Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
MegaMath
Datasets & benchmarksHugging Face dataset by IFM
IFM/MegaMath -
ICLR2025-Papers-with-Code
Agents & frameworks历年ICLR论文和开源项目合集,包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
git clone https://github.com/yinizhilian/ICLR2025-Papers-with-Code.git -
image text to text model by ukisai · gguf
ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF -
rapidfireai
AI repositoriesRapidFire AI: Rapid AI Customization from RAG to Fine-Tuning
git clone https://github.com/RapidFireAI/rapidfireai.git -
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 -
lora-dataset-studio
AI repositoriesFree local LoRA training studio: build character, style and concept datasets from one photo or a big image folder, caption them (JoyCaption, prose or booru tags), train LoRAs with ai-toolkit for Krea 2, FLUX.1, FLUX.2 Klein, Qwen-Image 2.1, Z-Image, SDXL and Anima, then compare checkpoints side by side. ComfyUI-powered, self-hosted.
git clone https://github.com/perfectgf/lora-dataset-studio.git -
deepresearch-agent
Agents & frameworks一个生产级的深度研究 Agent 系统,从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力,配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。
git clone https://github.com/qiqihezh/deepresearch-agent.git -
UltraData-RL-2609
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraData-RL-2609 -
CaPtain
Agents & frameworksCaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters
git clone https://github.com/waltstephen/CaPtain.git -
wildjailbreak
Datasets & benchmarksHugging Face dataset by allenai
allenai/wildjailbreak -
nixtla
AI repositoriesTimeGPT-2.1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
git clone https://github.com/Nixtla/nixtla.git -
higgsfield
AI repositoriesFault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters
git clone https://github.com/higgsfield-ai/higgsfield.git -
skills
SkillsAgent skills for Ultralytics YOLO, covering models, datasets, training, tuning, inference, tracking, and export.
git clone https://github.com/ultralytics/skills.git -
Erotic_Literature_Collection
Datasets & benchmarksHugging Face dataset by ystemsrx
ystemsrx/Erotic_Literature_Collection -
nefes-0.5
Modelstext to speech model by alicangunduz · nefes
alicangunduz/nefes-0.5 -
Training-360
MCP serversRead your company's Training-360 trainings, results, certificates and follow-up. Company admins.
-
SWE-ZERO-12M-trajectories
Datasets & benchmarksHugging Face dataset by AlienKevin
AlienKevin/SWE-ZERO-12M-trajectories -
Strava Training MCP
MCP serversConnect Strava training data to Claude for training load analysis and activity insights
strava-training-mcp@0.3.2 -
synthetic-healthcare-admissions
Datasets & benchmarksHugging Face dataset by strova-ai
strova-ai/synthetic-healthcare-admissions -
UltraData-SFT-2605
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraData-SFT-2605 -
Traintrackr
MCP serversGB (National Rail) train times: live departures, platforms, timetables and journey planning.
-
image text to text model by huihui-ai · transformers
huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-v2-GGUF -
Trainerfu by Cotlet
MCP serversTrainerfu's coaching work connects training plans, activity and client conversations.
-
Trainer Connect
MCP serversManage students, workouts, appointments and payments through your personal trainer account.
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.