Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
open-genai
AI repositoriesデジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。
git clone https://github.com/hirokawaguchi/open-genai.git -
semantic-router
AI repositoriesAn open, programmable decision layer for models and compute.
git clone https://github.com/vllm-project/semantic-router.git -
sparrow
AI repositoriesStructured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
git clone https://github.com/katanaml/sparrow.git -
dramaclaw
AI repositoriesA general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product videos, otome games, and more. | 通用 AIGC 视频引擎 —— 从剧本到成片一条流水线,漫剧、广告、电商、乙游皆可
git clone https://github.com/dramaclaw/dramaclaw.git -
FunClip
AI repositoriesFunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
git clone https://github.com/modelscope/FunClip.git -
stickman-video-director
AI repositoriesTurn any script into viral, multi-style animated stickman videos for Faceless YouTube Channels. Automate visuals, voiceover, captions & SFX. 100% Free & Open-Source.
git clone https://github.com/kaomei/stickman-video-director.git -
vllm-ascend
AI repositoriesCommunity maintained hardware plugin for vLLM on Huawei Ascend
git clone https://github.com/vllm-project/vllm-ascend.git -
MeshAnything
AI repositories[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
git clone https://github.com/buaacyw/MeshAnything.git -
SwanLab
AI repositories⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultralytics / MMEngine / Keras etc.
git clone https://github.com/SwanHubX/SwanLab.git -
MindSearch
AI repositories🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
git clone https://github.com/InternLM/MindSearch.git -
beat-ai
AI repositories不玩晦涩不搞少数派的 AI 入门圣经,从学生到工程师都能轻松掌握。涵盖神经网络到大模型、顶层设计到微观原理、工程实现到算法基础。 学完后,大家能彻底看懂为什么下一 token 预测这个看似不起眼的能力可以改变世界,也能发现原来 AI 并没有想象中那么神秘、那么高不可攀。 Let's just beat it !
git clone https://github.com/origin-brain/beat-ai.git -
PaddleNLP
AI repositoriesEasy-to-use and powerful LLM and SLM library with awesome model zoo.
git clone https://github.com/PaddlePaddle/PaddleNLP.git -
LLM-RL-Visualized
AI repositories🌟100+ 原创 LLM / RL 原理图📚,《大模型算法》作者巨献!💥(100+ LLM/RL Algorithm Maps )
git clone https://github.com/changyeyu/LLM-RL-Visualized.git -
engine
AI repositories2bit quants, kernels and runtime for consumer devices.
git clone https://github.com/cactus-compute/engine.git -
vox-director
AI repositoriesTurn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
git clone https://github.com/Alisa0808/vox-director.git -
Toonflow-app
AI repositories短剧、漫剧制作工具 Toonflow:开源 AI 视频创作平台,集成剧本创作、智能分镜、角色与场景资产管理、图像生成和视频生成。融合无限画布、AI Agent 与可视化工作流,支持本地部署、自选模型、跨平台客户端、MCP 与插件扩展。Open-source AI short drama and motion comic creation tool with an infinite canvas, AI agents, storyboarding, image and video generation. Self-hosted and extensible, with a canvas-based approach similar to LibTV and TapNow.
git clone https://github.com/HBAI-Ltd/Toonflow-app.git -
txtai
AI repositories💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
git clone https://github.com/neuml/txtai.git -
video-search-and-summarization
AI repositoriesNVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git -
Soup
AI repositoriesFine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
git clone https://github.com/MakazhanAlpamys/Soup.git -
llm-beginner
AI repositories《大模型与智能体》电子书与 6 个编程任务:Transformer、mini-GPT、SFT/DPO、RAG、工具调用与编程智能体。
git clone https://github.com/nndl/llm-beginner.git -
DocsGPT
AI repositoriesPrivate AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
git clone https://github.com/arc53/DocsGPT.git -
superduper
AI repositoriesSuperduper: End-to-end framework for building custom AI applications and agents.
git clone https://github.com/superduper-io/superduper.git -
mlx-vlm
AI repositoriesMLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
git clone https://github.com/Neywa-Labs/mlx-vlm.git -
SparkVSR
AI repositories[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
git clone https://github.com/taco-group/SparkVSR.git
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.