# openmathmodel/open-math-harness

> The open-source runtime of Open Math OS for collaborative math research: runs agents on open models, parallel proof search and Lean-checked verification. Written in Rust, requires Linux and bubblewrap.

- Magnitude: 5.4 out of 10 — Early signal
- Stars: 129 total · +3 stars measured 2026-10-24, 00:03–01:26 UTC, ≈ 97 by evening
- Star trust: star growth looks organic
- Category: Science & research · Language: Rust · License: Apache-2.0 · Created: 2026-10-22 · Last push: 2026-10-23
- GitHub: https://github.com/openmathmodel/open-math-harness · Homepage: https://www.openmathmodel.org/ · Page: https://gitnova.dev/en/r/openmathmodel/open-math-harness

## Useful for

- Build the runtime from source with cargo to study its architecture
- Run the small self-contained example included in the repository
- Study the implementation of the capability-based microkernel and agent confinement

## Why it’s here

- Star-counter measurements on 2026-10-24 (UTC), 00:03–01:26: 126 → 129 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +97 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 129 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #175.
- About 21 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: 13
- Issues and pull requests: 3
- Watchers: 0
- Average over the last week: 75 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2
- Latest release: v0.41.0 (2026-10-23)

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-10-22 … 2026-10-24: 24, 105, 3

## Spotted in now

- Top new repositories this week: #175

## More in this category

1. **CuboiLeo/SuperMimic-Reproduced** — 4.1 · Early signal · Science & research · Python · +0 stars measured 2026-10-24, 00:03–01:26 UTC, ≈ 38 by evening
   From-scratch reproduction of the SuperMimic paper (arXiv:2610.28480): a differentiable world model plus short-horizon BPTT actor-critic for Unitree G1 whole-body motion tracking, built on mjlab/MuJoCo Warp, with data pipeline, training,…
   Full card: https://gitnova.dev/en/r/CuboiLeo/SuperMimic-Reproduced.md
2. **flybrainlabs/miner** — 3.7 · Early signal · Science & research · JavaScript · +4 stars measured 2026-10-24, 00:04–01:27 UTC, ≈ 70 by evening
   Deterministic integer LIF neuron simulation with a WASM engine, browser workers and a three-stage mining workflow for the flybrainlabs project.
   Full card: https://gitnova.dev/en/r/flybrainlabs/miner.md
3. **openai/math** — 2.0 · Cooling · Science & research · Lean · +2 stars measured 2026-10-24, 00:07–01:29 UTC, ≈ 26 by evening
   A collection of mathematical manuscripts and Lean formalizations produced by an internal OpenAI model while solving open research problems. Intended for mathematicians and researchers studying the results and verifying proofs.
   Full card: https://gitnova.dev/en/r/openai/math.md
4. **elder-plinius/V3R1T4S** — 1.8 · Cooling · Science & research · Python · +1 star measured 2026-10-24, 00:09–01:30 UTC, ≈ 11 by evening
   A collection of prompts and agent workflows for attacking open scientific problems: cipher breaking, graph bounds, codes and number-theory conjectures. Aimed at researchers and hobbyists willing to run LLM agents on unsolved problems.
   Full card: https://gitnova.dev/en/r/elder-plinius/V3R1T4S.md
5. **CrocSwap/integer-mult-bounds** — 1.6 · Steady · Science & research · Python · +0 stars measured 2026-10-24, 00:07–01:31 UTC, ≈ 2 by evening
   A research repository of community proofs improving the asymptotic exponent for integer multiplication (κ > 2^-15), with certificates, Lean checks and reproducible audits.
   Full card: https://gitnova.dev/en/r/CrocSwap/integer-mult-bounds.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 01:35 UTC, updated every 30 minutes.