Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
pydantic-ai
Agents & frameworksHow Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
git clone https://github.com/pydantic/pydantic-ai.git -
automatic speech recognition model by pyannote · pyannote-audio
pyannote/speaker-diarization-community-1 -
Upsonic
MCP serversBuild autonomous AI agents in Python.
git clone https://github.com/Upsonic/Upsonic.git -
notebooks
Modelsmodel by agents-course
agents-course/notebooks -
HY-Embodied-0.5
Modelsimage text to text model by tencent · transformers
tencent/HY-Embodied-0.5 -
neutts-air
Modelstext to speech model by neuphonic
neuphonic/neutts-air -
DeepSeek-V3-Base
Modelsmodel by deepseek-ai
deepseek-ai/DeepSeek-V3-Base -
metaflow
AI repositoriesBuild, Manage and Deploy AI/ML Systems
git clone https://github.com/Netflix/metaflow.git -
Qianfan-OCR
Modelsimage text to text model by baidu · transformers
baidu/Qianfan-OCR -
GLM-5.3-CYBERSECURITY-FP8
Modelstext generation model by dealignai
dealignai/GLM-5.3-CYBERSECURITY-FP8 -
Kolibri-1
Modelstext generation model by Aleph-Alpha · transformers
Aleph-Alpha/Kolibri-1 -
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 -
wikipedia
Datasets & benchmarksHugging Face dataset by wikimedia
wikimedia/wikipedia -
claude-mem
SkillsPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
git clone https://github.com/thedotmack/claude-mem.git -
animatediff
Modelsmodel by guoyww
guoyww/animatediff -
ReplaceAnything
Tools & appsHugging Face space by modelscope
modelscope/ReplaceAnything -
ell
PromptsA language model programming library.
git clone https://github.com/MadcowD/ell.git -
agentops
AI repositoriesPython SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
git clone https://github.com/AgentOps-AI/agentops.git -
Qwen3-Omni-30B-A3B-Instruct
Modelsany to any model by Qwen · transformers
Qwen/Qwen3-Omni-30B-A3B-Instruct -
image text to text model by ISTA-DASLab · gguf
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF -
nightingale
MCP serversOpen-source, self-hosted alerting for metrics, logs, and databases. Includes a built-in AI agent and MCP server.
git clone https://github.com/ccfos/nightingale.git -
image feature extraction model by facebook · transformers
facebook/dinov3-vitl16-pretrain-lvd1689m -
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 -
cursor-talk-to-figma-mcp
MCP serversTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
git clone https://github.com/grab/cursor-talk-to-figma-mcp.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.