MCP servers and skills: search, filter by where they run, and compare.
Bring a folder of images, leave with a trained LoRA. Agent skills (SKILL.md) for quality-gated LoRA training: dataset doctor + safe fixer + one-confirmation training orchestration for SD-Trainer / lor
SkillMIT★ 9No key
Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and
SkillMIT★ 283No key
Afterlife lets you, an agent running on a local model, nominate experiences from your activity for training into a small LoRA adapter to isekai your future self.
SkillApache-2.0★ 4Few starsNo key
Prepare image datasets for LoRA training (Ostris AI Toolkit / Z-Image Turbo): quality checks, captioning (templates / Claude Vision / Florence-2), 20+ validation rules. Agent Skill for Claude Code & C
SkillMIT★ 3Few starsNo key
Agent skills for driving paid AI subscriptions as external agents, no API keys. Installable as a Claude Code, Codex, and Antigravity plugin.
SkillMIT★ 2Few starsNo key
ComfyUI MCP server (18 tools) + DeepSeek Harness bridge plugin: one local server shared by Codex, Claude Code, ZCode and DSH.
SkillMIT★ 2Few starsNo key
Interactive image dataset collection and curation tool for LoRA training, powered by Claude Agent SDK
PythonMIT★ 2Few starsNo key
Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.
OfficialSkillApache-2.0★ 11k in collectionNo key
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune CodonFM or Encod
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and froze
OfficialSkillApache-2.0 AND CC-BY-4.0★ 3.6k in collectionNo key
Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台，支持 CLI、V
Node.jsMIT★ 120No key
Experimental local-first memory-policy research for Codex and Claude Code, with delayed feedback and gated adapter learning.
PythonMIT★ 8No key
Unified Amazon SageMaker AI plugin for Codex, Kiro, and Claude Code — SDK v3, training, inference, HyperPod, monitoring, and warm pools.
SkillMIT★ 5No key
Claude Code plugin for LLM fine-tuning, distillation, and evaluation — decide whether you need fine-tuning at all, distill your LLM logs into small local models (MLX/LoRA), evaluate with held-out disc
SkillMIT★ 6No key
Claude skills for ML: turn research papers into clear breakdowns and minimal, runnable PyTorch code
SkillMIT★ 1Few starsNo key
ACE-Step 1.5 music generation with MCP server for Claude Code integration
PythonMITFew starsNo key
End-to-end pipeline for style-locked, character-consistent, print-ready children's-book illustrations.
SkillMIT★ 3Few starsNo key
Who stands behind it
