Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
math_dataset
Datasets & benchmarksHugging Face dataset by deepmind
deepmind/math_dataset -
Official DeepMind blog: Gemini & AI model releases. Be born in one call — free testnet funds.
-
Weasley DeepMind
MCP serversSecure, fragment-based long-term memory for MCP-compatible AI agents.
weasley-deepmind@1.0.0 -
code_contests
Datasets & benchmarksHugging Face dataset by deepmind
deepmind/code_contests -
deepsearchqa
Datasets & benchmarksHugging Face dataset by google
google/deepsearchqa -
LLM4AD_Next
AI repositoriesA next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use
git clone https://github.com/Optima-CityU/LLM4AD_Next.git -
concordia
Agents & frameworksA library for generative social simulation
git clone https://github.com/google-deepmind/concordia.git -
system_prompts_leaks
PromptsNew updated extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini
git clone https://github.com/zebbern/system_prompts_leaks.git -
Curated Gemini Omni prompts, API guide, and video examples — video generation, editing, camera control, style transfer, text rendering, and multi-modal workflows.
git clone https://github.com/Evolink-AI/awesome-gemini-omni-1.2-flash-API-guide-and-prompt.git -
LLM-PySC2
Agents & frameworksLLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.
git clone https://github.com/NKAI-Decision-Team/LLM-PySC2.git -
Google: Gemma 4 31B
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it -
Google: Gemma 4 31B (free)
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it:free -
Google: Gemma 4 26B A4B
ModelsGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
google/gemma-4-26b-a4b-it -
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
google/gemma-4-26b-a4b-it:free
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.