1

    nex-open-brain-rag

    by Ch1n4 G3nd4x

    Deploy a self-hosted, private RAG system with pgvector, Ollama, and a Telegram interface for your personal notes.

    Updated Jun 2026
    Security scanned

    $15

    · or 75 credits

    30-day refund guarantee

    Secure checkout via Stripe

    Included in download

    • Build a private personal knowledge base with semantic search capabilities
    • Deploy a self-hosted vector database on a Raspberry Pi using pgvector
    • terminal automation included
    • Instant install

    Sample input

    I have a folder of markdown research notes. Set up a local RAG system on my Pi to search them and give me a Telegram bot interface to ask questions.

    Sample output

    I've generated your Second Brain stack:

    • docker-compose.yml: Local pgvector setup.
    • file_ingestor.py: Chunks your notes (1500 chars) with metadata extraction.
    • vector_search.py: Cosine-distance search logic.
    • telegram_bot.py: Your chat interface. Just run docker compose up!

    About This Skill

    What it does

    Nex Open Brain RAG is a developer-centric skill for building a private, self-hosted second brain. It automates the creation of a full-stack Retrieval-Augmented Generation (RAG) system optimized for local hardware like a Raspberry Pi 5. It manages the entire pipeline: from setting up PostgreSQL with pgvector for semantic search to implementing local embeddings via Ollama and a multi-stage LLM fallback chain (local, Qwen, or Claude).

    Why use this skill

    Most RAG setups are expensive or leak data to the cloud. This skill provides a private alternative that costs nothing to run. It handles the nuances of vector database alignment—ensuring your 768-dim embeddings match your schema—and adds an intelligent metadata layer that automatically extracts topics, sentiment, and summaries from your notes. It's better than manual prompting because it generates production-ready scripts for chunking, batch embedding, and asynchronous database management that are pre-integrated.

    Supported tools

    • Database: PostgreSQL with pgvector (Dockerized)
    • Frameworks: FastAPI, SQLAlchemy (Async), Pydantic
    • Embeddings: Local Ollama (nomic-embed-text)
    • Interfaces: Telegram Bot API & RESTful API
    • LLMs: Ollama, Qwen, and Claude fallback logic

    Use Cases

    • Build a private personal knowledge base with semantic search capabilities
    • Deploy a self-hosted vector database on a Raspberry Pi using pgvector
    • Automate metadata extraction (topics, people, sentiment) from raw text notes
    • Create a Telegram bot that answers questions based on your private documents

    Reviews

    No reviews yet - be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    Terminal / Shell

    Allowed Hosts

    dashscope-us.aliyuncs.com
    172.17.0.1
    api
    nex-ai.be

    File Scopes

    assets/**
    references/**
    scripts/**

    Tags

    rag
    pgvector
    raspberry-pi
    self-hosted
    knowledge-management
    python

    Creator

    Ch1n4 G3nd4x

    Founder of Nex AI. I build production-grade Claude Skills from systems that actually run: multi-tenant SaaS, Telegram agents, Raspberry Pi infrastructure, 3D multiplayer rooms. Every skill ships battle-tested patterns, not theory. 33+ open source skills published, commercial catalog growing.

    Frequently Asked Questions

    Learn More About AI Agent Skills

    More Premium Skills

    synthesizing-institutional-knowledge

    Builds the organizational memory schema your AI agent needs to answer why — capturing decision provenance, causal chains, and event context that embedding-based retrieval permanently discards.

    $103 installs

    designing-hybrid-context-layers

    Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

    $1012 installs

    diagnosing-rag-failure-modes

    RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.

    $105 installs

    consumer-motivation-analyzer

    Go beyond surface-level feedback to uncover the psychological drivers and hidden motivations behind buyer behavior.

    $199 installs