Retrieval-Augmented Generation

Multimodal RAG Production

It show how to use Bedrock Data Automation for RAG.

It shows how to use s3 vector for generative AI application.

Native PDF library for DeepSeek Harness Web: bounded evidence retrieval, page images and source citation highlighting.

It shows how to use wiki for the data source of agent.

Recap everything the web says about a topic — keyless multi-backend web search into a citation-checked, tiered Markdown + HTML report, in five modes (topic/bug/research/learn/startup), plus an agentic deep-research tier (decompose, merge, adversarially verify). The web-facing sibling of ultradoc. A skills.sh agent skill.

Personal-memory RAG for an AI coding agent: BM25 + bge vectors + file-level RRF, CLI/MCP dual outlets, 18-query golden eval (18/18, MRR .880)

Framework-aware code intelligence MCP server for Claude Code and Codex — 70.5% fewer input tokens to review a pull request, median over 60 merged PRs in repos we don't own, comprehension at parity. 81 languages, 87 frameworks. Your code and index never leave the machine; an anonymous usage ping is on by default and opt-out.

Answer ultra-precise questions — and generate grounded, citation-checked reference docs — about any open-source project from its real source code, issues, PRs, docs and the web. Grounded retrieval, not the model's memory. A skills.sh agent skill + zero-dependency CLI.

A RAG-powered LLM hallucination detection & context verification engine that grounds model outputs against verified knowledge bases with confidence scoring and evidence provenance.

A highly customizable personal AI assistant for Discord featuring smart agentic AI features such as memory, personas, tool usage, and more! ｜ 長期記憶やペルソナ、ツール連携を完備。 次世代の「自律型AIエージェント」Discordボット！

A personal knowledge engine that synthesizes instead of transcribes — every claim carries a citation back to its source. Write-time synthesis + cited retrieval for LLM agents.

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

LangGraph multi-agent system: researcher → writer → peer-reviewer with a scored revision loop. Free stack: Groq (llama-3.3-70b) + DuckDuckGo. WIP.

Local-first root-cause diagnosis engine for LLM, RAG, and Agent failures — deterministic, evidence-backed, zero API keys required.

Local RAG pipeline (FAISS + Ollama) with deterministic and LLM-as-a-Judge quality auditing. Reference implementation with a fully mocked unit-test suite (no live Ollama/PDFs required).

Graph-based reasoning library with embedding search, multi-hop traversal, and automatic entity extraction

Index a whole repo (code + docs) into a navigable, AI-analyzed encyclopedia — map + per-module entries + typed link-graph — so an AI works in huge codebases without filling its context. One auto-routing skills.sh skill with grounded, citation-checked analysis and optional local (Ollama) semantic search.

An AI-powered, multilingual emergency response platform built with Flutter, on-device TFLite computer vision, and NLP triage to guide bystanders and save lives during the Golden Hour.