DeepSeek
Portfolio concentration
62%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
6 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (18), Unknown (8), C++ (2)
Average size
12.5K
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
62%
of the visible star count comes from this organization's top three repositories.
12.5K
stars per repository in this same snapshot.
Python
is the most common language here, with 6 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 30 repositories.
Organization pages work best when you separate portfolio breadth from flagship concentration. In DeepSeek's case, the visible top three repositories account for about 62% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (18), Unknown (8), C++ (2). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | ⭐ Stars | 🍴 Forks | Updated |
|---|---|---|---|---|---|
| 1 | deepseek-ai/DeepSeek-V3 | Python | 103.6K | 16.7K | 9 months ago |
| 2 | deepseek-ai/DeepSeek-R1 | 92K | 11.7K | 11 months ago | |
| 3 | deepseek-ai/awesome-deepseek-integration Integrate the DeepSeek API into popular software | 37.6K | 4.1K | 3 months ago | |
| 4 | deepseek-ai/DeepSeek-OCR Contexts Optical Compression | Python | 23.2K | 2.1K | 4 months ago |
| 5 | deepseek-ai/Janus Janus-Series: Unified Multimodal Understanding and Generation Models | Python | 17.7K | 2.2K | 1 years ago |
| 6 | deepseek-ai/FlashMLA FlashMLA: Efficient Multi-head Latent Attention Kernels | C++ | 12.7K | 1K | 3 weeks ago |
| 7 | deepseek-ai/3FS A high-performance distributed file system designed to address the challenges of AI training and inference workloads. | C++ | 9.9K | 1.1K | 2 weeks ago |
| 8 | deepseek-ai/DeepEP DeepEP: an efficient expert-parallel communication library | Cuda | 9.7K | 1.3K | Yesterday |
| 9 | deepseek-ai/open-infra-index Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation | 8K | 287 | 1 years ago | |
| 10 | deepseek-ai/DeepGEMM DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling | Cuda | 7.3K | 1K | 2 weeks ago |
| 11 | deepseek-ai/DeepSeek-Coder-V2 DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence | 6.8K | 1.1K | 6 months ago | |
| 12 | deepseek-ai/DeepSeek-VL2 DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding | Python | 5.3K | 1.8K | 1 years ago |
| 13 | deepseek-ai/DeepSeek-V2 DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model | 5K | 541 | 1 years ago | |
| 14 | deepseek-ai/smallpond A lightweight data processing framework built on DuckDB and 3FS. | Python | 5K | 442 | 1 years ago |
| 15 | deepseek-ai/Engram Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models | Python | 4.4K | 336 | 4 months ago |
| 16 | deepseek-ai/DeepSeek-VL DeepSeek-VL: Towards Real-World Vision-Language Understanding | Python | 4.1K | 594 | 2 years ago |
| 17 | deepseek-ai/DeepSeek-Math DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models | Python | 3.3K | 581 | 2 years ago |
| 18 | deepseek-ai/DualPipe A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training. | Python | 3K | 325 | 4 months ago |
| 19 | deepseek-ai/DeepSeek-OCR-2 Visual Causal Flow | Python | 2.9K | 252 | 3 months ago |
| 20 | deepseek-ai/awesome-deepseek-agent | 2.6K | 284 | 4 days ago | |
| 21 | deepseek-ai/DeepSeek-MoE DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models | Python | 1.9K | 309 | 2 years ago |
| 22 | deepseek-ai/DeepSeek-V3.2-Exp | Python | 1.6K | 173 | 6 months ago |
| 23 | deepseek-ai/DeepSeek-Math-V2 | Python | 1.6K | 147 | 5 months ago |
| 24 | deepseek-ai/TileKernels A kernel library written in tilelang | Python | 1.6K | 131 | 1 months ago |
| 25 | deepseek-ai/EPLB Expert Parallelism Load Balancer | Python | 1.4K | 201 | 1 years ago |
| 26 | deepseek-ai/DeepSeek-Prover-V2 | 1.3K | 100 | 10 months ago | |
| 27 | deepseek-ai/profile-data Analyze computation-communication overlap in V3/R1. | 1.2K | 147 | 1 years ago | |
| 28 | deepseek-ai/ESFT Expert Specialized Fine-Tuning | Python | 735 | 263 | 1 years ago |
| 29 | deepseek-ai/DeepSeek-Prover-V1.5 | Python | 573 | 240 | 1 years ago |
| 30 | deepseek-ai/LPLB An early research stage expert-parallel load balancer for MoE models based on linear programming. | Python | 505 | 36 | 6 months ago |
Next step after the organization read
Learn and methodology
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.