DeepSeek
@deepseek-ai • Open source projects from deepseek-ai. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
72%
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 (7), C++ (2)
Average size
18.3K
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-08-21(5d ago)GitHub API fallback30 repositories
72%
of the visible star count comes from this organization's top three repositories.
18.3K
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.
Balanced portfolio across 30 reposTop 3 share 72%
Organization pages work best when you separate portfolio breadth from flagship concentration. In DeepSeek's case, the visible top three repositories account for about 72% 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 (7), 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 |
|---|---|---|---|
| 1 | deepseek-ai/deepseek-harness DeepSeek Harness: Everything is a Plugin. | TypeScript | 197.4K |
| 2 | deepseek-ai/DeepSeek-V3 | Python | 104.4K |
| 3 | deepseek-ai/DeepSeek-R1 | 92K | |
| 4 | deepseek-ai/DeepSeek-OCR Contexts Optical Compression | Python | 23.9K |
| 5 | deepseek-ai/Janus Janus-Series: Unified Multimodal Understanding and Generation Models | Python | 17.8K |
| 6 | deepseek-ai/FlashMLA FlashMLA: Efficient Multi-head Latent Attention Kernels | C++ | 12.9K |
| 7 | deepseek-ai/3FS A high-performance distributed file system designed to address the challenges of AI training and inference workloads. | C++ | 10.2K |
| 8 | deepseek-ai/DeepEP DeepEP: an efficient expert-parallel communication library | Cuda | 10.1K |
| 9 | deepseek-ai/open-infra-index Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation | 8.1K | |
| 10 | deepseek-ai/DeepGEMM DeepGEMM: clean and efficient BLAS kernel library on GPU | Cuda | 7.7K |
| 11 | deepseek-ai/DeepSpec DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms | Python | 7K |
| 12 | deepseek-ai/DeepSeek-Coder-V2 DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence | 7K | |
| 13 | deepseek-ai/awesome-deepseek-agent | 6K | |
| 14 | deepseek-ai/DeepSeek-VL2 DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding | Python | 5.4K |
| 15 | deepseek-ai/DeepSeek-V2 DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model | 5K | |
| 16 | deepseek-ai/smallpond A lightweight data processing framework built on DuckDB and 3FS. | Python | 5K |
| 17 | deepseek-ai/Engram Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models | Python | 4.6K |
| 18 | deepseek-ai/DeepSeek-VL DeepSeek-VL: Towards Real-World Vision-Language Understanding | Python | 4.2K |
| 19 | deepseek-ai/DeepSeek-Math DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models | Python | 3.4K |
| 20 | deepseek-ai/DeepSeek-OCR-2 Visual Causal Flow | Python | 3.4K |
| 21 | deepseek-ai/DualPipe A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training. | Python | 3K |
| 22 | deepseek-ai/TileKernels A kernel library written in tilelang | Python | 1.7K |
| 23 | deepseek-ai/DeepSeek-V3.2-Exp | Python | 1.6K |
| 24 | deepseek-ai/DeepSeek-Math-V2 | Python | 1.6K |
| 25 | deepseek-ai/EPLB Expert Parallelism Load Balancer | Python | 1.4K |
| 26 | deepseek-ai/DeepSeek-Prover-V2 | 1.3K | |
| 27 | deepseek-ai/profile-data Analyze computation-communication overlap in V3/R1. | 1.2K | |
| 28 | deepseek-ai/ESFT Expert Specialized Fine-Tuning | Python | 746 |
| 29 | deepseek-ai/DeepSeek-Prover-V1.5 | Python | 584 |
| 30 | deepseek-ai/LPLB An early research stage expert-parallel load balancer for MoE models based on linear programming. | Python | 530 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
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.