Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
| Date | Stars |
|---|---|
| 2026-07-24 | 6890 |
| 2026-07-25 | 6893 |
| 2026-07-28 | 6893 |
| 2026-07-30 | 6893 |
| 2026-07-31 | 6895 |
| 2026-08-06 | 6895 |
Today
— stars today
This week
+2 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.03%/day
# Awesome LLM Strawberry (OpenAI o1) [](https://github.com/sindresorhus/awesome)   [](https://github.com/hijkzzz/Awesome-LLM-Strawberry/blob/main/LICENSE) This is a collection of research papers & blogs for **OpenAI Strawberry(o1) and Reasoning**. And the repository will be continuously updated to track the frontier of LLM Reasoning. ## OpenAI Docs - [https://platform.openai.com/docs/guides/reasoning](https://platform.openai.com/docs/guides/reasoning) - <img src="https://github.com/user-attachments/assets/b165cb20-9202-4951-8783-6b2f7e0d6071" width="600px"> ## News - [OpenAI] [Introducing deep research](https://openai.com/index/introducing-deep-research/) - [OpenAI] [o3 preview & o3 mini](https://openai.com/12-days/) - [OpenAI] [Introducing ChatGPT Pro](https://openai.com/index/introducing-chatgpt-pro/) - [Google DeepMind] [Gemini 2.0 Flash Thinking](https://x.com/JeffDean/status/1869789813232341267) - [Ilya Sutskever] [AI with reasoning power will be less predictable](https://www.reuters.com/technology/artificial-intelligence/ai-with-reasoning-power-will-be-less-predictable-ilya-sutskever-says-2024-12-14/) - [SemianAlysis] [Scaling Laws – O1 Pro Architecture, Reasoning Training Infrastructure, Orion and Claude 3.5 Opus “Failures” ](https://semianalysis.com/2024/12/11/scaling-laws-o1-pro-architecture-reasoning-training-infrastructure-orion-and-claude-3-5-opus-failures/) - [DeepSeek] [DeepSeek-R1-Lite-Preview is now live: unleashing supercharged reasoning power!](https://api-docs.deepseek.com/news/news1120) - [Moonshoot] [数学对标o1系列，搜索再次进化，Kimi 新推理模型与你一起拓展智能边界](https://mp.weixin.qq.com/s/g4DltigncX-4sfaQ6Qn1zA) - [Moonshoot] [Kimi 发布视觉思考模型 k1，多项理科测试行业领先](https://mp.weixin.qq.com/s/8cip3dehL8OIfZSnbZ1ftQ) - [InternLM] [强推理模型书生InternThinker开放体验：自主生成高智力密度数据、具备元动作思考能力](https://mp.weixin.qq.com/s/l7fdHlETvhKgZmUl23EiRA) - [新智元] [万字独家爆光，首揭o1 pro架构！惊人反转，Claude 3.5 Opus没失败？](https://mp.weixin.qq.com/s/LozJEE1sAAYAOrEFDVb6mg) ## Blogs - [OpenAI] [Learning to Reason with LLMs](https://openai.com/index/learning-to-reason-with-llms/) - [OpenAI] [OpenAI o1-mini Advancing cost-efficient reasoning](https://openai.com/index/openai-o1-mini-advancing-cost-efficient-reasoning) - [OpenAI] [Finding GPT-4’s mistakes with GPT-4](https://openai.com/index/finding-gpt4s-mistakes-with-gpt-4/) - [ARC-AGI] [OpenAI o3 Breakthrough High Score on ARC-AGI-Pub](https://arcprize.org/blog/oai-o3-pub-breakthrough) - [Anthropic] [Building effective agents](https://www.anthropic.com/research/building-effective-agents) - [hijkzzz] [Stabilizing MoE RL Without Router Replay: The Online IcePop Solution](https://hijkzzz.notion.site/online-ice-pop) - [hijkzzz] [REINFORCE++-baseline is all you need in RLVR](https://medium.com/@janhu9527/reinforce-baseline-is-all-you-need-in-rlvr-f5406930aa85) - [hijkzzz] [Exploring OpenAI O1 Model Replication](https://hijkzzz.notion.site/exploring-openai-o1-model-replication?pvs=74) - [Nathan Lambert] [OpenAI’s Strawberry, LM self-talk, inference scaling laws, and spending more on inference](https://www.interconnects.ai/p/openai-strawberry-and-inference-scaling-laws) - [Nathan Lambert] [Reverse engineering OpenAI’s o1](https://www.interconnects.ai/p/reverse-engineering-openai-o1) - [Andreas Stuhlmüller, jungofthewon] [Supervise Process, not Outcomes](https://www.alignmentforum.org/posts/pYcFPMBtQveAjcSfH/supervise-process-not-outcomes) - [Nouha Dziri] [Have o1 Models Cracked Human Reasoning?](https://substack.com/home/post/p-148782195) - [Rishabh Agarwal] [Improving LLM Reasoning using Self-generated data: RL and Verifiers](https://rosanneliu.com/dlctfs/
Excerpt of 44,973 characters
Read on GitHub
274
25
Chen-Hao (Leo) Chang · @Tencent-Hunyuan, @OpenDILab, @vision-x-nyu, HUST · United States
6
3
2
2
ChiYeung Law · Salesforce Research · Singapore
1
1
Naoto Usuyama · Microsoft Research · United States
1
1
1
Hill Zhang · Bytedance · China
1
1
1
1
Fabian Henning · Germany
1
1
1
Fei Yu · CUHKSZ
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8fd61083f95241c8, topic:llm
matched fp:8fd61083f95241c8, topic:reinforcement-learning