← 返回 Skills 市场
rokkiezeng

MAMP

作者 rokkiezeng · GitHub ↗ · v1.2.1 · MIT-0
cross-platform ⚠ suspicious
108
总下载
1
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install mamp-memory
功能描述
Mark AI Memory Protocol — persistent, searchable session memory for AI agents. SQLite-only, zero external dependencies.
使用说明 (SKILL.md)

MAMP — Mark AI Memory Protocol

Gives AI agents persistent, searchable memory using SQLite.

When to Use

  • User says "remember what I told you last time"
  • Agent needs to recall facts across conversations
  • User asks about past topics, preferences, or decisions
  • Context window is filling up and older info needs to be summarized

Core Concepts

  • Session — a conversation, has an ID, survives restarts
  • Turn — one message in a session (role: user/assistant)
  • Tag — labels for a turn, e.g. ["finance", "important"]
  • Priority — importance level: critical, normal, trivial

Key Methods

from importlib.util import spec_from_file_location, module_from_spec
spec = spec_from_file_location("mamp", "ai_memory_protocol_v1.2.0.py")
mod = module_from_spec(spec)
spec.loader.exec_module(mod)

# Manual mode — explicit add_turn() calls
sm = mod.SessionManager()
sm.start_conversation()
sm.add_turn("user", "I prefer dark mode")
sm.add_turn("assistant", "Noted")

# Auto mode (v1.1.8+) — auto-captures turns without manual add_turn()
sm = mod.SessionManager(auto_record=True)
sm.start_conversation()
# ... conversations are recorded automatically ...
sm.stop()  # flushes buffer and disables auto_record

# Heartbeat (v1.1.9+) — called externally every ~5 min via Hermes cron
# sm.heartbeat()  # flushes buffer + closes idle sessions (>30 min)

# Explicit db_path (recommended)
sm = mod.SessionManager(db_path="./memory.db", auto_record=True)

# Environment variable override:
# export MARK_MEMORY_DB=/path/to/memory.db

What It Solves

AI forgets everything each conversation. MAMP makes memory persistent, searchable, and structured — without any external service, API key, or dependency beyond SQLite.

Security Notes

Default behavior — local directory only:

  • DB file written to ./mark_memory.db in the current working directory
  • No system directories are touched
  • No log files, audit files, or hidden state files are written
  • No network access, no external services

Pass an explicit path to isolate data:

sm = mod.SessionManager(db_path="/your/specific/path/memory.db")

Environment variable override:

export MARK_MEMORY_DB=/your/specific/path/memory.db

This takes precedence over both the default and any db_path argument.

Permissions awareness:

  • The DB file contains your conversation history in plaintext
  • Ensure the directory has appropriate access controls
  • If multiple agents run on the same host with the same path, they share memory — use different paths per agent to isolate

No credentials stored:

MAMP uses no API keys, tokens, or secrets. It is a pure local SQLite store.

