16 skills found
huang-sh / pytorch-fsdpAn open-source, model-agnostic AI workbench for scientific discovery.
Rath-Team / OpenRathAn open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
kwon416 / real-estimate-AIPython RAG LangChain + 부동산 통계 정보 open API 챗봇 프로젝트
uiuc-kang-lab / hyperparamsGuide for hyperparameter selection — learning rate formulas, LoRA rank, batch size, group size, schedules, and model-specific tuning
HaseebKhalid1507 / VelociRAGLightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
Nikunj2003 / LLaMa-MCP-StreamlitAI assistant built with Streamlit, NVIDIA NIM (LLaMa 3.3:70B) / Ollama, and Model Control Protocol (MCP).
pandazki / pneuma-skillsCo-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution.
graphlit / graphlit-mcp-serverModel Context Protocol (MCP) Server for Graphlit Platform
scraperapi / scraperapi-skillsScraperAPI's Agent Skills.
majiayu000 / llm-pipelinePydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.
remete618 / widemem-aiNext-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
PatrickJS / automl-hyperparameter-optimizationAutoML and hyperparameter optimization rules for Python ML projects using Ray Tune, Optuna, PyCaret, and time-series AutoML libraries
NPC-Worldwide / npcpyThe python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.
symgraph / BinAssistMCPBinary Ninja plugin to provide MCP functionality.
ashishps1 / learn-ai-engineeringLearn AI and LLMs from scratch using free resources
kyouyap / python- **最初に型とインターフェース（関数のシグネチャ）を考える** Python では、PEP 484 に基づく型ヒントや `typing.NewType`、`Protocol` を活用して、処理対象の型と関数のシグネチャを設計します。
