Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
-
janas
AI repositories37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
git clone https://github.com/prabanta-dev/janas.git -
mcpproxy-go
MCP serversSupercharge AI Agents, Safely
git clone https://github.com/smart-mcp-proxy/mcpproxy-go.git -
awesome-openclaw-tutorial
SkillsOpenClaw 中文教程(4500+ Star · 已出版纸质书):安装、配置、Skills、飞书接入与避坑|作者的 GPT-6 / Codex / Claude Code 新项目见 README 顶部
git clone https://github.com/xianyu110/awesome-openclaw-tutorial.git -
EXAONE-3.0-7.8B-Instruct
Modelstext generation model by LGAI-EXAONE · transformers
LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct -
ADR
MCP serversADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
git clone https://github.com/uber/ADR.git -
translategemma-12b-it
Modelsimage text to text model by google · transformers
google/translategemma-12b-it -
LightCompress
Datasets & benchmarks[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
git clone https://github.com/ModelTC/LightCompress.git -
subtitle-translator
AI repositoriesTranslate a whole season of subtitles in one pass — .srt/.ass/.vtt/.lrc, 120+ languages, 27 LLM providers, timing untouched | 整季字幕一次译完,时轴不动,支持 120+ 语言
git clone https://github.com/rockbenben/subtitle-translator.git -
labs-molt
AI repositoriesA scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
git clone https://github.com/NVIDIA-NeMo/labs-molt.git -
GLM-4.6V
Modelsimage text to text model by zai-org · transformers
zai-org/GLM-4.6V -
os
Agents & frameworksEnables organizations to create and deploy customizable AI agents with support for multiple LLM providers, real-time chat, voice, document training, analytics, user management, SSO authentication, and embeddable widgets. Built with React 19, Redux Toolkit, Radix UI, and Tailwind CSS.
git clone https://github.com/iblai/os.git -
LFM2.5-24B-A2B
Modelstext generation model by LiquidAI · transformers
LiquidAI/LFM2.5-24B-A2B -
acip
PromptsThe Advanced Cognitive Inoculation Prompt
git clone https://github.com/Dicklesworthstone/acip.git -
orla
Tools & appsAn open-source high performance execution engine for agentic workflows
git clone https://github.com/harvard-cns/orla.git -
DriveLM
Prompts[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering
git clone https://github.com/OpenDriveLab/DriveLM.git -
Qwen3.6-27B-NVFP4
Modelstext generation model by nvidia · Model Optimizer
nvidia/Qwen3.6-27B-NVFP4 -
TuyaOpen
AI repositoriesNext-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more – Fast IoT and AI Agent hardware integration
git clone https://github.com/tuya/TuyaOpen.git -
image text to text model by LuffyTheFox · hermes
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF -
OpenJudge
SkillsOpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
git clone https://github.com/agentscope-ai/OpenJudge.git -
promptdesk
PromptsPromptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).
git clone https://github.com/promptdesk/promptdesk.git -
prompt-tower
PromptsContext management for long-context LLMs, agents, and vibe coding. Instantly build context for an entire repo, selected files, folders, and GitHub issues to generate structured AI-XML context with real-time token counting.
git clone https://github.com/backnotprop/prompt-tower.git -
text generation model by IQuestLab · transformers
IQuestLab/IQuest-Coder-V1-40B-Loop-Instruct -
dsh-plugin-subscriptions
AI repositoriesUse ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys
git clone https://github.com/V1ki/dsh-plugin-subscriptions.git -
UI-TARS-1.5-7B
Modelsimage text to text model by ByteDance-Seed · transformers
ByteDance-Seed/UI-TARS-1.5-7B
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.