検索拡張生成（RAG）に関連する測定済みカタログ項目です。
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 with citations & branded HTML reports. 13 commands, no Node runtime.
スター30実測 · 2026/10/19
モメンタム19.67 日 · 実測 · +3.45% 相対変化
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
スター121実測 · 2026/10/19
モメンタム19.17 日 · 実測 · +1.68% 相対変化
🤖 The strongest curated list of open-source AI-agent tools for literature review — 70+ tools across 11 categories (Claude Code skills, deep research, MCP servers, PDF parsing, systematic review). 面向智能体文献综述的最强工具大全。
スター35実測 · 2026/10/18
モメンタム18.67 日 · 実測 · +2.94% 相対変化
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.
スター386実測 · 2026/10/19
モメンタム18.47 日 · 実測 · +0.78% 相対変化
Deploy intelligence. Open-source infrastructure for AI agents in production.
スター191実測 · 2026/10/19
モメンタム16.97 日 · 実測 · +1.06% 相対変化
Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity
スター193実測 · 2026/10/19
モメンタム16.87 日 · 実測 · +1.05% 相対変化
⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.
スター50実測 · 2026/10/19
モメンタム16.37 日 · 実測 · +2.04% 相対変化
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 tools. MCP · ACP · A2A. One Rust binary.
スター65実測 · 2026/10/19
モメンタム14.87 日 · 実測 · +1.56% 相対変化
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 with 600x lower cost.
スター67実測 · 2026/10/19
モメンタム14.77 日 · 実測 · +1.52% 相対変化
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 verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.
スター373実測 · 2026/10/19
モメンタム14.37 日 · 実測 · +0.54% 相対変化