# minimAluminiumalism/open-CoT

> Engineering reproductions of methods for extracting chain-of-thought from closed frontier models like GPT and Claude via a forced tool-call protocol, with benchmark scripts and reports.

- Magnitude: 4.7 out of 10 — Early signal
- Stars: 169 total · +64 stars measured 2026-10-14, 00:48–17:10 UTC, ≈ 87 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-10-09 · Last push: 2026-10-10
- GitHub: https://github.com/minimAluminiumalism/open-CoT · Page: https://gitnova.dev/en/r/minimAluminiumalism/open-CoT

## Useful for

- Run a single forced-reasoning session on a math problem via replay_cot.py
- Reproduce the full benchmark matrix of 10 problems across two models
- Compare forced protocol results against a no-tool control

## Why it’s here

- Star-counter measurements on 2026-10-14 (UTC), 00:48–17:10: 105 → 169 stars (+64). This is the change over that interval.
- Estimated end-of-day forecast: about +87 stars, using observed gains and the previous day.
- The repository is 5 days old and already has 169 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #112.

## 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: 7
- Issues and pull requests: 0
- Watchers: 5
- Average over the last week: 34 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 6

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-10-09 … 2026-10-14: 5, 11, 7, 21, 73, 64

## Magnitude by day, last 2 days

10-13 2.9, 10-14 4.7

## Spotted in now

- Top new repositories this week: #112

## More in this category

1. **lyogavin/airllm** — 6.6 · Breakout · Language models · Jupyter Notebook · +328 stars measured 2026-10-14, 00:37–17:25 UTC, ≈ 473 by evening
   A library for inference and training of large language models on low-VRAM GPUs: it streams weights layer by layer from disk, letting 70B–671B models run on 4–12 GB of VRAM without quantization or distillation.
   Full card: https://gitnova.dev/en/r/lyogavin/airllm.md
2. **prabanta-dev/janas** — 6.5 · Early signal · Language models · C · +57 stars measured 2026-10-14, 00:37–17:25 UTC, ≈ 88 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. **open-webui/open-webui** — 5.4 · Breakout · Language models · Python · +83 stars measured 2026-10-14, 00:37–17:09 UTC, ≈ 128 by evening
   Open WebUI is a self-hosted web interface for AI models via Ollama and OpenAI-compatible APIs, with RAG, plugins, agents, and team collaboration.
   Full card: https://gitnova.dev/en/r/open-webui/open-webui.md
4. **mw00/project-maya** — 5.1 · Early signal · Language models · C++ · +86 stars measured 2026-10-14, 00:37–17:10 UTC, ≈ 117 by evening
   Local engine, server and dashboard to run the 321B MoE model GLM-5.3-Flash on one or two NVIDIA GPUs, offloading experts to RAM and NVMe.
   Full card: https://gitnova.dev/en/r/mw00/project-maya.md
5. **Niko1221/Strata** — 4.7 · Steady · Language models · C++ · +703 stars measured 2026-10-14, 00:38–17:10 UTC, ≈ 966 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

---

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 2026-10-14 17:26 UTC, updated every 30 minutes.