memvault

    1

    Enable local, long-term agent memory using MemVault and MCP for persistent context across chat sessions.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    memvault

    Example session with this skill installed

    I'm starting work on the 'apollo-bridge' project. Search the memory for any deployment paths or specific environment rules we discussed in the last session and add them to context.

    • Read your context and instructions
    • Compiled the memvault

    I have searched the apollo-bridge namespace for deployment and environment configurations. I found three relevant facts, including a pinned deployment path and a specific environment variable requirement for the staging tier.

    Retrieved Context: apollo-bridge

    Fact IDContentStatusRecall Reason
    fb-9921The production deploy script is located at ./scripts/deploy-prod.sh and requires sudo.PinnedKeyword match: 'deploy'
    fb-4402Use NODE_ENV=staging when testing the bridge component locally to bypass auth mocks.ActiveKeyword match: 'environment'
    fb-1053All secrets must be loaded via the 1Password CLI integration, not .env files.ActiveVector match: 'rules'

    Next steps

    1. Run memory_explain with retrieval ID ret-8821 if you need to see the ledger verification for these facts.
    2. Tell me if the deployment script path has changed so I can update fb-9921.
    3. Proceed with the bridge component work using the staging environment variables.

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

    About this skill

    LLMs lose context between sessions, forcing you to repeat preferences, architectural decisions, and project paths every time you open a new chat. This skill solves the "goldfish memory" problem by integrating MemVault, a local-first memory engine that uses the Model Context Protocol (MCP) to persist knowledge across conversations without relying on cloud storage.

    What it does

    • Persistent storage saves specific facts, preferences, and decisions to a local database that survives session restarts.
    • Context injection retrieves relevant historical data via keyword or vector search and feeds it directly into the current prompt.
    • Fact versioning updates existing memories by superseding old facts with new ones while maintaining a verifiable history.
    • Verified recall uses a hash-chained ledger to explain exactly why a specific fact was retrieved for a given query.
    • Privacy control runs entirely on your local machine with no network access unless you explicitly configure an external embedding provider.

    How it works

    1. Installation downloads the MemVault binary and generates the necessary JSON configuration for your MCP client.
    2. Namespace creation segments memories by project or repository name to ensure relevant retrieval without cross-talk.
    3. Write loop captures stand-alone facts during the conversation, marking critical architectural rules as pinned.
    4. Search loop queries the local vault at the start of new tasks to pull in previously learned context.

    Frameworks & tools

    This skill uses the Model Context Protocol (MCP) and interfaces with the MemVault Rust-based binary. It integrates with any MCP-compliant client such as Claude Code or Cursor and supports OpenAI-compatible embedding endpoints like Ollama for semantic search.

    Why this beats prompting it yourself

    Writing to a text file is messy and lacks ranking. This skill provides a structured API for the agent to manage its own memory, ensuring the most relevant facts are prioritized within the token budget while maintaining a permanent, auditable record of why information was recalled.

    Use cases

    • Store project conventions like specific linting rules or deployment paths that are not in the README.
    • Remember user preferences regarding coding style, documentation depth, or preferred libraries across different sessions.
    • Track architectural decisions and the reasoning behind them to prevent re-litigating the same technical debt later.
    • Maintain stateful workflows by recording the progress of long-running tasks that span multiple days or chat threads.

    Known limitations

    Requires manual binary installation and client restart for initial setup. Semantic search requires an external embedding provider like Ollama; otherwise, retrieval defaults to keyword-only BM25.

    Requires manual binary download and MCP config merging. Semantic search functionality depends on an external OpenAI-compatible embedding endpoint. Keyword search is the default.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 28 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Network Access
    Listed28 days ago

    What's inside

    Frequently Asked Questions

    MemVault creates a local, persistent database that stores architectural decisions, project rules, and user preferences, allowing your AI agent to recall them in future sessions without you having to re-explain the context.

    The skill is compatible with any platform that supports the Model Context Protocol (MCP), including popular tools like Claude Code and Cursor.

    Yes, MemVault is local-first; all memories are stored on your machine, and it only requires network access if you choose to connect an external embedding provider like Ollama for semantic search.

    Setup involves downloading the MemVault binary and adding the generated JSON configuration to your MCP-compliant client to enable the memory interface.

    Unlike a basic text file, this skill provides a structured API that uses BM25 or vector search to prioritize the most relevant facts within your token budget, ensuring the agent isn't overwhelmed by irrelevant data.

    MemVault uses fact versioning and a hash-chained ledger to update old information with new context while maintaining a verifiable history of why specific facts were recalled.

    New in LLM Ops