Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    basemem memory

    1

    Local-first persistent project memory for coding agents using SQLite to track decisions and code structure.

    Free

    2 usesSecurity scanned
    basemem memory

    basemem memory

    Example session with this skill installed

    We decided to use SQLite for this project because it is local-first and requires no server. Can you remember this and tell me what the next step is for the 'basemem' topic?

    • Read your context and instructions
    • Compiled the basemem memory

    I have recorded the decision regarding SQLite and updated the project memory.

    Project Memory Update: basemem

    ActionDetails
    Logged DecisionChose SQLite for local-first architecture and zero server overhead.
    Topicbasemem
    StatusActive
    Memory ID842

    Next steps

    • Use update_planet to define the specific technical milestones for the SQLite implementation.
    • Call code_init to begin indexing the current repository structure into the memory database.
    • Run session_end when you finish this session to generate a durable summary for your next login.

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

    About this skill

    Agents lose context between sessions, forcing you to re-explain architectural decisions and project constraints. This skill provides a local-first persistent memory layer that stores decisions, project state, and code-graph evidence in a SQLite database.

    What it does

    • Persistent memory stores decisions, facts, and architectural constraints across multiple agent sessions.
    • Code intelligence indexes project symbols, callers, and callees to provide structural context without full-file reads.
    • Session management tracks progress with session starts, recaps, and end summaries to maintain continuity.
    • Conflict resolution identifies and manages contradictory notes or outdated project information.
    • Local storage maintains all data in a local SQLite database with no requirement for external vector stores or hosted services.

    How it works

    1. Initialize the memory by calling code_init to index the project and update_planet to set the initial goal.
    2. Record significant decisions mid-work using logInteraction to ensure constraints are preserved.
    3. Recover context at the start of new sessions using session_recap or read_planet.
    4. Search for specific historical context using search_notes or code_find when encountering unfamiliar symbols.

    Frameworks & tools

    This tool requires Python 3.10+, Node.js, and Git. It utilizes a local SQLite database for storage and optionally integrates with ripgrep for fast text searches.

    Why this beats prompting it yourself

    Standard prompts are transient and lose detail once the context window rolls over or a new session starts. This skill automates the retrieval of specific historical facts and structural code data that manual prompting cannot reliably recall or maintain.

    Use cases

    • Multi-day refactoring where the agent must remember why a specific pattern was chosen across several sessions.
    • Onboarding agents to large codebases by providing an indexed symbol graph and recorded architectural decisions.
    • Tracking constraints to prevent the agent from suggesting solutions that were previously rejected for specific technical reasons.

    Known limitations

    Data paths vary between the curl installer and manual setup, requiring explicit environment variables to avoid ambiguity. Session-start context injection is limited to specific supported agents.

    Database path defaults vary by installation method. Auto-injection of context at start is restricted to Tier 1/2 agents. Large text searches require ripgrep.

    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

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    GitHub
    Python
    Node.js
    Basemem MCP
    Mem MCP
    macOS
    Only MCP
    Git

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files

    Allowed Hosts

    raw.githubusercontent.com
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike standard prompts that are lost when a session ends, this skill uses a local SQLite database to store architectural decisions and code structures permanently, ensuring your agent never forgets past constraints or project context.

    The skill stores all data locally on your machine in a SQLite database, meaning your project's architectural history and code symbols never leave your environment or require a subscription to an external vector database.

    You will need Python 3.10 or higher, Node.js, and Git installed; for optimal performance during symbol searches, the tool also integrates with ripgrep if available on your system.

    Yes, it is specifically designed for multi-day workflows by using 'session_recap' and 'read_planet' functions to bridge the context gap between different sessions or agent restarts.

    The tool includes built-in conflict resolution features that identify and manage contradictory notes, ensuring that outdated project information doesn't interfere with current development goals.

    New in Agents & Orchestration