Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ds4-on-spark
Datasets & benchmarksEntrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support
git clone https://github.com/Entrpi/ds4-on-spark.git -
CountBot
SkillsLightweight open-source AI Agent optimized for Chinese users | Native support for domestic large-model coding plans | Compatible with the OpenClaw Skills ecosystem | Integrated with WeChat ClawBot, Weibo Lobster, Feishu, DingTalk, QQ, Xiaozhi AI, Telegram and dsh.
git clone https://github.com/countbot-ai/CountBot.git -
AgentPay Gate v4.0 MCP
MCP serversDrop-in x402 v2 PAYMENT-REQUIRED validator & MCP Ed25519 manifest builder ($1 USDC).
-
DeepCheck KYB v4.0 MCP
MCP serversReal-time B2B counterparty KYB, SSL, DNSSEC & DMARC/SPF trust verifier ($1 USDC).
-
RugShield AI v4.0 MCP
MCP servers42-Point On-Chain Token Honeypot, Liquidity Lock & Drainer Scanner ($1 USDC Pro).
-
mlx-serve
AI repositoriesNative LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
git clone https://github.com/ddalcu/mlx-serve.git -
deepseek-local-guide-ru
Docs & tutorials🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки
git clone https://github.com/justxor/deepseek-local-guide-ru.git -
TheDrummer: Cydonia 24B V4.1
ModelsUncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.
thedrummer/cydonia-24b-v4.1 -
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
deepseek/deepseek-v4-flash-0731 -
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
deepseek/deepseek-v4-flash -
unsloth
AI repositoriesLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
git clone https://github.com/unslothai/unsloth.git -
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
deepseek/deepseek-v4-pro -
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
deepseek/deepseek-v4-flash-0731:batch -
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
deepseek/deepseek-v4.1-flash -
Cross-Border B2B Invoice Generator, W-8BEN / EU VAT Verifier & Fraud Scanner ($1 USDC, $950 Buyout).
-
short-drama-factory
Prompts🎬 Short-Drama Factory v4.9.1 · 抖音/红果爆款短剧工业化编剧超级系统 | 一句创意/一部网文 → 标准60-100集·长档30-50集·漫剧带付费墙剧本 | v4.9 强画面支撑+15秒换挡+大白话直给+剥壳仿写 | 40赛道全图+六母型钩子+五大断章+A~I反转轮换 | 情绪契约单元链·单矛盾≤30集闭环 | 动态按需挂载矩阵(8交互模式防Context爆炸)| 机检E1~E26+S1~S8 | 纯剧本层 · Industrial hit short-drama screenplay engine (60-100 eps, paywall built-in)
git clone https://github.com/lixiaoxiao9888-create/short-drama-factory.git -
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
deepseek/deepseek-v4.1-flash:batch -
claude-skills
SkillsSkills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.
git clone https://github.com/jezweb/claude-skills.git -
ms-swift
AI repositoriesUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
git clone https://github.com/modelscope/ms-swift.git -
Magnum v4 72B
ModelsThis is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
anthracite-org/magnum-v4-72b -
claude-skills
SkillsProduction-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations
git clone https://github.com/secondsky/claude-skills.git -
zerikai_memory
MCP serversA standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP servers
git clone https://github.com/KikeVen/zerikai_memory.git -
UUID Mint
MCP serversMint a random UUID v4.
-
LoongForge
AI repositoriesA high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3 and more.
git clone https://github.com/baidu-baige/LoongForge.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.