Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
pplx-decider-v1-27b
Modelstext classification model by perplexity-ai · pytorch
perplexity-ai/pplx-decider-v1-27b -
pixai-tagger-v1.0
Modelsimage classification model by pixai-labs · transformers
pixai-labs/pixai-tagger-v1.0 -
wanderlog-mcp
MCP serversMCP server for Wanderlog — build and edit trip itineraries through conversation
git clone https://github.com/shaikhspeare/wanderlog-mcp.git -
MemT-1.0-Flash
Modelstext generation model by MemTensor · transformers
MemTensor/MemT-1.0-Flash -
Gamma-World
Agents & frameworksImplementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
git clone https://github.com/nv-tlabs/Gamma-World.git -
jev
AI repositoriesjevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.
git clone https://github.com/feder-cr/jev.git -
apple-docs-mcp
MCP serversMCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objective-C APIs & code examples in Claude, Cursor & AI assistants
git clone https://github.com/kimsungwhee/apple-docs-mcp.git -
image text to text model by alesha-pro · gguf
alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF -
kanzo
MCP serversSelf-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero setup.
git clone https://github.com/emanuele-em/kanzo.git -
Qwen3.8-27B-Ridge-GGUF
Modelsimage text to text model by empero-ai · gguf
empero-ai/Qwen3.8-27B-Ridge-GGUF -
WorldSeed
Agents & frameworksMore is Different. A multi-agent world engine where AI agents live, talk, compete, ally.
git clone https://github.com/AIScientists-Dev/WorldSeed.git -
cc-haha
AI repositories本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5.
git clone https://github.com/NanmiCoder/cc-haha.git -
Xing4.0-29B-Intent
Modelstext generation model by XingChen-AGI · transformers
XingChen-AGI/Xing4.0-29B-Intent -
Cotal
SkillsThe open standard for agent coordination
git clone https://github.com/Cotal-AI/Cotal.git -
cli
MCP serversOfficial Model Studio CLI(阿里云百炼 CLI)built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
git clone https://github.com/modelstudioai/cli.git -
flux-3-image-klein-base
Modelsimage to image model by black-forest-labs · diffusers
black-forest-labs/flux-3-image-klein-base -
amos-1-large
Modelsmodel by mukaddamzaid
mukaddamzaid/amos-1-large -
fable-method
SkillsThe Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
git clone https://github.com/Sahir619/fable-method.git -
agent-router
Tools & appsCLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr
git clone https://github.com/nidhi-singh02/agent-router.git -
LFM3-Audio-2B
Modelsany to any model by LiquidAI · transformers
LiquidAI/LFM3-Audio-2B -
EnterpriseRAG-Bench
AI repositoriesDataset and benchmark for RAG on company internal documents.
git clone https://github.com/onyx-dot-app/EnterpriseRAG-Bench.git -
image text to text model by peculiar-ragdoll · gguf
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP -
Nex-N2.6
Modelsimage text to text model by nex-agi · transformers
nex-agi/Nex-N2.6 -
openharness
MCP serversThe ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
git clone https://github.com/autonomous-ai/openharness.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.