homepage: https://pysr.ai · Page: https://gitnova.dev/en/r/astroautomata/PySR

## Useful for

- Find a formula describing experimental data instead of training a neural network
- Extract an analytic equation from a trained neural network via symbolic distillation
- Compare candidate equations by accuracy and complexity using model.equations_

## Why it’s here

- Star-counter measurements on 2026-10-24 (UTC), 19:21–20:07: 4133 → 4135 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +3 stars, using observed gains and the previous day.
- Interest is fading: the two-day pace is 48% of the previous week and a half.
- Hacker News: “Symbolic Learning in Python and Julia” — 25 points, 4 days ago.

## 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: 385
- Issues and pull requests: 935
- Watchers: 31
- Average over the last week: 32 per day
- Usual pace: 2 per day
- Stars in the last hour (measured): 3
- Latest release: v2.7.2 (2026-10-19)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-25 … 2026-10-24: 6, 1, 1, 1, 3, 0, 2, 4, 1, 1, 2, 1, 2, 2, 0, 1, 1, 1, 3, 1, 2, 8, 89, 20, 85, 71, 18, 6, 23, 2

## Hacker News

- Symbolic Learning in Python and Julia — 25 points, 4 comments: https://news.ycombinator.com/item?id=50171936

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **deepseek-ai/DeepInfer** — 7.1 · Cooling · Language models · Python · +661 stars measured 2026-10-24, 00:03–20:02 UTC, ≈ 792 by evening
   Offline inference framework for running DeepSeek models at large scale: optimized kernels, MoE/Attention parallelism, deterministic sampling and structured outputs. Aimed at teams deploying DeepSeek-V4.1-Flash on NVIDIA SM100 or Huawei…
   Full card: https://gitnova.dev/en/r/deepseek-ai/DeepInfer.md
2. **Niko1221/Strata** — 4.5 · Steady · Language models · C++ · +723 stars measured 2026-10-24, 00:04–20:03 UTC, ≈ 851 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
3. **google-pytorch/torch_tpu** — 4.4 · Early signal · Language models · C++ · +15 stars measured 2026-10-24, 00:03–20:03 UTC, ≈ 19 by evening
   TorchTPU is a PyTorch backend for Google TPUs that lets you run PyTorch models and operations on TPU devices, with custom ATen kernels, an XLA compilation cache, and distributed training support.
   Full card: https://gitnova.dev/en/r/google-pytorch/torch_tpu.md
4. **Edge0-AI/Edge0** — 4.4 · Steady · Language models · Python · +230 stars measured 2026-10-24, 00:04–20:03 UTC, ≈ 273 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
5. **h563k/chat-keeper** — 4.2 · Early signal · Language models · CSS · +61 stars measured 2026-10-24, 00:06–20:04 UTC, ≈ 71 by evening
   A third-party mirror of the Claude web interface plus API access to Claude, Gemini and OpenAI, reachable directly from China without a VPN. The repository mainly serves as a landing page and entry point for the paid service.
   Full card: https://gitnova.dev/en/r/h563k/chat-keeper.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 20:13 UTC, updated every 30 minutes.