19 skills found
huang-sh / pytorch-fsdpAn open-source, model-agnostic AI workbench for scientific discovery.
remete618 / widemem-aiNext-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
liwala / shealself-healing and self-learning loop for coding agents
majiayu000 / llm-pipelinePydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.
vllm-project / semantic-routerA programmable Mixture-of-Models router for heterogeneous LLM inference
LycheeMem / LycheeMemLightweight Long-Term Memory for LLM Agents.
carloluisito / mindkeg-mcpA persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings so agents retain knowledge across sessions.
airmcp-com / mcp-standardsSelf-learning AI standards system - learns from corrections and auto-updates CLAUDE.md
patakuti / local-knowledge-rag-mcpA semantic search and retrieval system for local documents using vector embeddings. Powered by MCP (Model Context Protocol).
itayinbarr / little-coderA harness optimized to smaller LLMs
ashishps1 / learn-ai-engineeringLearn AI and LLMs from scratch using free resources
Dimokat / Antigravity_Optimizer_MCPA local RAG-powered Model Context Protocol (MCP) server using Qdrant and FastEmbed to help AI coding agents navigate, understand, and optimize large codebases.
keshrath / agent-knowledgeCross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
HaseebKhalid1507 / VelociRAGLightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
NeuralBlitz / climate-science-based-validationAlternative to OpenClaw with OpenClaw Support 👍
MatthewZMD / aidermacsAI Pair Programming in Emacs with Aider
datawhalechina / easy-vibe💻 The first course for AI-native product builders.
78 / xiaozhi-esp32An MCP-based chatbot | 一个基于MCP的聊天机器人
ncmonx / icemageToken-efficient context engine for AI coding agents. v2.21.0: brain+token trio — session-aware recall delta, contradiction sentinel, adaptive recall depth. 2416 tests, 42 MCP tools, Elastic-2.0.