安全使用建议
This package is not clearly coherent with its public description. Before installing or enabling it for an agent: (1) Inspect the full ai_memory_protocol_v1.2.1.py for places where platform_info is written to the DB or where DEFAULT_DB_PATH points to /opt or /vol2; the code does detect hostname and container status at import time. (2) If you want strictly local cwd storage, set MARK_MEMORY_DB or pass db_path explicitly to ./mark_memory.db and verify the SessionManager uses that value. (3) Consider disabling auto_record by default and only calling add_turn() explicitly, so the agent doesn't passively capture all outbound messages. (4) Run the module in a sandboxed account or VM first to confirm it only creates the files and writes you expect. (5) Ask the maintainer to clarify the contradiction between SKILL.md/CHANGELOG (cwd-only) and v1.2.1 (platform-aware paths and possible platform_info persistence). If you cannot verify these points, treat the skill as untrusted.
功能分析
Type: OpenClaw Skill Name: mamp-memory Version: 1.2.1 The MAMP skill bundle contains intrusive runtime behaviors, specifically a monkey-patching mechanism in SessionManager._enable_auto_record (found in ai_memory_protocol_v1.1.8.py and later versions). This feature scans sys.modules to dynamically wrap and intercept callables in other modules to capture message content. Additionally, ai_memory_protocol_v1.2.1.py includes environment fingerprinting logic (_detect_platform) that collects hostnames, Python executable paths, and container metadata. While these capabilities are plausibly linked to the stated goal of 'passive memory capture' and no external exfiltration code was identified, the use of runtime method redirection and system-level fingerprinting is high-risk and characteristic of monitoring or surveillance software.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The declared purpose (local, SQLite-only, DB in current working directory) conflicts with code in ai_memory_protocol_v1.2.1.py that implements platform detection and a platform-aware default DB path (/opt/claw/hermes/protocol/mark_memory.db or /vol2/1000/claw/hermes/protocol/mark_memory.db). The CHANGELOG and SKILL.md also contradict each other about platform_info persistence. Requesting no credentials is consistent, but the file-path behavior is disproportionate to the 'cwd-only' claim.
Instruction Scope
SKILL.md instructions themselves are scoped to local SQLite usage and provide an env var override (MARK_MEMORY_DB) and explicit db_path parameter. However, the codebase exposes auto_record (which wraps agent message-sending methods) and heartbeat hooks for cron, allowing passive capture of messages and automated flushes — this is within memory-skill scope but increases the breadth of data captured. More importantly, instructions claim no platform info persistence while the v1.2.1 code contains platform detection and a get_platform_info function; it's unclear whether platform info is stored in the DB in this release.
Install Mechanism
No install spec or external downloads — this is an instruction-only skill with bundled Python files. No remote code fetches are present, so install risk from network downloads is low. Code is executed locally via dynamic import as described in SKILL.md.
Credentials
No credentials are requested (OK). But the platform-aware code can change the DB default to system locations outside the working directory, which is more privileged than advertised and may require write access to /opt or /vol2 paths. The module also collects local host information (hostname, python_executable, container heuristics) at import time — harmless by itself, but if persisted contradicts the stated 'no platform_info persistence' and raises privacy concerns.
Persistence & Privilege
The skill does not request always:true and allows agent invocation. It writes a persistent SQLite DB (expected). The auto_record feature that hooks message-sending methods can capture data passively; this increases its blast radius but is within the stated functionality for a memory service. Combined with the platform-aware default path, persistent writes may land in system directories unless MARK_MEMORY_DB or explicit db_path is set.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install mamp-memory
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /mamp-memory 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.2.1
- Added new documentation files: iteration_guide.md and launch_post.md - Added versioned changelog files: CHANGELOG_v1.1.5.md, CHANGELOG_v1.1.7.md - Included new protocol file: ai_memory_protocol_v1.2.1.py - Removed deprecated protocol files ai_memory_protocol_v1.1.6.py and ai_memory_protocol_v1.2.0.py - Updated core docs (SKILL.md, CHANGELOG.md) and scripts (demo.py, ai_memory_protocol_v1.1.8.py) with recent changes and improvements
v1.2.0
- New protocol file added: ai_memory_protocol_v1.2.0.py. - All docs and imports now reference version 1.2.0. - README, SKILL.md, and demo.py updated to reflect new version and usage. - No dependencies or security requirements changed.
v1.1.9
Version 1.1.9 introduces a new heartbeat mechanism and updates to file references. - Added heartbeat support: new sm.heartbeat() method for buffer flush and idle session handling. - Updated all file and code references to use ai_memory_protocol_v1.1.9.py. - Documentation updated to describe the heartbeat feature and clarify usage. - No external dependencies added; local SQLite use maintained.
v1.1.8
- Adds auto_record mode: sessions can now auto-capture turns without manual add_turn() calls. - New parameter auto_record for SessionManager; auto-recording is enabled with auto_record=True. - Skill name updated from mamp to mamp-memory. - Documentation and code samples updated to reflect the new auto_record capability and name. - New implementation file ai_memory_protocol_v1.1.8.py added.
v1.1.7
- Updated skill documentation for improved clarity on usage, core concepts, and security practices. - Clarified that memory is persistent, searchable, and implemented with SQLite only—no external dependencies. - Expanded instructions for database path customization, including environment variable override. - Detailed security considerations, emphasizing local-only data storage and plaintext conversation history. - No changes to credential access or external service usage; remains local and self-contained.
元数据
Slug mamp-memory
版本 1.2.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 5
常见问题

MAMP 是什么?

Mark AI Memory Protocol — persistent, searchable session memory for AI agents. SQLite-only, zero external dependencies. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 108 次。

如何安装 MAMP?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install mamp-memory」即可一键安装,无需额外配置。

MAMP 是免费的吗?

是的,MAMP 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

MAMP 支持哪些平台?

MAMP 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 MAMP?

由 rokkiezeng(@rokkiezeng)开发并维护,当前版本 v1.2.1。

💬 留言讨论