Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 26 of 26
topogpt3
Complex-valued spectral language model for code with Grassmannian training diagnostics and hierarchical recursive reasoning inference.
langchain-hugging-bay
Hugging Bay model discovery tools and retriever for LangChain.
raglu
Pure Rational GLU (RaGLU) and RaLU activations for PyTorch, Triton CUDA and Apple MLX.
tokencraft-gpt
An educational GPT language model implemented from scratch with PyTorch.
More in Agent frameworks & infrastructure
Agent frameworks & SDKs12,596Multi-agent orchestration6,185Observability & evaluation5,667Agent memory & context4,032LLM gateways & API proxies4,018Awesome lists & learning resources3,621Chat UIs & LLM clients2,986Agent sandboxes & runtimes1,721Local LLM runtimes1,401Prompt engineering & prompt libraries913Model serving & inference775