More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    PostgreSQL Semantic Memory MCP

    1

    Equip LLMs with persistent episodic memory, knowledge graphs, and pgvector semantic retrieval over PostgreSQL.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    PostgreSQL Semantic Memory MCP

    PostgreSQL Semantic Memory MCP

    Example session with this skill installed

    Remember that for all backend microservices in this repository, our team uses FastAPI with Pydantic v2 and PostgreSQL with SQLAlchemy async sessions.

    • Read your context and instructions
    • Compiled the postgresql semantic memory

    Memory Stored Successfully

    Stored the architectural decision in PostgreSQL long-term memory:

    AttributeValue
    Memory IDmem_1730206800000
    Categoryarchitecture_decision
    BackendPostgreSQL + pgvector
    Tagsfastapi, pydantic-v2, postgresql, sqlalchemy-async
    StatusIndexed & Searchable

    Content Recorded

    "For all backend microservices in this repository, our team uses FastAPI with Pydantic v2 and PostgreSQL with SQLAlchemy async sessions."

    Verification

    You can recall this anytime in future sessions using:
    query_memories(query="backend tech stack and ORM preferences")

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

    About this skill

    🧠 Long-Term Semantic Memory for AI Agents

    A production-grade Model Context Protocol (MCP) server providing persistent cross-session memory for AI agents (Claude Code, Cursor, Antigravity, Codex CLI, and Gemini).

    🚀 Key Capabilities

    • Episodic Recall: Store user preferences, project context, and past decisions across sessions.
    • pgvector Semantic Search: Hybrid retrieval combining dense vector similarity with keyword/tag filtering.
    • Entity Graph Exploration: Query related concepts and categories learned by your agents.
    • Automatic Pruning: Purge stale memories based on configurable retention policies.

    💎 Production-Grade Commercial Benefits

    • Zero Cloud Lock-in: Run locally or on your own private PostgreSQL instance with complete data sovereignty.
    • Enterprise-Ready: Handles connection pooling, automatic database schema migrations, and pgvector indexing.
    • Universal Multi-Agent Support: Compatible with Claude Code, Cursor, Codex CLI, Antigravity, and custom LangGraph agents.

    Requires an existing PostgreSQL instance with the pgvector extension enabled; does not provision cloud database hosting.

    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 18 days ago

    Requires

    Postgresql
    Postgres Memory Server MCP
    Python
    Git

    Permissions

    Terminal / Shell
    Read Files
    Browser
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    postgresql.org

    File Scopes

    **/.env

    Network and environment variables are strictly used to connect to the user's private PostgreSQL database.

    Listed18 days ago

    What's inside

    Frequently Asked Questions

    Yes, for dense vector similarity queries you need pgvector (CREATE EXTENSION IF NOT EXISTS vector;). It also supports fallback text and tag search.

    No. All memories and embeddings stay strictly within your own private PostgreSQL database.

    Add postgres-memory to your client's MCP configuration JSON with your DATABASE_URL environment variable.

    New in LLM Ops