More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Brain — long-term memory for coding agents

    1

    Local long-term memory and multi-agent coordination protocol for persistent coding context.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Coding agents lose context when a session ends or when switching between different tools. Important architectural decisions, hard-won bug fixes, and project-specific preferences vanish, forcing you to repeat instructions. This package provides a durable, local long-term memory layer using the Brain MCP server to ensure knowledge persists across sessions and agent handoffs.

    What it does

    • Persistent memory storage saves decisions, snippets, and todos in a local database that survives session restarts.
    • Multi-agent coordination enables messaging and handoffs between different agents like Claude and Codex using a formal protocol.
    • Context retrieval searches project-specific or global knowledge bases to prevent contradicting prior decisions.
    • Knowledge hygiene audits existing memories for duplicates, stale dates, or oversized entries to maintain context quality.
    • Automated upkeep proposes merges and updates based on local evidence while protecting sensitive record types.

    How it works

    1. Setup installs the agent-memory-brain server via uv or pipx and registers it with your local agent host.
    2. Capture uses memory_save to store actionable facts as specific kinds like decision, preference, or snippet.
    3. Query calls memory_search or project_context at the start of tasks to pull relevant historical data.
    4. Coordinate sends messages between agents via message_post and tracks replies with message_wait for complex workflows.

    Frameworks & tools

    This skill requires Python 3.12+ and the Brain MCP server. It is designed for use with Claude Code, Cursor, or any MCP-compliant agent host. It uses uv for tool management and stores data in a local SQLite database.

    Why this beats prompting it yourself

    Standard prompting relies on a limited context window that clears every session. This skill implements a structured retrieval-augmented memory system that survives reboots. It includes built-in deduplication and relationship mapping that raw system prompts cannot maintain reliably.

    Use cases

    • Record why a specific library was chosen to prevent an agent from suggesting a migration later.
    • Pass a task state and context from a research agent to a coding agent via the handoff protocol.
    • Store a global preference for small PRs that applies across all your local repositories.
    • Audit a project knowledge base to find and merge overlapping architectural notes.

    Known limitations

    Memory content is capped at 2,000 characters by default. It does not store secrets or credentials. Requires a local Python environment for the MCP server.

    Content capped at 2,000 chars per entry. No storage of secrets/tokens. Requires Python 3.12+. Multi-agent handoffs require all agents to support the Brain protocol.

    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 today

    Requires

    OpenAI
    Anthropic
    Astral
    Pypa
    Pypi
    Python
    Brain MCP
    uv, or pipx with Python 3.12+
    agent-memory-brain
    Claude Code or Codex

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Allowed Hosts

    api.openai.com
    api.anthropic.com
    astral.sh
    pipx.pypa.io
    pypi.org

    File Scopes

    ~/.devmem/**
    ~/.claude.json
    ~/.claude/settings.json
    ~/.claude/projects/**
    ~/.codex/config.toml
    ~/.codex/sessions/**
    ~/.local/bin/brain
    ~/.local/bin/devmem
    ~/.local/share/uv/tools/agent-memory-brain/**
    Listed6 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    Brain provides a persistent SQLite-backed memory layer that stores project decisions and architectural context locally, ensuring your coding agent remembers previous work even after a session restart or tool switch.

    This skill is compatible with any MCP-compliant host, including Claude Code and Cursor, provided you have Python 3.12+ installed on your local machine.

    Yes, the built-in multi-agent coordination protocol allows you to post messages and track replies between different agents, facilitating seamless handoffs and task delegation.

    The package includes the Brain MCP server, the necessary schemas for structured memory storage (decisions, snippets, etc.), and a suite of tools for memory retrieval, auditing, and multi-agent messaging.

    No, Brain is a local-first solution that stores all data in a local database on your machine; it does not require an external cloud subscription or send your project data to third-party servers.

    While the server handles storage automatically, it includes a 'Knowledge Hygiene' feature that audits your database to merge duplicates, remove stale information, and keep the context window efficient.

    New in Agents & Orchestration