Library
86,671 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
multimodal-image-retrieval
Prompts多模态检索实战:意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。
git clone https://github.com/liangjianshu/multimodal-image-retrieval.git -
ken
MCP serversFast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.
git clone https://github.com/townsendmerino/ken.git -
snapref-v2a-pre2
Modelstext to image model by 0ppxnhximxr · diffusers
0ppxnhximxr/snapref-v2a-pre2 -
MOSS-Image-pose-control-lora
Modelsimage to image model by thedeoxen · diffusers
thedeoxen/MOSS-Image-pose-control-lora -
image to image model by gribbliest · diffusers
gribbliest/qwen-image-2.1-qma-camera-angles -
image text to text model by DavidAU
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF -
Pika-H3-Flex-Turbo-LoRA
Modelsimage to video model by akhaliq · minimax-h3
akhaliq/Pika-H3-Flex-Turbo-LoRA -
model by lightx2v · minimax-h3
lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA -
text generation model by Kujira · gguf
Kujira/Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUF -
mneme
AI repositoriesThe memory that dreams — long-term memory for AI agents. Readable files on your own machine, consolidated between sessions. Runs as a DeepSeek Harness plugin or over MCP.
git clone https://github.com/slow-stack/mneme.git -
gcf
MCP serversThe AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1 Stable.
git clone https://github.com/blackwell-systems/gcf.git -
ronykit
MCP serversAPI Framework supporting REST and RPC.
git clone https://github.com/clubpay/ronykit.git -
tutor-mcp
MCP serversAn open-source MCP server that turns any LLM into an Intelligent Tutoring System. 50 years of cognitive science, MIT licensed.
git clone https://github.com/ArnaudGuiovanna/tutor-mcp.git -
pydantic-deepagents
Agents & frameworksOpen-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
git clone https://github.com/vstorm-co/pydantic-deepagents.git -
VideoJev-4B
Modelsfeature extraction model by ZhuYuhan · transformers
ZhuYuhan/VideoJev-4B -
Sentiment-Analysis-7B
Modelstext generation model by microsoft · transformers
microsoft/Sentiment-Analysis-7B -
sift-mcp
MCP serversValhuntir SIFT platform — MCP servers, gateway, Examiner Portal
git clone https://github.com/AppliedIR/sift-mcp.git -
studio-live-window-capture
MCP serversRoblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch
git clone https://github.com/tbee6061-ctrl/studio-live-window-capture.git -
marm-memory
AI repositoriesLocal-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.
git clone https://github.com/Lyellr88/marm-memory.git -
d1-3B-GGUF
Modelsimage text to text model by LiquidAI · gguf
LiquidAI/d1-3B-GGUF -
Ditto
Datasets & benchmarksA self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".
git clone https://github.com/OFA-Sys/Ditto.git -
Qwen-Image-2.1-Turbo-GGUF
Modelstext to image model by Abiray
Abiray/Qwen-Image-2.1-Turbo-GGUF -
promptbench
PromptsA unified evaluation framework for large language models
git clone https://github.com/microsoftarchive/promptbench.git -
Inkling-2-Small-GGUF
Modelsimage text to text model by unsloth
unsloth/Inkling-2-Small-GGUF
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.