Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Efficient-LLMs-Survey
AI repositories[TMLR 2024] Efficient Large Language Models: A Survey
git clone https://github.com/AIoT-MLSys-Lab/Efficient-LLMs-Survey.git -
EconomicIndex
Datasets & benchmarksHugging Face dataset by Anthropic
Anthropic/EconomicIndex -
DeepSeek-OCR
Modelsimage text to text model by deepseek-ai · transformers
deepseek-ai/DeepSeek-OCR -
tiny-llm
AI repositorieslearn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
git clone https://github.com/skyzh/tiny-llm.git -
objaverse
Datasets & benchmarksHugging Face dataset by allenai
allenai/objaverse -
heretic
AI repositoriesTraining-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
git clone https://github.com/p-e-w/heretic.git -
LMOps
AI repositoriesGeneral technology for enabling AI capabilities w/ LLMs and MLLMs
git clone https://github.com/microsoft/LMOps.git -
grace
PromptsA prompt engineering functional programming language
git clone https://github.com/Gabriella439/grace.git -
WikiChat
AI repositoriesWikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
git clone https://github.com/stanford-oval/WikiChat.git -
spacy-llm
Prompts🦙 Integrating LLMs into structured NLP pipelines
git clone https://github.com/explosion/spacy-llm.git -
star-vector
AI repositoriesStarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.
git clone https://github.com/joanrod/star-vector.git -
LightMem
AI repositories[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
git clone https://github.com/zjunlp/LightMem.git -
page-agent
Agents & frameworksJavaScript in-page GUI agent. Control web interfaces with natural language.
git clone https://github.com/alibaba/page-agent.git -
Liquid
AI repositories(Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators
git clone https://github.com/FoundationVision/Liquid.git -
mergekit
AI repositoriesTools for merging pretrained large language models.
git clone https://github.com/arcee-ai/mergekit.git -
VideoRAG
AI repositories[KDD'2026] "VideoRAG: Chat with Your Videos"
git clone https://github.com/HKUDS/VideoRAG.git -
awesome-social-media-skills
Skills自媒体运营 Skill(技能包)精选:小红书、抖音、公众号、视频号、B 站、X、YouTube、TikTok、LinkedIn 的选题、写稿、配图、发布和数据,千问、豆包、龙虾 OpenClaw、WorkBuddy、Claude Code、Codex 等智能体可用 | Curated agent skills for social media: Xiaohongshu (RedNote), Douyin, WeChat, X, YouTube, TikTok and LinkedIn
git clone https://github.com/UnderleveledBuilder/awesome-social-media-skills.git -
picollm
AI repositoriesOn-device LLM Inference Powered by X-Bit Quantization
git clone https://github.com/Picovoice/picollm.git -
ShareGPT-Chinese-English-90k
Datasets & benchmarksHugging Face dataset by shareAI
shareAI/ShareGPT-Chinese-English-90k -
awesome-japanese-nlp-resources
AI repositoriesA curated list of resources for Japanese natural language processing (NLP): Python libraries, LLMs, dictionaries, corpora, and datasets. Includes Claude Code and Codex skills to search resources.
git clone https://github.com/taishi-i/awesome-japanese-nlp-resources.git -
pump-fun-sdk
MCP serversTypeScript SDK, pump CLI and MCP server for the Pump protocol on Solana: bonding curves, AMM pools and creator fees.
git clone https://github.com/nirholas/pump-fun-sdk.git -
SkyPile-150B
Datasets & benchmarksHugging Face dataset by Skywork
Skywork/SkyPile-150B -
R2R
AI repositoriesSoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
git clone https://github.com/SciPhi-AI/R2R.git -
OpenO1-SFT
Datasets & benchmarksHugging Face dataset by O1-OPEN
O1-OPEN/OpenO1-SFT
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.