More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    mem20 memory model

    1

    Enforce structural partitioning between grounded facts and simulated hypotheses to eliminate memory contamination.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    mem20 memory model

    mem20 memory model

    Example session with this skill installed

    Explain the mem20 memory model and tell me why my recent project forecast isn't showing up when I search for project milestones.

    • Read your context and instructions
    • Compiled the mem20 memory model

    I have analyzed your query against the mem20 architectural standards. The reason your project forecast is missing from standard search results is due to the mem20 contamination invariant.

    mem20 Memory Model Specification

    The mem20 model enforces a structural separation between observed reality and model speculation to ensure agent reliability.

    PartitionData TypeIndexed for Recall?Default Recall?
    GroundedReal observations, user statements, attested eventsYes (Vector + BM25)Yes
    SimulatedHypotheses, counterfactuals, model speculation, forecastsNoNo

    Analysis of Missing Forecasts

    In the mem20 model, a "forecast" is classified as

    Simulated content. Because these are unverified model outputs, they are refused from grounded indexes at the write path. Default recall operations strictly exclude the simulated partition to prevent downstream planning from resting on speculation. Until this forecast is promoted via external evidence or user confirmation, it will not appear in grounded search results.

    System Integrity State

    A healthy mem20 store must maintain a contamination_rate = 0.0. If simulated content were to appear in your grounded recall without a formal promotion event, the system would report this as

    index drift, a critical defect.

    Next steps

    1. Use mem20-audit to check your current contamination_rate and verify store health.
    2. Review the promotion rules to move specific forecast milestones into the grounded partition.
    3. Use the explicit simulated recall path if you specifically need to retrieve speculative data.

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

    About this skill

    Memory management for AI agents often fails when models treat speculative thoughts and user-confirmed facts with equal weight. This skill implements the mem20 memory model, a structural framework that prevents hallucination by strictly partitioning grounded observations from simulated hypotheses. It ensures your agent maintains a clean data provenance chain and provides tools for auditing memory integrity.

    What it does

    • Strict Partitioning separates real-world observations from model-generated speculation at the write path.
    • Recall Filtering defaults all retrieval operations to grounded data only to prevent plan contamination.
    • Contamination Auditing detects and reports simulated content that has leaked into grounded indexes.
    • Evidence-Based Promotion defines the specific criteria for moving data from simulated to grounded storage.
    • Integrity Monitoring tracks index drift and ledger disagreement as formal system defects.

    How it works

    1. Configure Write Paths by directing verified environment data to grounded storage and guesses to simulated storage.
    2. Execute Recall using the default grounded filter to retrieve only trusted information for downstream reasoning.
    3. Run Contamination Audits after bulk imports or migrations to verify a contamination_rate of 0.0.
    4. Apply Promotion Rules only when external evidence or user confirmation justifies upgrading a hypothesis to a fact.

    Frameworks & tools

    This skill is designed for agents using vector databases or BM25 indexing systems that support metadata filtering and multi-partition storage. It is the architectural core for the mem20-harness and mem20-audit ecosystems.

    Why this beats prompting it yourself

    Standard prompting relies on the agent's "good behavior" to distinguish facts from fiction, which frequently fails under high token pressure. This skill treats the distinction as a structural invariant, making memory integrity a measurable technical metric rather than a stylistic preference.

    Use cases

    • Prevent speculative model "hallucinations" from polluting long-term project memory.
    • Audit large-scale data migrations for hidden model speculation or noise.
    • Build agents that can explain exactly why they trust a specific piece of information.
    • Debug agent failures caused by plans built on unverified hypotheses.

    Known limitations

    Requires a substrate that supports separate indexing or metadata-based partitioning. Does not automatically verify the truth of user statements, only tracks their status as grounded vs simulated.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires backend support for metadata filtering or dual-index storage. Does not verify external truth, only handles internal architectural partitioning and promotion logic.

    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 buying a skill.

    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 8 days ago

    Software
    mem20
    ormem20-ce

    Permissions

    Environment Variables
    Network Access
    Write Files
    Terminal / Shell
    Read Files
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    mem20 solves 'memory contamination,' where an AI agent begins to treat its own internal guesses or hallucinations as verified facts, leading to recursive errors in future tasks.

    This skill is compatible with any agent framework using vector databases or BM25 indexes that support metadata filtering, including LangChain, AutoGPT, and custom-built LLM-ops pipelines.

    No, mem20 implements structural partitioning at the data layer, ensuring integrity even when the model is under high token pressure or complex reasoning loads where prompts often fail.

    You will receive the architectural framework for mem20, the logic for the dual-partition write/recall paths, and the schema for contamination auditing and promotion rules.

    Setup involves configuring your storage substrate to support dual-indexing or metadata tagging, then routing your agent's input streams through the mem20 partitioning logic.

    mem20 tracks data provenance but does not verify external truth; it ensures that if a user provides false information, it is stored as a 'grounded observation' rather than a 'model speculation.'

    New in Agents & Orchestration