Die Werkzeugbeschreibungen sind auf Englisch.

RAG und Suche

Retrieval, Vektordatenbanken, Embeddings und semantische Suche.

Anwendungsfall

Aktivität

Sortieren nach

142

Werkzeug-Rangliste

Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    Skill
    Aktiv

    SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

    PythonLizenz: MIT
    • agent-memory
    • agent-skills
    • agentic-ai
    • benchmark
    • llm-based-agents

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/oneal2000/SR-Agents ~/.claude/skills/SR-Agents

    102GitHub-Sterne+1 (+0.99 %)
  2. 2

    Agent
    Aktiv

    Data-Agent：从 0 到 1 构建 Text2SQL 智能体实战教程，覆盖 StateGraph 编排、双重 RAG、关系图谱、HITL 人工确认、SQL 自动纠错、Python Docker 沙盒执行与 A2A + SSE 流式交互。

    Kotlin
    • a2a
    • ai-agent
    • human-in-the-loop
    • rag
    • stategraph

    githubgemessenes WachstumQuelle öffnen ↗

    100GitHub-Sterne-1 (-0.99 %)
  3. 3

    Skill
    Aktiv

    Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters,…

    Python
    • agent-use-ready
    • ai-agents
    • claude-code
    • claude-skills
    • doc-converter

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/agentii-ai/DocMeld ~/.claude/skills/DocMeld

    100GitHub-Sternestabil
  4. 4

    Skill
    Aktiv

    Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.

    TypeScriptLizenz: MIT
    • ai-tools
    • claude-code-plugin
    • claude-code-skill
    • codex-skill
    • cursor

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add praneybehl/llm-wiki-plugin

    99GitHub-Sterne+5 (+5.3 %)
  5. 5

    Agent
    Aktiv

    🚀 Way Back Home

    PythonLizenz: Apache-2.0
    • a2a
    • adk
    • agents
    • bigquery
    • google-cloud

    githubgemessenes WachstumQuelle öffnen ↗

    96GitHub-Sternestabil
  6. 6

    Skill
    Aktiv

    Distill any document corpus into a navigable skill hierarchy for LLM agents — no retrieval system needed at serve time.

    PythonLizenz: MIT
    • agent-skills
    • emnlp-2026
    • enterprise-search
    • llm
    • llm-agents

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/dukesun99/Corpus2Skill ~/.claude/skills/Corpus2Skill

    84GitHub-Sterne+1 (+1.2 %)
  7. 7

    Skill
    Aktiv

    Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer,…

    PythonLizenz: MIT
    • agentic-ai
    • ai-agents
    • claude
    • claude-code
    • claude-skills

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/alfadur7/llm-wiki-newsroom ~/.claude/skills/llm-wiki-newsroom

    81GitHub-Sterne+1 (+1.2 %)
  8. 8

    MCP
    Aktiv

    AST knowledge graph MCP server for Claude Code — semantic search, call graph traversal, HTTP route tracing, impact analysis. Auto-indexes 10 languages via Tree-sitter.

    RustLizenz: MIT
    • ast
    • call-graph
    • claude-code
    • claude-code-plugin
    • code-navigation

    githubgemessenes WachstumQuelle öffnen ↗

    72GitHub-Sterne+2 (+2.9 %)
  9. 9

    MCP
    Aktiv

    Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks.…

    PythonLizenz: MIT
    • agent-memory-system
    • agent-skills
    • causal-inference
    • claude-code
    • codex

    githubgemessenes WachstumQuelle öffnen ↗

    71GitHub-Sternestabil
  10. 10

    Skill
    Aktiv

    The official Pinecone marketplace for Claude Code Plugins

    PythonLizenz: MIT
    • anthropic-claude
    • claude-code
    • claude-code-plugin
    • claude-code-plugin-marketplace
    • hybrid-search

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add pinecone-io/pinecone-claude-code-plugin

    68GitHub-Sternestabil
  11. 11

    Skill
    Aktiv

    Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.

