Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Mesh-Context-Layer

    1

    Persistent, shared semantic memory for AI agents using hybrid vector search and MCP tools.

    Free

    1 useSecurity scanned
    Mesh-Context-Layer

    Mesh-Context-Layer

    Example session with this skill installed

    I've discovered that our staging database is now running on port 5439 instead of 5432. Can you remember this for the team?

    • Read your context and instructions
    • Compiled the mesh-context-layer

    I have stored this updated configuration in the shared memory layer. I also checked for conflicts and updated the existing record to ensure all agents use the new port.

    Memory Update Summary

    ActionIDContentTypeTags
    Updateddb-cfg-92Staging database port is 5439factdatabase, staging, config
    Resolvedconf-412Overwrote old port (5432)conflictport-mapping

    Next steps

    1. Run mesh_recall with the query "staging database" to verify the update appears in your active context.
    2. Use mesh_sync at the end of your session to summarize any other infrastructure changes you made.
    3. Check mesh_contradictions to ensure no other agents have conflicting local overrides for this service.

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

    About this skill

    Development teams struggle with "agent amnesia" where LLMs lose context between sessions or repeat mistakes other agents already solved. Mesh Context Layer provides a high-speed, persistent semantic memory layer that allows agents to share facts, decisions, and instructions across different tools and sessions.

    What it does

    • Persistent Storage of atomic facts, architectural decisions, and workflows using a SQLite-backed hybrid memory system.
    • Hybrid Search combines vector embeddings, BM25 text search, and exact token matching to find relevant context.
    • Conflict Management identifies contradictory information during storage and provides tools to resolve data inconsistencies.
    • Privacy Controls enable marking sensitive data as local-only to redact it from exports and logs.
    • Lifecycle Management uses TTL decay to automatically lower the confidence of stale information over time.

    How it works

    1. Initialize the environment using mesh setup to configure namespaces and local embedding models.
    2. Store discoveries using mesh_learn to save atomic facts with specific types like decision or instruction.
    3. Recall relevant context at the start of a task using mesh_recall to query the shared memory pool.
    4. Update existing knowledge using mesh_update to refine facts without losing historical access data.

    Frameworks & tools

    This skill interfaces with Python 3.10+, SQLite FTS5, and ONNX. It integrates directly with MCP-compatible clients including Claude Desktop, Cursor, and Gemini CLI.

    Why this beats prompting it yourself

    Manual prompting lacks persistence across different agent instances and cannot scale to thousands of project facts. This skill automates the vectorization, deduplication, and decay logic required to maintain a reliable long-term memory.

    Use cases

    • Cross-Agent Handover where a coding agent stores a bug fix and a DevOps agent later recalls the deployment steps.
    • Architecture Log to track why specific design choices were made to prevent regressive changes.
    • Shared Config Management for storing staging URLs, port mappings, and environment-specific flags.

    Known limitations

    Requires Python 3.10 or higher. Performance depends on SQLite FTS5 support and local disk I/O for the vector database.

    Requires Python 3.10+. Relies on SQLite FTS5 support. Requires ~90MB disk space for ONNX models if not using the fallback hash engine.

    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 1 month ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Mesh Context Layer solves 'agent amnesia' by providing a persistent semantic memory that allows multiple agents to share facts and decisions across different sessions, preventing them from repeating mistakes or losing track of project goals.

    The skill is built for the Model Context Protocol (MCP) and integrates natively with popular clients like Claude Desktop, Cursor, and Gemini CLI, provided you are running Python 3.10+.

    Unlike basic RAG, this skill uses a hybrid search (Vector, BM25, and exact match) and features a built-in 'TTL decay' system that automatically lowers the confidence of old information so your agents don't rely on stale data.

    The system includes dedicated conflict management tools that identify contradictory information during the storage phase, allowing you or your agents to resolve inconsistencies before they affect future tasks.

    Setup is handled via a simple `mesh setup` command that configures your namespaces and local embedding models; no external vector database subscription is required as it runs on a local SQLite-backed system.

    Yes, the skill includes built-in privacy controls that allow you to mark specific atomic facts as 'local-only,' ensuring sensitive data is redacted from external logs and exports.

    New in LLM Ops