Die Werkzeugbeschreibungen sind auf Englisch.

RAG und Suche

Retrieval, Vektordatenbanken, Embeddings und semantische Suche.

Anwendungsfall

Aktivität

Sortieren nach

142

Werkzeug-Rangliste

Ranked by normalized popularity across sources. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    MCP
    Aktiv

    AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.

    githubgemessenes WachstumQuelle öffnen ↗

    291GitHub-Sterne+33 (+12.8 %)
  2. 2
    Aktiv

    Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add shodh-memory -- npx @shodh/memory-mcp

    276GitHub-Sternestabil
  3. 3
    Aktiv

    全流程 智能招投标 Agent:标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档,全流程 AI 自动化。

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/guangshu100/BidMaster-Pro ~/.claude/skills/BidMaster-Pro

    244GitHub-Sterne+25 (+11.4 %)
  4. 4

    MCP
    Aktiv

    A semantic search engine for files and code.

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add vexor -- uvx vexor

    239GitHub-Sternestabil
  5. 5

    Skill
    Aktiv

    Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/qdrant/skills ~/.claude/skills/skills

    230GitHub-Sterne+4 (+1.8 %)
  6. 6

    Skill
    Aktiv

    The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add yonatangross/orchestkit

    227GitHub-Sterne+3 (+1.3 %)
  7. 7
    Aktiv

    Pure instruction-pack skill wrapping Ai2's Asta MCP server (Semantic Scholar). Intent-to-tool routing, safe defaults, multi-agent.

    githubgemessenes WachstumQuelle öffnen ↗

    183GitHub-Sterne-1 (-0.54 %)
  8. 8
    Aktiv

    USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with…

    githubgemessenes WachstumQuelle öffnen ↗

    178GitHub-Sterne+2 (+1.1 %)
  9. 9
    Aktiv

    Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.

    githubgemessenes WachstumQuelle öffnen ↗

    173GitHub-Sterne+8 (+4.8 %)
  10. 10

    Sonstige
    Aktiv

    Deploy intelligence. Open-source infrastructure for AI agents in production.

    githubgemessenes WachstumQuelle öffnen ↗

    169GitHub-Sterne-7 (-4.0 %)
  11. 11

    Skill
    Aktiv

    🤖 Curated AI OSINT resources — Google dorks, Shodan queries, GitHub dorks, and techniques to discover exposed LLM endpoints, leaked AI API keys, misconfigured vector databases, and unprotected AI agents

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/7WaySecurity/ai_osint ~/.claude/skills/ai_osint

    161GitHub-Sterne+7 (+4.5 %)
  12. 12

    Sonstige
    Aktiv

    剧本分镜工具智能体(PenShot):电影/动漫/短剧/小说/剧本→分镜→片段→prompt | 基于 LangGraph+LLM,自动解析任意格式剧本,生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致,支持 MCP/REST API/函数调用 | Python库 + A2A集成。(LLM-powered screenplay-to-video-prompt agent. Break scripts into…

    githubgemessenes WachstumQuelle öffnen ↗

    160GitHub-Sterne+7 (+4.6 %)
  13. 13
    Aktiv

    Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/hwfengcs/DM-Code-Agent ~/.claude/skills/DM-Code-Agent

    151GitHub-Sternestabil
  14. 14

    Agent
    Aktiv

    Ruby's capable AI runtime

    githubgemessenes WachstumQuelle öffnen ↗

    139GitHub-Sterne+2 (+1.5 %)
  15. 15
    Aktiv

    Context Engineering: Build Consistent, Accurate, Predictable AI Systems

    githubgemessenes WachstumQuelle öffnen ↗

    136GitHub-Sterne+5 (+3.8 %)
  16. 16

    Skill
    Aktiv

    A self-hosted knowledge platform for humans and AI agents — publish wikis, blogs, and portable Agent Skills.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Ciao1019/Petrichor ~/.claude/skills/Petrichor

    127GitHub-Sterne+1 (+0.79 %)
  17. 17

    Skill
    Aktiv

    Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge galaxies.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/NimaChu/my-wiki ~/.claude/skills/my-wiki

    123GitHub-Sternestabil
  18. 18

    Skill
    Aktiv

    Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under…

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/docmancer/docmancer ~/.claude/skills/docmancer

    123GitHub-Sterne+1 (+0.82 %)
  19. 19
    Aktiv

    Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients

    mcpgemessenes WachstumQuelle öffnen ↗

    Remote-Server, in der MCP-Konfiguration anzugeben https://mcp.apple-rag.com

    117GitHub-Sterne+1 (+0.86 %)
  20. 20
    Aktiv

    Self improving agents through iterations

    githubgemessenes WachstumQuelle öffnen ↗

    105GitHub-Sterne+1 (+0.96 %)
  21. 21
    Aktiv

    Pay-per-use IBM Granite AI via x402: chat, code, embeddings, forecasting. USDC on Base or Solana.

    mcpgemessenes WachstumQuelle öffnen ↗

    Remote-Server, in der MCP-Konfiguration anzugeben https://three.ws/api/ibm-mcp

    105GitHub-Sternestabil
  22. 22
    Aktiv

    Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add alibaba-cloud -- npx @three-ws/alibaba-cloud-mcp

    105GitHub-Sternestabil
  23. 23
    Aktiv

    IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add ibm-watsonx -- npx @three-ws/ibm-watsonx-mcp

    105GitHub-Sternestabil

Lern- und Referenzressourcen

Ranked by normalized popularity across sources. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

  1. 1
    AktivQuelle öffnen ↗

    Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically

    github

    Installieren git clone https://github.com/OmidZamani/dspy-skills ~/.claude/skills/dspy-skills

    Ressourcegemessenes Wachstum
    122GitHub-Sterne+1 (+0.83 %)
  2. 2
    AktivQuelle öffnen ↗

    AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI

    github

    Installieren git clone https://github.com/malevrigns/atlas-agent-control-plane ~/.claude/skills/atlas-agent-control-plane

    Ressourcegemessenes Wachstum
    110GitHub-Sterne+44 (+66.7 %)