Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
The project lists 3 contributors on GitHub.
Use Cases & Benefits
- Implements rStar2-Agent, a 14B parameter model for advanced agentic reasoning and math problem solving using reinforcement learning and tool use.
- Achieves state-of-the-art math reasoning performance with efficient training on limited GPU resources through a novel reinforcement learning algorithm and scalable infrastructure.
- Use for developing AI agents that autonomously plan, reason, and execute code to solve complex mathematical problems efficiently.
- Use for training smaller large language models to perform high-level scientific reasoning and alignment tasks with multi-stage reinforcement learning.
- Use for integrating tool-calling capabilities in AI models to enable dynamic code execution and verification in interactive problem-solving workflows.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Code of conduct: present
Watch-outs
- Warning: No commits in over a year (last push Sep 2025).
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
Authors: Ning Shang*, Yifei Liu*, Yi Zhu*, Li Lyna Zhang*†, Weijiang Xu, Xinyu Guan, Buze Zhang, Bingcheng Dong, Xudong Zhou, Bowen Zhang, Ying Xin, Ziming Miao, Scarlett Li, Fan Yang, Mao Yang†
Figure 1: rStar2-Agent-14B reaches frontier-level math reasoning in just 510 RL training step
Note: Our prior work Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers is open-sourced on the rStar-mutualreasoning b branch.
Note: Our prior work rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking is open-sourced on the rStar-math branch.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
133+1
Open issues
38+0
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| microsoft/rStar | 1.4K | — | 12 | — |
| Category median | 56.0K | +2.3K | 29 | — |
Also by microsoft
Other repositories from this maintainer that GStars tracks
- TypeScript194.4K stars
vscode
Visual Studio Code
- Python193.9K stars
markitdown
Python tool for converting files and office documents to Markdown.
- C140.1K stars
PowerToys
Microsoft PowerToys is a collection of utilities that supercharge productivity and customization on Windows
- Jupyter Notebook122.9K stars
generative-ai-for-beginners
21 Lessons, Get Started Building with Generative AI
- Go111.7K stars
TypeScript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
Discover Repositories
Search across tracked repositories by name or description