Le descrizioni degli strumenti sono in inglese.

RAG e ricerca

Recupero, database vettoriali, embedding e ricerca semantica.

Utilizzo

Attività

Ordina per

142

Classifica degli strumenti

Ranked by normalized popularity across sources. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1

    MCP
    Attivo

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

    ↓ 73 download/settimanaJavaScriptLicenza: Apache-2.0

      mcpcrescita misurataApri fonte ↗

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

      105stelle GitHubstabile
    • 2

      MCP
      Attivo

      x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.

      ↓ 70 download/settimanaJavaScriptLicenza: Apache-2.0

        mcpcrescita misurataApri fonte ↗

        Installa claude mcp add ibm-x402-mcp -- npx @three-ws/ibm-x402-mcp

        105stelle GitHubstabile
      • 3

        MCP
        Attivo

        Self improving agents through iterations

        PythonLicenza: Apache-2.0
        • agent-learning
        • agent-memory
        • agentic-workflows
        • ai-agents
        • claude-code

        githubcrescita misurataApri fonte ↗

        104stelle GitHubstabile
      • 4

        Skill
        Attivo

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

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

        githubcrescita misurataApri fonte ↗

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

        102stelle GitHub+1 (+0.99 %)
      • 5

        Agente
        Attivo

        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

        githubcrescita misurataApri fonte ↗

        100stelle GitHub-1 (-0.99 %)
      • 6

        Skill
        Attivo

        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

        githubcrescita misurataApri fonte ↗

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

        100stelle GitHubstabile
      • 7

        Skill
        Attivo

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

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

        githubcrescita misurataApri fonte ↗

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

        99stelle GitHub+5 (+5.3 %)
      • 8

        Agente
        Attivo

        🚀 Way Back Home

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

        githubcrescita misurataApri fonte ↗

        96stelle GitHubstabile
      • 9

        Skill
        Attivo

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

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

        githubcrescita misurataApri fonte ↗

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

        84stelle GitHub+1 (+1.2 %)
      • 10

        Skill
        Attivo

        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,…

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

        githubcrescita misurataApri fonte ↗

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

        81stelle GitHub+1 (+1.2 %)
      • 11

        MCP
        Attivo

        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.

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

        githubcrescita misurataApri fonte ↗

        72stelle GitHub+2 (+2.9 %)
      • 12

        MCP
        Attivo

        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.…

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

        githubcrescita misurataApri fonte ↗

        71stelle GitHubstabile
      • 13

        Skill
        Attivo

        The official Pinecone marketplace for Claude Code Plugins

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

        githubcrescita misurataApri fonte ↗

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

        68stelle GitHubstabile
      • 14

        Skill
        Attivo

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

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

        githubcrescita misurataApri fonte ↗

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

        68stelle GitHubstabile
      • 15

        MCP
        Attivo

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

        RustLicenza: MIT

          mcpcrescita misurataApri fonte ↗

          67stelle GitHubstabile
        • 16

          MCP
          Attivo

          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

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

          githubcrescita misurataApri fonte ↗

          67stelle GitHub+1 (+1.5 %)
        • 17

          MCP
          Attivo

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

          PythonLicenza: Apache-2.0

            mcpcrescita misurataApri fonte ↗

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

            66stelle GitHubstabile
          • 18

            MCP
            Attivo

            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

            githubcrescita misurataApri fonte ↗

            65stelle GitHub+1 (+1.6 %)
          • 19

            Skill
            Attivo

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

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

            githubcrescita misurataApri fonte ↗

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

            64stelle GitHubstabile
          • 20

            MCP
            Attivo

            Semantic search and pattern discovery for Obsidian and markdown vaults.

            TypeScript

              mcpcrescita misurataApri fonte ↗

              59stelle GitHubstabile
            • 21

              Agente
              Attivo

              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

              githubcrescita misurataApri fonte ↗

              59stelle GitHub+2 (+3.5 %)
            • 22

              Altro
              Attivo

              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…

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

              githubcrescita misurataApri fonte ↗

              58stelle GitHub+1 (+1.8 %)
            • 23

              MCP
              Attivo

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

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

              githubcrescita misurataApri fonte ↗

              58stelle GitHub+3 (+5.5 %)
            • 24

              MCP
              Attivo

              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…

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

              githubcrescita misurataApri fonte ↗

              57stelle GitHub+3 (+5.6 %)

            Risorse didattiche e di riferimento

            Ranked by normalized popularity across sources. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

            1. 1

              membrane

              Skill
              AttivoApri fonte ↗

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

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

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

              Risorsacrescita misurata
              94stelle GitHubstabile