Tag

memvid

Packages an AI agent's memory — data, embeddings, search indexes, and metadata — into one portable .mv2 file, replacing multi-service RAG stacks. Combines BM25 and HNSW search with temporal queries and sub-millisecond local reads, fully offline.

MS MARCO Translations Dataset (ai4bharat/MSMARCO-XI)

Provides MS MARCO queries, passages and answers translated into 14 Indic languages while keeping the original English content and per-example translation metadata. Includes train/validation splits, passage selection flags, and translation model parameters for multilingual IR, QA and RAG research.

Claude-Flow

Wraps Claude Code as an MCP server that orchestrates 100+ specialized agents into self-organizing swarms — hierarchical, mesh, or adaptive consensus — backed by persistent vector memory, coordination hooks, and secure cross-machine federation.

ruflo

Wraps Claude Code and Codex with an execution harness that turns one coding agent into coordinated swarms. A single init command adds ~98 agents, an MCP tool server, cross-session vector memory, and cross-machine federation.

All-in-RAG

Practical, full-stack tutorial for building Retrieval-Augmented Generation (RAG) systems—covers data preprocessing, vector embedding and indexing, hybrid and multimodal retrieval, generation integration, evaluation and production-ready engineering. Includes hands-on projects and examples for developers with Python experience.

RAG-Anything

Extends RAG beyond text: parses PDFs and Office files containing images, tables, equations, and charts, then queries them through one multimodal knowledge graph. Built on LightRAG, it replaces separate parsing and retrieval tools.

Code-Graph-RAG

Parses multi-language repositories into a Memgraph knowledge graph and enables natural-language RAG querying, grounded source retrieval, and AI-driven AST edits. Key features include Tree-sitter parsing, LLM-to-Cypher generation, structural search-and-replace, and MCP server integration.

Agents Towards Production

A code-first collection of runnable tutorials for building production-ready generative-AI agents — step-by-step guides covering stateful workflows, vector memory, RAG, tool integrations, Docker/AWS/RunPod deployment, security guardrails, observability, and multi-agent patterns.

Project N.O.M.A.D.

Offline-first knowledge server that bundles local AI chat (Ollama + vector RAG), offline Wikipedia/education/maps, and utility tools behind a Dockerized management UI — designed to keep searchable knowledge available without cloud access.

Coze Studio

Provides a visual, low-code environment to build, debug, and deploy AI agents—integrates model services (OpenAI, Volcengine), RAG, plugins, workflows, and a Chat SDK for embedding agents into apps.

LEANN

Stores a pruned proximity graph instead of all embeddings, recomputing vectors on demand at query time. A 60M-doc index takes 6GB, not 201GB (97% less), at comparable recall. Powers private local RAG over files, mail, chat, and browser history.

OpenRAG

Bundles Langflow, Docling, and OpenSearch into one installable package so you can ingest messy documents, run agentic retrieval with re-ranking, and chat over your own knowledge base. Ships Python/TS SDKs and a built-in MCP server at /mcp.