Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    agent dreams

    2

    Persistent memory and cognitive sleep cycle for AI agents using SQLite FTS5 and Ebbinghaus decay.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    agent dreams

    agent dreams

    Example session with this skill installed

    I'm switching to Tailwind for this project. Remember that we never use utility classes for margins; use the spacing tokens in the config. Record this as a collective rule.

    • Read your context and instructions
    • Compiled the agent dreams

    I have persisted this architectural decision to the collective memory. It will now be available across all sessions and agents when searching for styling or Tailwind-related constraints.

    Memory Consolidation Report

    FieldValue
    Tool Useddream_learn
    Memory IDmem_8f29ac10
    Scopecollective
    Categoryarchitecture / styling
    ContentUse Tailwind spacing tokens for all margins. Avoid direct utility classes.
    Decay InitializedEbbinghaus Curve (Strength: 1.0)
    Search Keywordstailwind, margin, spacing, config, styling

    Next steps

    1. Run dream_recall with the query "Tailwind margin" in your next session to verify the constraint.
    2. Use dream_learn to record the specific spacing token map once the tailwind.config.js is finalized.

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

    About this skill

    LLM context windows are volatile and reset every session, forcing you to repeat instructions or re-explain architectural decisions. Agent Dreams provides a persistent cognitive memory layer and sleep cycle architecture that prevents information loss between agent restarts.

    What it does

    • Persistent storage saves atomic architectural decisions, pitfalls, and user preferences to a local SQLite database.
    • Scope management allows memories to be shared globally across all agents or locked to specific agent instances.
    • Smart filtering automatically masks API keys and sensitive credentials before data is written to disk.
    • Temporal decay applies Ebbinghaus-inspired forgetting curves to deprioritize stale or low-utility information.
    • Hybrid retrieval uses FTS5 keyword and semantic search to pull relevant context without bloating the token window.

    How it works

    1. Observation triggers the dream_learn tool when a significant logic change or project rule is established.
    2. Consolidation occurs as the system filters noise and indexes the new memory with appropriate metadata.
    3. Retrieval happens via dream_recall when the agent needs historical context or previous solutions for the current task.
    4. Reinforcement updates the memory's internal score every time it is successfully recalled, protecting it from decay.

    Frameworks & tools

    Built with SQLite FTS5 for search and Bun for the runtime. Compatible with any MCP-enabled agent host including Claude Desktop, Cursor, Windsurf, and OpenCode.

    Why this beats prompting it yourself

    Manual prompts and custom instructions are static and limited by the context window. This skill provides a dynamic, searchable long-term memory that evolves with your codebase and forgets irrelevant details automatically.

    Use cases

    • Architectural tracking to remember why a specific pattern or library was chosen over another.
    • Preference persistence for keeping track of your specific naming conventions and indentation styles across sessions.
    • Error avoidance by logging past bugs and their fixes to prevent regressions in future tasks.

    Known limitations

    Requires Bun runtime for execution. Memory decay is automatic and based on frequency of use.

    Requires Bun runtime installed on the host machine. Automatic memory decay may deprioritize rarely used but important information if not recalled periodically.

    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 9 days ago

    Permissions

    No special permissions declared or detected

    Listed9 days ago

    What's inside

    Frequently Asked Questions

    Unlike static prompts that bloat your context window, this skill uses a dynamic SQLite FTS5 backend and Ebbinghaus-inspired decay to surface only relevant historical data while 'forgetting' obsolete information.

    Agent Dreams is an MCP-compliant server designed to work seamlessly with any Model Context Protocol host, including Claude Desktop, Cursor, Windsurf, and OpenCode.

    You can define memories as 'Global' for cross-project preferences or 'Instance-Specific' to ensure project-specific architectural decisions don't bleed into unrelated work.

    The skill includes a smart filtering layer that automatically identifies and masks API keys, secrets, and sensitive credentials before they are ever written to the local database.

    The installation requires the Bun runtime; once installed, you simply add the server to your MCP configuration file to enable the dream_learn and dream_recall tools.

    Every time a memory is successfully retrieved via `dream_recall`, its internal utility score increases, which resets its decay curve and ensures important insights stay accessible.

    New in LLM Ops