rag — independent software & tools
-
Delphi-RAG-Lint
Delphi-native, MIT-licensed RAG + linter for Delphi/Pascal source code. Symbol-exact + fuzzy + tree-sitter lint. Pure Delphi at runtime.
-
exomem
Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.
-
epicurus
Self-hosted, modular, local-first personal-assistant platform — an AI agent plus pluggable integration modules.
-
gnosis
Gnosis is a Greek noun meaning "knowledge" or "awareness"
-
wavemind
Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.
-
open-mind
Understand any unfamiliar codebase in an afternoon — a local, deterministic, source-traceable knowledge index (glossary · graphs · code search) that never invents what isn't there.
-
wigolo
The go-to web for your agent!
-
CrewLoop
A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.
-
Talos
Selfhosted AI-Platform for using Local LLMs with a Multi-User Terminal and advanced RAG Pipeline for the LLM.
-
tailor
TAILOR — self-hosted AI memory framework. 100% local, LLM-agnostic, MCP-native
-
@cemised/cognitive-memory
An autonomous graph-vector memory engine powered by SQLite and Ollama.
-
@copilotkit/pathfinder
The knowledge server for AI agents — index docs, code, Notion, Slack, and Discord into searchable, agent-accessible knowledge via MCP. Supports OpenAI, Ollama, and local transformers.js embeddings.
-
@keleshteri/pageindex-rag
Vectorless RAG using LLM-driven hierarchical document indexing — PDF and Markdown/Obsidian vault support
-
@mastra/core
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
-
paqad-ai
Spec-driven development framework — AI agents that think before they type
-
@retineo/core
Connection discovery engine (L0–L3). Open-source core for the Retineo ecosystem.
-
ruvector
Self-learning vector database for Node.js — hybrid search, Graph RAG, FlashAttention-3, HNSW, 50+ attention mechanisms
-
@sentropic/graphify
AI coding assistant skill (Claude Code, Codex, Gemini CLI, Kimi Code, GitHub Copilot CLI, Aider, OpenCode, OpenClaw) - turn any folder of code, docs, papers, images, or audio/video transcripts into a queryable knowledge graph
-
@tobilu/qmd
Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
-
opti-oignon
Local-first AI inference platform for LLMs — private chat, RAG, defense-in-depth security (Daily/Bulbe, encryption at rest, 2FA), on your own hardware. SvelteKit + FastAPI
-
2ndbrain
AI-native markdown knowledge base with semantic search, RAG, and MCP server
-
Paperwise
Convert academic papers into annotated, browser-friendly web pages with color-coded logic and easy navigation powered by OpenAlex data.
-
SQLBot
🤖 Enhance data queries with SQLBot, an intelligent system that combines advanced models and RAG for seamless integration and secure access control.
-
graphRAG-retrievers-agents
🚀 Explore GraphRAG by building customized retrievers and agents using Neo4j for advanced semantic and hybrid search solutions.
-
axon
Self-hosted web crawling and RAG pipeline with MCP tooling for scrape, crawl, ingest, embed, query, and ask workflows.
-
wsl-assistant
A fully auto configured, self-hosted local AI & database stack on Debian WSL2.
-
promptbook-mcp
🤖 Store, search, and organize your AI prompts easily with RAG-powered semantic search in this plug-and-play server for developers.
-
SmartDocQ
SmartDocQ is an AI-powered assistant designed to help users intelligently search, analyze, and extract insights from documents. Powered by Google Gemini, it uses natural language to automate document processing for learning, research, and professional document management.
-
@andersmyrmel/vard
Lightweight prompt injection detection for LLM applications. Zod-inspired chainable API for prompt security.