Persistent kb

    2

    Local, SQLite-backed cross-session memory for agents to store and retrieve lessons, decisions, and facts via FTS5.

    $9

    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

    persistent-kb

    Example session with this skill installed

    What did we learn from the database migration issues last November? Show me the specific fix.

    • Read your context and instructions
    • Compiled the persistent-kb

    [ID: 42] Title: Production Database Migration Fix
    Kind: lesson | Tags: postgres, devops, fix
    Content: Encountered 'lock timeout' during v2 schema migration. Resolved by setting statement_timeout to 60s. Use scripts/migrate_v2_patch.sql for future staging runs.
    (Created: 2023-11-15)

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

    About this skill

    What it does

    Persistent KB provides your AI agent with a long-term, local memory using a SQLite-backed knowledge base. It allows agents to save cross-session facts, lessons learned, and project decisions into a structured database that survives context window resets and machine reboots.

    Why use this skill

    Unlike standard LLM "memory" which is often session-bound or cloud-hosted, this skill offers a privacy-first, developer-centric approach. It solves the "amnesia" problem where agents forget technical hurdles or design decisions made in previous chats. By using FTS5 (Full-Text Search), it enables fast retrieval of relevant context without cluttering the current prompt window.

    Supported tools

    • SQLite: Local storage with high-performance FTS5 indexing.
    • Python 3.10+: Zero-dependency implementation (standard library only).
    • CLI: A robust script (kb.py) for easy integration with any shell-enabled agent.

    The Output

    The skill produces structured summaries of stored knowledge, including entry IDs, categories (lessons, decisions, references), and tags. It handles conflict resolution by superseding old facts, ensuring the agent always retrieves the most current information while maintaining history.

    • Local-only (single machine).
    • FTS5 keyword search only; no vector/semantic embedding support.
    • CLI-driven; requires agent permission to execute local Python scripts.

    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 months ago

    Software
    Python

    Permissions

    Terminal / Shell
    Environment Variables
    Listed6 months ago

    What's inside

    Frequently Asked Questions

    This skill provides a local SQLite database that allows your AI agents to store and recall information across different chat sessions, long after the context window has been cleared or the system has been restarted.

    Any AI agent or framework with shell access and Python 3.10+ can use this skill, as it operates via a robust CLI script (kb.py) that requires no external cloud dependencies.

    The skill utilizes SQLite's FTS5 (Full-Text Search) extension, which enables the agent to instantly find specific facts or past decisions based on keyword relevance rather than scanning the entire files.

    The package includes the full kb.py script, documentation on the CLI commands, and a pre-configured local database setup so your agent can begin saving lessons and decisions immediately.

    The skill is designed for ease of use; as long as your system has Python 3.10 or higher installed, there are no additional third-party libraries or API keys required to maintain your local knowledge base.

    Yes, the skill includes a conflict resolution system that allows agents to update existing records or supersede old facts, ensuring that the most current information is prioritized during retrieval.

    New in Agents & Orchestration