    PythonLizenz: MIT
    • academic
    • agent-skill
    • agent-skills
    • citations
    • claude-code

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Agents365-ai/semanticscholar-skill ~/.claude/skills/semanticscholar-skill

    68GitHub-Sternestabil
  12. 12

    MCP
    Aktiv

    Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL visualization. LongMemEval R@5=97.45%. Self-hosted, Ollama-optional

    PythonLizenz: MIT
    • ai-memory
    • ai-tools
    • anthropic
    • chromadb
    • claude-code

    githubgemessenes WachstumQuelle öffnen ↗

    67GitHub-Sterne+1 (+1.5 %)
  13. 13

    MCP
    Aktiv

    Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 55 tools, no cloud.

    RustLizenz: MIT

      mcpgemessenes WachstumQuelle öffnen ↗

      67GitHub-Sternestabil
    • 14

      MCP
      Aktiv

      Token-efficient code review knowledge graph: semantic search and call-graph resolution.

      PythonLizenz: Apache-2.0

        mcpgemessenes WachstumQuelle öffnen ↗

        Installieren claude mcp add better-code-review-graph -- uvx better-code-review-graph

        66GitHub-Sternestabil
      • 15

        MCP
        Aktiv

        RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet),…

        JavaScript
        • agentdb
        • ai-agents
        • anthropic-claude
        • claude-code
        • claude-code-plugin

        githubgemessenes WachstumQuelle öffnen ↗

        65GitHub-Sterne+1 (+1.6 %)
      • 16

        Skill
        Aktiv

        Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants

        Lizenz: MIT
        • ade
        • agent-skills
        • claude
        • document-extraction
        • document-processing

        githubgemessenes WachstumQuelle öffnen ↗

        Installieren git clone https://github.com/landing-ai/ade-document-processing-skills ~/.claude/skills/ade-document-processing-skills

        64GitHub-Sternestabil
      • 17

        MCP
        Aktiv

        Semantic search and pattern discovery for Obsidian and markdown vaults.

        TypeScript

          mcpgemessenes WachstumQuelle öffnen ↗

          59GitHub-Sternestabil
        • 18

          Agent
          Aktiv

          专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。

          Python
          • agentic-ai
          • claim-chart
          • claude-code
          • claude-code-skill
          • codex

          githubgemessenes WachstumQuelle öffnen ↗

          59GitHub-Sterne+2 (+3.5 %)
        • 19

          Sonstige
          Aktiv

          A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed…

          RustLizenz: MIT
          • a2a
          • acp
          • ai-agent
          • claude
          • cli

          githubgemessenes WachstumQuelle öffnen ↗

          58GitHub-Sterne+1 (+1.8 %)
        • 20

          MCP
          Aktiv

          Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.

          TypeScriptLizenz: Apache-2.0
          • agent-skills
          • ai-memory
          • ai-tools
          • claude-code
          • codex

          githubgemessenes WachstumQuelle öffnen ↗

          58GitHub-Sterne+3 (+5.5 %)
        • 21

          MCP
          Aktiv

          Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem…

          JavaScriptLizenz: MIT
          • agent-memory
          • ai-coding-assistant
          • ai-memory
          • anthropic
          • claude

          githubgemessenes WachstumQuelle öffnen ↗

          57GitHub-Sterne+3 (+5.6 %)
        • 22

          Skill
          Aktiv

          Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with…

          PythonLizenz: MIT
          • agent-memory
          • agent-skills
          • agentic-workflow
          • agents
          • anthropic

          githubgemessenes WachstumQuelle öffnen ↗

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

          55GitHub-Sternestabil
        • 23

          MCP
          Aktiv

          Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.

          TypeScriptLizenz: MIT

            mcpgemessenes WachstumQuelle öffnen ↗

            Installieren claude mcp add smart-connections-mcp -- npx smart-connections-mcp

            54GitHub-Sternestabil
          • 24

            Skill
            Aktiv

            A LangGraph-powered multi-agent deep research system featuring task planning, human-in-the-loop review, multi-source retrieval, evidence-grounded report generation, full tracing and reproducible evaluation.

            PythonLizenz: MIT
            • agent
            • agent-skills
            • agentic-workflow
            • langgraph
            • llm

            githubgemessenes WachstumQuelle öffnen ↗

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

            50GitHub-Sternestabil

          Lern- und Referenzressourcen

          Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

          1. 1

            membrane

            Skill
            AktivQuelle öffnen ↗

            A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

            GoLizenz: MIT
            • agent
            • agent-framework
            • agent-memory
            • agent-skills
            • agentic
            github

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

            Ressourcegemessenes Wachstum
            94GitHub-Sternestabil