Live tracker of new RAG implementations, tools, and patterns — updated every 15 minutes
⭐ Star this repo to bookmark — fresh data every 15 minutes
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.
⏰ Last updated: 2026-07-16 06:45 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | Bielrezende/WMB-100K | 0 | — | 2026-07-16 | Benchmark AI memory systems for situational retrieval with 4.3M tokens and 2,708 questions in real-world scenarios |
| 2 | satbirbhbc-ux/ai-coding-principles | 1 | — | 2026-07-16 | Build AI coding principles for Claude Code, with discipline rules and system design guides to improve code quality and r |
| 3 | AnalyseDeCircuit/oxideterm | 935 | Rust | 2026-07-16 | AI-native workspace for local shells and remote machines.Zero Electron, zero OpenSSL, zero telemetry, and no app subscri |
| 4 | Capricevirological936/agentic-workflow | 0 | JavaScript | 2026-07-16 | Orchestrate agentic workflows for autonomous task management, parallel agent spawning, and multi-step Backlog.md-driven |
| 5 | sabinequarterly135/Helix | 1 | Python | 2026-07-16 | Optimize LLM prompts with automated tests and genetic search to improve pass rates without breaking what already works |
| 6 | seaofokhotskquakerism746/dabench-rlm-eval | 0 | Python | 2026-07-16 | Benchmark DSPy Recursive Language Models on DABench data analysis tasks with automated scoring for iterative code-based |
| 7 | codingiswine/law11 | 0 | Python | 2026-07-16 | Domain-specific RAG chatbot for Korean industrial safety law — hybrid search (exact match + vector), cross-encoder reran |
| 8 | jeremylongshore/bobs-big-brain-plugin | 1 | JavaScript | 2026-07-16 | Bob's Big Brain — the governed team brain, as a local-first Claude Code + Cowork plugin. Turn your own files into cited |
| 9 | wolfie88/Whatsapp-chat-voice-Bot-with-Realtime-scraping | 0 | — | 2026-07-16 | Automate WhatsApp voice and chat replies with real-time scraping, lead qualification, and sales routing for faster custo |
| 10 | juninfxp/git-trend-sync | 0 | Python | 2026-07-16 | Track AI trends and sync relevant agent updates to your project with activity-based scoring and Claude Code commands |
| 11 | Unfed-parenthesisfreenotation627/cag-service | 0 | Python | 2026-07-16 | Serve Cache-Augmented Generation as a service with zero retrieval latency for bounded knowledge bases |
| 12 | Human-fairness510/mini-cc | 1 | TypeScript | 2026-07-16 | Build a local Ollama-based code assistant CLI with LangChain.js and native tool calling for reliable developer workflows |
| 13 | ayush-s-tomar/agentic-rag-research-assistant | 0 | Python | 2026-07-16 | Agentic RAG assistant — LangGraph tool-routing, Chroma retrieval, Groq inference. Grounds answers, refuses out-of-scope |
| 14 | framerslab/agentos | 596 | TypeScript | 2026-07-16 | TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers. |
| 15 | beeblastco/cheapkb | 0 | TypeScript | 2026-07-16 | Cost-effective serverless RAG knowledge base on AWS. Ingest, chunk, embed, and vector-search documents within the Free T |
| 16 | cyberlife-coder/VelesDB | 75 | Rust | 2026-07-16 | The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL |
| 17 | Ayush-2703/Large_languaage_Models | 3 | Python | 2026-07-16 | A comprehensive blueprint for Large Language Models. A rigorous curriculum covering transformer architectures, pre-train |
| 18 | ongridio/ongrid | 465 | Go | 2026-07-16 | An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, L |
| 19 | Straying-bodypad392/vemb | 2 | Python | 2026-07-16 | Embed text, images, audio, video, and PDFs from the command line with vemb, an httpie-style tool for Gemini embeddings |
