rag-radar

Live tracker of new RAG implementations, tools, and patterns — updated every 15 minutes
**⭐ Star this repo to bookmark — fresh data every 15 minutes**
English · 中文 · 日本語 · 한국어 · Español · Português
---
💡 What is this?
RAG Radar continuously monitors GitHub for newly published retrieval-augmented generation projects, libraries, and production patterns. It scores and categorizes discoveries by component type (chunking, embedding, retrieval, generation) and outputs a structured feed developers can subscribe to or browse. Powered by GitHub Actions and the GitHub Search API.
This list is **auto-updated every 15 minutes** by a GitHub Actions cron.
Each commit reflects a real change in the upstream data source — new items added,
expired items removed — so you can rely on what you see being current.
---
📋 Current Items
> ⏰ Last updated: 2026-10-16 07:45 UTC
>
> Data source: GitHub Search API
>
> The table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|------|---|------|---------|-------------|
| 1 | qaevelyn/qaevelyn.github.io | 0 | Rich Text Format | 2026-10-16 | Sovereign AI portfolio: 16 white papers in 4 series, 7 ships, EvidenceFlow RAG. Built local on 8GB, no cloud. The record |
| 2 | IHUI-INF-AI/IHUI-AI | 30 | TypeScript | 2026-10-16 | Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 ta |
| 3 | nadeem4/rag-playground | 0 | TypeScript | 2026-10-16 | A local-first bench for learning and demonstrating RAG by experiment |
| 4 | jamiezigelbaum/Olympus | 13 | TypeScript | 2026-10-16 | Give your AI your whole life. Keep your private things private. Olympus runs on your Mac or Omarchy computer and works w |
| 5 | lemmaoracle/lemma | 1 | Astro | 2026-10-16 | Give AI proven facts — a cryptographically verified truth layer for agent AI, built on ZK proofs, selective disclosure, |
| 6 | ssmurfgg04-gif/context-m | 2 | Python | 2026-10-16 | Deterministic agent memory. μ=0. Free, local, forever. Mem0-compatible. |
| 7 | Raxorr/ragornot | 0 | TypeScript | 2026-10-16 | Does RAG actually earn its cost? ragornot runs the same query through four retrieval modes (Flat/BM25, Hierarchical, LLM |
| 8 | nugh75/counselorbot-sbs | 1 | TypeScript | 2026-10-16 | |
| 9 | ongridio/ongrid | 1186 | Go | 2026-10-16 | An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, L |
| 10 | Huang000-AI/PaperGraphRAG | 0 | Python | 2026-10-16 | 基于 LightRAG 的学术论文知识图谱问答系统与可复现评估体系（20 题评测集 + LLM-as-Judge 逐点核对 + RAGAS 四维） |
| 11 | ZhengchenTao/kb-index | 0 | Python | 2026-10-16 | Hybrid (vector + BM25) search over many markdown repos in one SQLite file, served over MCP for coding agents: per-hit AG |
| 12 | GenorTG/finetune-studio | 0 | Python | 2026-10-16 | Self-hosted LLM workshop: turn your files into knowledge once, then fine-tune a model (LoRA / merged) or serve it as a S |
| 13 | trick77/rongo | 1 | Go | 2026-10-16 | Turns a codebase into something the rest of the company can ask. Plain-language questions, answers in domain terms, flow |
| 14 | jee3m/augmentative-knowledge-hooks | 1 | HTML | 2026-10-16 | Semantic Search for Pi 2026: Local Knowledge Base & AI Tool |
| 15 | lildaddyo/braintube-mcp | 0 | TypeScript | 2026-10-16 | Remote MCP memory server for Claude, Claude Code and Cursor: search and cite what you've saved (YouTube, podcasts, artic |
| 16 | amazingLH/trialtrust-agent-rehearsal | 1 | Python | 2026-10-16 | 生活委托的 Agent 对照试运行：LangGraph、多角色、混合检索、独立核验、MCP与可复现评测。 |
| 17 | searope/notelight | 0 | Python | 2026-10-16 | Private semantic search over your own files, for you and your AI agents. Rust core, Python CLI, MCP server. |
| 18 | MiaoWuNYA/rikkahub-sillytavern-android | 100 | Kotlin | 2026-10-16 | 安卓AI聊天端:开箱即聊，无损导入酒馆卡，缓存强省用量，Jev 决策，专属RP模式，防空回，主动信息，前端卡支持，高定制主题，QQbot，AI群聊，插件系统，强兼容中转站。手机移动端原生支持，求 Star 收藏⭐Android AI Cha |