Retrieval-augmented generation (RAG)

Measured catalogue entries associated with Retrieval-augmented generation (RAG).

397 measured catalogue entriesSnapshot measured Oct 19, 2026Sort: Momentum

Refine this view

Measured resources

Page 8 of 40

  1. antigravity-plugin-cc

    SkillActive

    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.

    Source
    GitHub
    Language
    Python
    Last activity
    Oct 11, 2026

    Stars30Measured · Oct 19, 2026

    Momentum19.67 days · Measured · +3.45% relative change

  2. llm-wiki-plugin

    SkillActive

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

    Source
    GitHub
    Language
    TypeScript
    Last activity
    Sep 13, 2026

    Stars121Measured · Oct 19, 2026

    Momentum19.17 days · Measured · +1.68% relative change

  3. lit-review-agent-tools

    MCP serverActive

    🤖 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。

    Source
    GitHub
    Language
    Python
    Last activity
    Oct 12, 2026

    Stars35Measured · Oct 18, 2026

    Momentum18.67 days · Measured · +2.94% relative change

  4. EDDI

    MCP serverActive

    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.

    Source
    GitHub
    Language
    Java
    Last activity
    Oct 19, 2026

    Stars386Measured · Oct 19, 2026

    Momentum18.47 days · Measured · +0.78% relative change

  5. muxi

    OtherActive

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

    Source
    GitHub
    Last activity
    Sep 28, 2026

    Stars191Measured · Oct 19, 2026

    Momentum16.97 days · Measured · +1.06% relative change

  6. trace-mcp

    MCP serverActive

    Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity

    Source
    GitHub
    Language
    TypeScript
    Last activity
    Oct 19, 2026

    Stars193Measured · Oct 19, 2026

    Momentum16.87 days · Measured · +1.05% relative change

  7. token-reducer

    SkillDormant

    ⚡ 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.

    Source
    GitHub
    Language
    Python
    Last activity
    May 2, 2026

    Stars50Measured · Oct 19, 2026

    Momentum16.37 days · Measured · +2.04% relative change

  8. zeph

    OtherActive

    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.

    Source
    GitHub
    Language
    Rust
    Last activity
    Oct 18, 2026

    Stars65Measured · Oct 19, 2026

    Momentum14.87 days · Measured · +1.56% relative change

  9. claude-mem-lite

    MCP serverActive

    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.

    Source
    GitHub
    Language
    JavaScript
    Last activity
    Oct 17, 2026

    Stars67Measured · Oct 19, 2026

    Momentum14.77 days · Measured · +1.52% relative change

  10. deepdive

    SkillActive

    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.

    Source
    GitHub
    Language
    Python
    Last activity
    Oct 18, 2026

    Stars373Measured · Oct 19, 2026

    Momentum14.37 days · Measured · +0.54% relative change