| 20 | viditk9780/smart-mom-mobile-prod | 0 | TypeScript | 2026-07-16 | Record offline-first mobile meetings, upload audio chunks, and sync reliably with the Smart MoM backend |
| 21 | Tavarasu/autoresearch-adal | 0 | — | 2026-07-16 | Compare AdaL and Claude Code on Autoresearch benchmarks to find better hyperparameters, run more experiments, and conver |
| 22 | linny006/vector-db-live | 3 | Python | 2026-07-16 | Live-updating landscape of vector database projects, integrations, and benchmarks — refreshed every |
| 23 | involvex/nova-assistant | 0 | Dart | 2026-07-16 | Nova runs AI models entirely on your device - no data is sent to external servers. Get fast, private AI assistance with |
| 24 | strobilevitellus470/argus-ai | 1 | Python | 2026-07-16 | Monitor LLM app quality in production with Argus AI: scoring groundedness, accuracy, reliability, variance, cost, and sa |
| 25 | Prudencefiberscope303/emograph | 1 | Python | 2026-07-16 | Store emotional memories and personality profiles for LLMs to deliver real-time emotion detection and tailored advice |
| 26 | Asahi298/llm-circuit-finder | 1 | Python | 2026-07-16 | Find and duplicate transformer reasoning circuits to boost LLM logic without training or weight changes |
| 27 | mahdyet1845/Consultor-Tributario-AI | 0 | — | 2026-07-16 | Analise a Reforma Tributária com IA e dados da web em tempo real para responder sobre IBS, CBS, transição e impacto fisc |
| 28 | driftfishquakergun623/surf | 0 | Python | 2026-07-16 | Build self-hosted AI chat with web search, browser automation, and a web UI plus CLI for local or remote models |
| 29 | emapleural312/alipay-securityguard-analysis | 0 | C | 2026-07-16 | Analyze Alipay SecurityGuard SDK architecture, privacy, and attack surface to expose unprotected APIs and VM bypass risk |
| 30 | Sebastian3909/obsidian-web-mcp | 1 | Python | 2026-07-16 | Access and edit your Obsidian vault remotely with a secure HTTPS MCP server, OAuth 2.0, and full-text search |
| 31 | labring/fastgpt-plugin | 41 | TypeScript | 2026-07-16 | FastGPT plugin system. Provide model presets, system tools and other extended functions for FastGPT. |
| 32 | sheelaghexpensive483/mcp-local-school-orchestrator | 0 | Python | 2026-07-16 | Manage school data locally with MCP, LangGraph, and Ollama for natural language queries, PDF reports, and privacy-first |
| 33 | Emanuele-Chiummo/llm-wiki-synapse | 0 | Python | 2026-07-16 | Self-hosted AI wiki that organizes itself — LLM ingest, knowledge graph, cited chat, Obsidian-compatible vault. FastAPI |
| 34 | trenchant-rogaine315/ai-engineer-vault | 0 | — | 2026-07-16 | Build production-ready AI systems with vendor-neutral patterns for LLMs, retrieval, and agents. |
| 35 | linny006/rag-radar | 3 | Python | 2026-07-16 | Live tracker of new RAG implementations, tools, and patterns — updated every 15 minutes |
| 36 | GizClaw/flowcraft | 486 | Go | 2026-07-16 | Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a lib |
| 37 | Duoarsenic792/stock-futures-automation | 1 | — | 2026-07-16 | Automate stock and futures signal display, bridge execution, and message push setup in one Flask dashboard for live data |
| 38 | GamerBoiyzz/deepagents | 1 | Python | 2026-07-16 | Build agent apps with a batteries-included harness for tools, memory, and control flow |
| 39 | recordrnase224/brix-protocol | 1 | Python | 2026-07-16 | Build runtime reliability guards for LLM pipelines with one wrap() call and configurable protection against common produ |
| 40 | Waqar-743/RAG_Chatbot | 10 | Python | 2026-07-16 | This full-stack application implements RAG a technique that combines semantic search with LLM-powered generation to crea |
