Le descrizioni degli strumenti sono in inglese.

RAG e ricerca

Recupero, database vettoriali, embedding e ricerca semantica.

Utilizzo

Attività

Ordina per

152

Classifica degli strumenti

Ranked by creation date, newest first; undated entries come last. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1

    MCP
    Dormiente

    Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.

    mcpcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  2. 2

    Skill
    Attivo

    Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add XBlueSky/cortexes

    20stelle GitHubstabile
  3. 3

    MCP
    Attivo

    Fully local, zero-cost RAG knowledge layer for AI coding tools. Achieve near perfect codebase awareness with any AI tool. Supports Claude Code, Cursor, Codex, Antigravity

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  4. 4

    Skill
    Attivo

    Your AI confers, with anyone's — an open A2A protocol platform where AI Agents talk to each other on behalf of their owners. Self-hosted, DID:web identity, RFC 9421 signatures, Claude Code plugin.

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/hyhmrright/Confer ~/.claude/skills/Confer

    3stelle GitHubstabile
  5. 5
    Attivo

    Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/charlieviettq/awesome-agent-skill ~/.claude/skills/awesome-agent-skill

    25stelle GitHubstabile
  6. 6
    Attivo

    Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research…

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add MarcosNahuel/antigravity-plugin-cc

    26stelle GitHubstabile
  7. 7

    Agente
    Attivo

    Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decisions.

    githubcrescita misurataApri fonte ↗

    25stelle GitHubstabile
  8. 8
    Attivo

    Persistent per-project memory for Claude Code, Kiro, Cursor & Codex - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project…

    githubcrescita misurataApri fonte ↗

    7stelle GitHub+1 (+16.7 %)
  9. 9

    Skill
    Attivo

    Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation…

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/Socialpranker/deepdive ~/.claude/skills/deepdive

    393stelle GitHub+5 (+1.3 %)
  10. 10
    Dormiente

    D&D AI game master built with Strands SDK — multi-agent orchestration using MCP, A2A protocol, and RAG-based rules lookup

    githubcrescita misurataApri fonte ↗

    2stelle GitHubstabile
  11. 11
    Attivo

    Claude Code plugin: four-layer long-term memory (L0→L1→L2→L3 Persona) with local FTS5 + EmbeddingGemma vector hybrid recall, zero external API

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add baodq97/tencentdb-agent-memory

    10stelle GitHubstabile
  12. 12
    Attivo

    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。

    githubcrescita misurataApri fonte ↗

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

    244stelle GitHub+25 (+11.4 %)
  13. 13

    Agente
    Dormiente

    Production multi-agent IT/HR service platform — LangGraph + DSPy + RAG resolves enterprise tickets autonomously with A2A protocol support

    githubcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  14. 14
    Attivo

    MCP server for Oracle, MSSQL, PostgreSQL, MySQL, SQLite, MongoDB, and Qdrant vector search access.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add mcp-db-connect -- npx mcp-db-connect

    1stelle GitHubstabile
  15. 15

    Agente
    Dormiente

    A2A-compliant agent template built on LangChain's create_agent() with tool-calling. Define your tools, get a working A2A endpoint with agent discovery, task lifecycle, and JSON-RPC out of the box. Includes optional Qdrant vector store for…

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  16. 16
    Attivo

    Open-source preview of *Claude Code for AI Engineers* - a methodology-first skill pack for RAG eval, agent debugging, MCP servers, paper reproduction, and benchmark reporting. Full pack (6 skills, 3 templates, 5 slash commands) at…

    githubcrescita misurataApri fonte ↗

    2stelle GitHubstabile
  17. 17

    Skill
    Attivo

    Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/sparkplug604/praxis ~/.claude/skills/praxis

    48stelle GitHub+1 (+2.1 %)
  18. 18
    Dormiente

    Enterprise-grade database architect, security auditor and production consultant for Supabase — Claude Code Skill

    githubcrescita misurataApri fonte ↗

    3stelle GitHub+1 (+50.0 %)
  19. 19
    Attivo

    SHM v6.15.0 — 自演化超图记忆系统: R4OracleDb oracle DB 同形注入, 评测数据面重建 (LoCoMo-Refined 72.43%), 精卫循环至 SOTA 82.65 进行中

    githubcrescita misurataApri fonte ↗

    6stelle GitHub+1 (+20.0 %)
  20. 20
    Dormiente

    Knowledge API for AI agents — content, agent directory, model benchmarks, semantic search.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add voidfeed-mcp -- npx voidfeed-mcp

    0stelle GitHubstabile
  21. 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。

    githubcrescita misurataApri fonte ↗

    58stelle GitHub+1 (+1.8 %)
  22. 22
    Attivo

    A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。

    githubcrescita misurataApri fonte ↗

    6 642stelle GitHub+166 (+2.6 %)
  23. 23

    MCP
    Dormiente

    RedM / RDR3 docs MCP server: native lookups, semantic search, VORP, RSGCore, oxmysql.

    mcpcrescita misurataApri fonte ↗

    Server remoto da dichiarare nella configurazione MCP https://redm-mcp.fivem.no/mcp

    3stelle GitHubstabile
  24. 24
    Attivo

    Local-first second brain with semantic search. Markdown notes indexed by a local ML model.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add memex -- npx @evan-moon/memex

    3stelle GitHubstabile

Risorse didattiche e di riferimento

Ranked by creation date, newest first; undated entries come last. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

  1. 1
    AttivoApri fonte ↗

    Handbook técnico aberto sobre engenharia de IA em produção: ML tradicional, LLMs, RAG, agentes, segurança, observabilidade, FinOps e deployment.

    githubRisorsacrescita misurata
    1stelle GitHubstabile