# MUSE-AI-Lab/ReMCTS

> ReMCTS is a research framework that improves LLM code generation by searching over a tree of candidate programs. Each candidate is executed, and failures are turned into structured reflections that guide the search, outperforming direct generation on HumanEval and MBPP.

- Magnitude: 0.0 out of 10 — Cooling
- Stars: 274 total · +0 stars measured 2026-11-01, 00:03–12:24 UTC, ≈ 0 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-10-27 · Last push: 2026-10-30
- GitHub: https://github.com/MUSE-AI-Lab/ReMCTS · Page: https://gitnova.dev/en/r/MUSE-AI-Lab/ReMCTS

## Useful for

- Improve code generation accuracy on HumanEval-style benchmarks without fine-tuning the model.
- Run a code generation task without visible tests using the no_tests configuration.
- Reproduce the paper's ablations on tree search, reflection and reward components.

## Why it’s here

- Star-counter measurements on 2026-11-01 (UTC), 00:03–12:24: 274 → 274 stars (+0). This is the change over that interval.
- The repository is 5 days old and already has 274 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #117.

## 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: 0
- Issues and pull requests: 6
- Watchers: 0
- Average over the last week: 46 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

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

2026-10-27 … 2026-11-01: 0, 3, 184, 87, None, 0

## Magnitude by day, last 3 days

10-30 5.2, 10-31 4.4, 11-01 0.0

## Spotted in now

- Top new repositories this week: #117

## More in this category

1. **togg53192-cmd/jailbreaks** — 6.6 · Peaking · Language models · +302 stars measured 2026-11-01, 00:01–12:24 UTC, ≈ 645 by evening
   A collection of 31 system prompts, persona locks, and AGENTS.md files for 25+ models (Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Gemma, GPT-OSS). Intended for research on how instruction hierarchies and policy overrides affect model…
   Full card: https://gitnova.dev/en/r/togg53192-cmd/jailbreaks.md
2. **thomasunise/casecite** — 5.6 · Early signal · Language models · Python · +59 stars measured 2026-11-01, 00:03–12:24 UTC, ≈ 109 by evening
   Self-hosted legal research platform: upload your firm's documents, ask questions with citations, review contracts, draft documents and research judges. Runs on your own infrastructure with your own API keys.
   Full card: https://gitnova.dev/en/r/thomasunise/casecite.md
3. **dbreunig/nesformer** — 5.4 · Early signal · Language models · Python · +15 stars measured 2026-11-01, 00:02–12:24 UTC, ≈ 36 by evening
   An NES emulator compiled into the weights of a Qwen3.5 model: the 6502 CPU, 2 KB RAM and cartridge ROM run inside a stock checkpoint, with the Gated DeltaNet state acting as machine memory.
   Full card: https://gitnova.dev/en/r/dbreunig/nesformer.md
4. **FlashML-org/FreeToken** — 4.4 · Breakout · Language models · Python · +116 stars measured 2026-11-01, 00:04–12:25 UTC, ≈ 216 by evening
   A Mixture-of-Experts inference engine for running frontier-scale open-weight MoE models (290B+) on consumer hardware — GPUs, CPUs, and host memory. Aimed at users who want to run frontier models locally.
   Full card: https://gitnova.dev/en/r/FlashML-org/FreeToken.md
5. **Niko1221/Strata** — 4.4 · Steady · Language models · C++ · +285 stars measured 2026-11-01, 00:03–12:25 UTC, ≈ 557 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 2026-11-01 12:34 UTC, updated every 30 minutes.