Get Started

Technology · Model

DeepSeek

Model · DeepSeek · Catalog tech@1

DeepSeek's family of open models.

Categories
Matched as
  • deepseek
  • deepseek v4
  • deepseek v4 flash
  • deepseek-r1

Momentum

Each signal is ranked as a percentile among the technologies that have it. A signal without enough history is not counted, and never shown as zero. How momentum works

Momentum

Collecting0 of 5 signals

No score yet. Momentum is published only when at least 2 of the 5 signals have history. DeepSeek has 0, so there is no single number: each signal is shown on its own below. It is not a zero, and nothing is estimated in its place.

Snapshot OCT 24, 2026 · Scoring tech@1

Official repository stars
No official repository
The catalog lists no official repository, so this signal does not apply.
Member repository stars
Collecting
Star growth needs repository snapshots 30 days apart.0 new members in 30 days
Package adoption
No packages of its own
No package is linked as the technology itself, so this signal does not apply.
Open models
Collecting
Download growth needs Crest’s daily observations of its official models 30 days apart.23.6M downloads in 30 days · 27 official models
News
Collecting
News counts once there are 3 events across the last 60 days; it has 0.0 in the last 30 days · 0 in the 30 before

News activity

Events · 7 days
0published events that mention it
Events · 30 days
0published events that mention it
Previous 30 days
0events in the 30 days before

Momentum history

Momentum history starts OCT 8, 2026. A chart appears once two daily snapshots carry a score; none does so far.

Repositories

Official 0

The catalog lists no official repository for DeepSeek.

Members 166repositories tagged with one of its aliases, most-starred first

  • ollama/ollama

    Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

    Tagged deepseekGo

    182K

  • huggingface/transformers

    🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

    Tagged deepseekPython

    166.9K

  • langgenius/dify

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

    Tagged deepseekTypeScript

    157.7K

  • nexu-io/open-design

    🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.

    Tagged deepseekTypeScript

    99.2K

  • vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Tagged deepseekPython

    93.1K

  • lobehub/lobehub

    🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

    Tagged deepseekTypeScript

    83K

  • unslothai/unsloth

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

    Tagged deepseekPython

    77.1K

  • hiyouga/LlamaFactory

    Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

    Tagged deepseekPython

    75.3K

  • diegosouzapw/OmniRoute

    Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors

    Tagged deepseekTypeScript

    72.3K

  • openinterpreter/openinterpreter

    A coding agent for open models like Kimi K3 and GLM 5.3

    Tagged deepseekRust

    68.5K

  • xtekky/gpt4free

    The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

    Tagged deepseekPython

    66.8K

  • CherryHQ/cherry-studio

    AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

    Tagged deepseekTypeScript

    52.3K

Packages

“Is” packages are DeepSeek itself; ecosystem packages depend on them. The two are counted separately and never added together. Adoption is each registry’s own figure, with its percentile within that registry.

Is 0the technology itself, most-adopted first

No package is linked as DeepSeek itself.

Ecosystem 0packages that depend on it, most-adopted first

No package in the catalog depends on DeepSeek’s own packages.

Models

Open models on Hugging Face. Official models are published under the prefixes the catalog declares; derivatives declare an official model as their base, and are never credited by name alone. Downloads are the Hub’s rolling 30-day count. All of them in the model list

Official 27the 12 most downloaded

Derivatives 16the 8 most downloaded; models in the catalog that declare an official model as their base

Latest news the 3 latest events that mention it

DeepSeek · Model — Crest of Tech