Second Brain - notes that answer back, with citations

    1

    A personal second brain that never hallucinates. Save notes and links; ask questions and get answers built only from what you saved, with citations - or an honest "your notes don't cover this."

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Second Brain - notes that answer back, with citations

    Example session with this skill installed

    Retrieve my notes about the release checklist and summarize the steps.

    • Read your context and instructions
    • Compiled the second brain

    I found one relevant note regarding the release checklist (#4).

    Release Checklist Summary

    Based on your saved note #4: Release Checklist, here are the required steps:

    • Environment Check: Verify all environment variables are set in the production namespace [1].
    • Database Migrations: Run the pre-deployment migration script and verify the schema version [1].
    • Smoke Tests: Execute scripts/selftest.py to ensure the retrieval engine is functional [1].
    • Tagging: Create a git tag for the version and push to the main branch [1].

    Next steps

    1. Run python3 scripts/brain.py get 4 to see the full text of the checklist.
    2. If any steps are missing, say "Save this to the release checklist: [new step]" to update it.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    One SQLite file, Python standard library only, no API key required. Hybrid BM25 + vector retrieval merged with Reciprocal Rank Fusion, plus a relevance gate that drops chunks neither side vouches for - so the agent answers from your notes or says NO_MATCH instead of inventing memories. Ships with a self-test, the full design writeup, and a guide to deploying the same system as a Telegram bot on Cloudflare's free tier. Distilled from a production bot (linked repo) serving real notes daily.

    Requires Python 3.9+ and SQLite FTS5. Vector embeddings require an OpenAI-compatible API key. Local-only mode has no external dependencies.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    Requires

    Wrangler
    Node.js
    Python

    Permissions

    Terminal / Shell
    Write Files
    Network Access
    Environment Variables
    Listed6 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a permanent, local SQLite database for your agent, allowing it to store and retrieve specific project notes or documents across different sessions without forgetting or confusing them with its training data.

    The 'Gated Retrieval' feature acts as a quality filter; if a query doesn't find a strong match in your local database, the skill returns a 'NO_MATCH' signal, forcing the agent to admit it doesn't know the answer rather than making one up.

    The core engine is built on Python's standard library and local SQLite, so your data stays on your machine; an internet connection and API key are only required if you choose to enable the optional vector embedding features.

    You will receive the complete Python source code for the retrieval engine, the SQLite schema configurations, and a comprehensive integration guide for connecting it to your preferred agent framework.

    This skill is compatible with any Python-based agent framework (like LangChain, AutoGPT, or custom scripts) and requires Python 3.9+ with SQLite FTS5 support, which is standard in most modern environments.

    Unlike simple prompting which has a limited 'memory' window, this skill uses a retrieval pipeline that can handle thousands of documents, only feeding the agent the most relevant snippets to keep costs low and accuracy high.

    New in Agents & Orchestration