에이전트 및 멀티 에이전트
anthropics/claude-cookbooks
Anthropic’s collection of Claude development examples covers classification, summarization, retrieval augmentation, tool use, image understanding, and evaluation. It is suitable for learning from specific tasks and adapting the code.
★ 52.6K⑂ 6.3KJupyter Notebook
MITQ92
RAG 및 지식 시스템
labring/FastGPT
A visual knowledge-workflow platform with document ingestion, hybrid retrieval, reranking, and application publishing.
★ 29.6K⑂ 7.3KTypeScript
라이선스가 감지되지 않음Q90
RAG 및 지식 시스템
onyx-dot-app/onyx
A self-hostable team AI platform combining knowledge connectors, retrieval, agents, and research workflows.
★ 32K⑂ 4.4KPython
라이선스가 감지되지 않음Q90
RAG 및 지식 시스템
microsoft/graphrag
A graph-based text indexing and question-answering research project, now largely in maintenance mode.
★ 35.9K⑂ 3.8KPython
MITQ90
RAG 및 지식 시스템
siyuan-note/siyuan
A knowledge workspace emphasizing local data, privacy and human–AI collaboration.
★ 46.2K⑂ 3KTypeScript
AGPL-3.0Q85
RAG 및 지식 시스템
pathwaycom/llm-app
Application templates for RAG, search and AI pipelines using live data sources.
★ 58.9K⑂ 1.5KJupyter Notebook
MITQ90
AI 코딩 및 개발자 도구
DietrichGebert/ponytail
Reusable guidance that encourages coding agents to simplify implementations and avoid unnecessary code.
★ 126.8K⑂ 6.8KJavaScript
MITQ90
AI Applications & Automation
open-webui/open-webui
A self-hosted AI chat interface supporting Ollama and OpenAI-compatible APIs.
★ 151K⑂ 22.1KPython
라이선스가 감지되지 않음Q85
에이전트 및 멀티 에이전트
NVIDIA/skills
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
★ 2.7K⑂ 304Python
Apache-2.0Q98
데이터 엔지니어링 및 파이프라인
NVIDIA/aistore
AIStore: scalable storage for AI applications
★ 1.9K⑂ 277Go
MITQ94
MCP 및 도구 호출
langgenius/dify
Dify is an LLM application development platform for visually building workflows, RAG pipelines, and tool-using agents. It combines model management, prompt development, observability, and application APIs in a collaborative workspace that can be used as a hosted service or self-hosted.
★ 151.2K⑂ 23.9KTypeScript
NOASSERTIONQ98
RAG 및 지식 시스템
milvus-io/milvus
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
★ 45.7K⑂ 4.2KGo
Apache-2.0Q98