dev-tools
Xerj: Auto-Indexed Search Built for Agents
Xerj autoindexes code, docs, logs and PDFs for AI agent search, claims 40x fewer tokens than grep, and stays Elasticsearch compatible.
#github-trending#rust#ai-search
Tag
Rag Posts
18 posts tagged #rag
Browse 18 posts tagged Rag. Setup notes, reviews, comparisons, and workflow patterns.
All Posts
tutorial
production-agentic-rag-course: notebooks to production
production-agentic-rag-course is a Python and Jupyter course repo with Airflow, Docker Compose, and Gradio, MIT licensed, with 9,409 GitHub stars.
#github-trending#rag#python
ai-setup
PageIndex: RAG without a vector database
PageIndex is an MIT-licensed Python tool that indexes documents for reasoning-based RAG, replacing vector similarity search with an LLM reading a document tree.
#github-trending#rag#python
ai-setup
Tencent WeKnora: An Open-Source LLM RAG Knowledge Platform
WeKnora is Tencent's open-source LLM knowledge platform for turning raw documents into a queryable RAG, reasoning agent, and self-maintaining Wiki. Go, 25k stars trending.
#github-trending#ai-setup#rag
ai-setup
awesome-llm-apps: 100+ Open-Source AI Agent and RAG Apps
A curated collection of 100+ open-source AI agent, agent skill, and RAG app examples in Python. Apache 2.0 licensed and actively maintained.
#github-trending#ai-agents#python
ai-setup
Airweave - Context Retrieval Layer for AI Agents
Open-source context retrieval layer connecting apps, databases, and documents to AI agents via unified search, SDKs, and MCP — 50+ integrations, self-hostable.
#ai-setup#rag#retrieval
ai-setup
MemoryStack - AI Memory Layer for Multi-Agent Systems
MemoryStack gives AI agents persistent memory, knowledge graphs, and semantic search. Free tier includes 500 memories/month with Python and Node.js SDKs.
#ai-setup#ai-agent#rag
ai-setup
Captain – Multimodal RAG Search That Scales
Captain connects to S3, SharePoint, and 20+ sources to index video, images, PDFs, and audio, then serves AI agents via a clean REST API or MCP server. YC W26.
#ai-setup#dev-tools#rag
ai-setup
Ragtime - Self-Hosted RAG API and MCP Server
Deploy a self-hosted RAG pipeline with built-in MCP tools for PostgreSQL, MSSQL, MySQL, SSH, and filesystem indexing. Works with Claude Desktop, Cursor, and any OpenAI-compatible client.
#rag#mcp#self-hosted
ai-setup
AnythingLLM - Desktop AI App With Private LLM and RAG
A full-featured desktop AI assistant that runs locally, supports multi-user workspaces, and connects to any LLM provider. MIT licensed, with built-in agents and document chat.
#ai-setup#local-ai#rag
ai-setup
Ragtoolina – MCP Tool That Cuts AI Coding Costs by 63%
Ragtoolina adds semantic codebase RAG to any MCP-compatible AI coding tool, cutting token usage by 63% with one line of config. Self-hosted option included.
#mcp#ai-coding#rag
dev-tools
Superexpert.AI - Build Multi-Task AI Agents Without Code
Open-source platform for building multi-task AI agents with a no-code interface, PostgreSQL backend, and support for OpenAI, Anthropic, and Gemini models
#ai-agents#open-source#no-code
ai-setup
Captain – Automated RAG for Files and Cloud Storage
Captain (YC W26) automates RAG pipeline setup for S3, GCS, and Google Drive. Index unstructured data in minutes with multimodal search across docs, images, and sheets.
#rag#ai-search#cloud-storage
ai-setup
ZeroEntropy - Search Infrastructure for RAG and AI Agents
ZeroEntropy (YC W25) builds embedding models, rerankers, and managed search APIs for RAG pipelines. Uses novel Elo-score training to outperform OpenAI and Cohere on retrieval benchmarks.
#rag#search#ai-infrastructure
ai-setup
Embedding.io - Turn Websites Into Knowledge Bases for LLMs
Crawl, chunk, and vectorize any website into a queryable knowledge base. REST API with collections, scheduled updates, and built-in RAG for LLM applications.
#rag#llm#ai-setup
dev-tools
Knowhere: AI Document Memory for Agents
Ingest documents into persistent navigable memory — tree-like hierarchy reconstruction, multi-modal parsing, and agentic RAG with evidence-based citations.
#github-trending#dev-tools#python
dev-tools
Chonkie - Open-Source RAG Chunking Library
Chonkie is a lightweight, fast RAG chunking library for Python and TypeScript. Up to 33x faster than LangChain, supports semantic, token, sentence, and code chunking.
#open-source#rag#python
ai-setup
Captain – Automated RAG Pipeline for Files
Captain automates building and maintaining RAG pipelines for unstructured data. Index S3, GCS, and Google Drive in minutes with one API call.
#rag#ai-setup#vector-search