MCP servers and skills: search, filter by where they run, and compare.
Unified LLM alignment suite orchestrating DPO & LoRA runs (Llama-Factory style)
SkillLink only★ 8
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
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
SkillMIT★ 1Few starsNo key
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedu
OfficialSkillApache-2.0★ 11k in collectionNo key
Experimental local-first memory-policy research for Codex and Claude Code, with delayed feedback and gated adapter learning.
PythonMIT★ 8No key
An MCP server for dataset generation, fine-tuning, RL, and evaluation of LLMs — directly from your coding agent.
PythonMIT★ 16No key
Distill a large LLM into a small open-weights model: generate questions, collect reasoning answers, fine-tune with Axolotl on your GPU or Runpod.
SkillApache-2.0★ 2Few starsNo key
Production-grade RLHF & post-training pipeline built from first principles in PyTorch. Features causal transformers, LoRA SFT, Bradley-Terry reward modeling, DPO, IPO, PPO with GAE, DeepSeek-R1 style
MCPLink only★ 5
Local-first opportunity engine that uses Gemma, Unsloth LoRA for shadow training, private memory, offline mobile, and proof tracking to turn effort into proof.
MCPLink only★ 1Few stars
Who stands behind it