| 41 | gonzaloaquiferous551/ccma-edge-architecture | 0 | TeX | 2026-07-16 | Build edge context management for CCMA with deterministic memory, lower attention cost, and better long-horizon LLM reca |
| 42 | Andre151989/obsidian-lilbee | 0 | TypeScript | 2026-07-16 | Enhance Obsidian search by indexing deleted files to keep them visible and searchable within your vault. |
| 43 | Celestynainterchangeable406/llm-response-evaluator | 0 | Python | 2026-07-16 | Evaluate and compare LLM responses across five key quality dimensions to improve post-training feedback and analysis. |
| 44 | Fritzvaried946/NexusRAG | 0 | Python | 2026-07-16 | Enable precise document search and answer generation using vector search, knowledge graphs, and cross-encoder reranking |
| 45 | OpenSourceAGI/qwksearch-research-agent | 73 | TypeScript | 2026-07-16 | 🤖🔎 STREAM: Search with Top Result Extraction & Answer Model 📈📝 REASON Docs Writing Agent 🚜📜 Tractor the Text Extrac |
| 46 | madfam-org/tezca | 5 | Python | 2026-07-16 | Open legal intelligence for Mexico. 30,000+ laws across federal, state, and municipal sources · 3.5M+ searchable article |
| 47 | tomyimkc/sophia-agi | 5 | Python | 2026-07-16 | Wisdom before intelligence. A provenance-aware reasoning layer that abstains instead of fabricating — stops LLMs inventi |
| 48 | Uncomfortable-filagree112/OpenViking | 0 | — | 2026-07-16 | Provide a scalable context database designed to improve memory and data handling for AI agents in complex tasks. |
| 49 | Ekaterinaacid284/memory-lancedb-pro-skill | 0 | — | 2026-07-16 | Provide Claude Code with expert guidance to install, configure, and optimize memory-lancedb-pro for long-term AI memory |
| 50 | Wadsworthshabbygenteel186/SaaS-AgenticWorkflow | 0 | — | 2026-07-16 | Automate SaaS service design and development with AI agents running multi-step workflows from PRD creation to full-stack |
Every 15 minutes, a GitHub Action runs tracker.py. That script:
- Fetches the latest state from
GitHub Search API. - Diffs against
data/items.json(the previous snapshot). - Rewrites the table above between the
<!-- TRACKER_TABLE_* -->markers. - Commits
feat: +N added, -M removed (timestamp)if anything changed.
No external services. No paid APIs. Just a public data source and a free GitHub Action.
See CONTRIBUTING.md — usually you don't need to: the tracker keeps itself current.
If you spot a data-source bug or want to suggest a new column for the table, open
an issue.
If you find this useful, you might also like these other auto-updated trackers from the same maintainer — same mechanism, different upstream:
- trending-claude-skills — What's shipping in Claude Skills this week (
topic:claude-skills) - mcp-servers-live — Live index of newest MCP servers (
topic:mcp-server) - cursor-rules-live — Newest Cursor rules and .cursorrules patterns (
topic:cursor-rules) - claude-code-plugin-tracker — Claude Code plugins and hook configs (
topic:claude-code) - llm-agents-radar — Newest LLM agent frameworks (
topic:llm-agent) - llm-eval-tracker — Newest LLM evaluation tools and benchmarks (
topic:llm-eval) - agent-framework-radar — Newest agent frameworks shipping on GitHub (
topic:agent-framework) - vector-db-live — Newest vector DB projects and integrations (
topic:vector-database) - llmops-radar — Newest LLMOps tooling (observability, deployment) (
topic:llmops) - prompt-tools-live — Newest prompt-engineering tools and prompt repos (
topic:prompt-engineering) - agent-eval-harness — Live benchmark of AI coding agents (
topic:llm-eval) - skills-tracker — Tracking new GitHub 'skills' repos (
topic:agent-skills) - awesome-agent-skills — Curated auto-updated awesome-list of AI agent skills (
topic:agent-skills)
MIT — see LICENSE.