Library
86,689 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
wikipedia-cn-20230720-filtered
Datasets & benchmarksHugging Face dataset by 0xDing
0xDing/wikipedia-cn-20230720-filtered -
sql-create-context
Datasets & benchmarksHugging Face dataset by b-mc2
b-mc2/sql-create-context -
geo-doctor
SkillsGEO 医生:一句话装进 AI 助手,查清豆包、DeepSeek、ChatGPT、Claude 为什么不推荐你,改资料、写内容、再复查。开源中英双语 GEO(生成式引擎优化)skill。
git clone https://github.com/Fangx-AI/geo-doctor.git -
creator-skills
SkillsCreator agent skills for video, music, publishing and brand voice: route every AI tool into one pipeline. Install: npx skills add frankxai/creator-skills
git clone https://github.com/frankxai/creator-skills.git -
oil-studio-skill
SkillsOil Studio Agent Skill for Claude Code & Codex: native macOS screen recording, auto-zoom demos, and transcript-driven video editing (macOS 原生录屏与口播精剪 Agent Skill)
git clone https://github.com/oil-oil/oil-studio-skill.git -
mojo-dllm
AI repositoriesLocal inference for diffusion language models (LLaDA, Dream), written in Mojo
git clone https://github.com/vladimirrott/mojo-dllm.git -
rtp-llm
AI repositoriesRTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
git clone https://github.com/alibaba/rtp-llm.git -
QwQ-LongCoT-130K
Datasets & benchmarksHugging Face dataset by amphora
amphora/QwQ-LongCoT-130K -
Mixtral-8x22B-Instruct-v0.1
Modelsmodel by mistralai · vllm
mistralai/Mixtral-8x22B-Instruct-v0.1 -
repo-bootcamp
Tools & apps🏕️ Turn any GitHub repository into a Day 1 onboarding kit using the GitHub Copilot SDK. Generates 12+ markdown docs in < 60 seconds.
git clone https://github.com/Arthur742Ramos/repo-bootcamp.git -
yt-dlp Link Extractor - Any Video URL to Direct Links
-
audio-video-transcriber
MCP serversTranscribe any audio or video URL to text, SRT and VTT, with chunking and only-new episodes
-
eroq — AI video, images, voice and music
MCP serversVideos, images, voices and songs from eroq's named and uncensored engines, with your characters.
-
Errandkit Video Frames for AI
MCP serversExtract timestamped scene frames from video for AI vision, with OCR. Runs on Apify, pay per use.
-
RemixViral: AI clipper for long videos you own
MCP serversCheck RemixViral clip jobs, videos and credits, and create faceless Shorts from a prompt.
-
controlnet-sd21
Modelsmodel by thibaud · diffusers
thibaud/controlnet-sd21 -
PPT-Design-Skill
SkillsPrecision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perfect Build Mode control, AI image generation, and fully editable PPTX. 面向专业演示设计场景,帮助用户从需求分析、视觉方向选择到原生可编辑 PPTX 交付,打造高质量、可持续修改的演示文稿。
git clone https://github.com/sunchaokun/PPT-Design-Skill.git -
TemporalNet
Modelsmodel by CiaraRowles · diffusers
CiaraRowles/TemporalNet -
KinoPipe
Public APIsTyped hosted video editing operations for agents and automation
-
Rendobar
Public APIsHosted media processing over REST: transcode, caption, watermark video
-
tiny-textbooks
Datasets & benchmarksHugging Face dataset by nampdn-ai
nampdn-ai/tiny-textbooks -
awesome-ai-tools
Prompts🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026
git clone https://github.com/eudk/awesome-ai-tools.git -
ai-model-world
Datasets & benchmarksAI 大模型世界,把 556 个大模型拟人化成像素小人的可视化站点。进来就能看到此刻谁最聪明、谁最会写代码、谁最便宜、谁刚发布,往下是国内与国外分区的厂商广场、完整的发布时间线和多维排行榜。搜索认模型名、厂商和能力,输入「多模态」会直接列出全部多模态模型。数据取自 Epoch AI、models.dev、LiveBench 与 Hugging Face,每小时自动同步,所有文案由真实数据生成,不调用任何 LLM。Next.js 静态导出,零后端。
git clone https://github.com/liyupi/ai-model-world.git -
PhotoMaker
Modelstext to image model by TencentARC · diffusers
TencentARC/PhotoMaker
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.