Skip to content
Agentmart
Submit a tool

AI Agent Memory

Agent-agnostic persistent memory MCP server.

Connector by xiangzi1126 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/xiangzi1126-ai-agent-memory-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Agent-agnostic persistent memory MCP server. Local-first: memories travel with your project.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
5 read · 1 write · 0 delete · 5 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 11

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • get_memory
  • list_memories
  • recall
  • search_journal
  • search_memories

Write 1 · Create, change, send or run things.

  • update_memory

Not yet classified 5 · We could not tell from the name and description.

  • forget
  • journal_entry
  • remember
  • setup_profile
  • who_am_i

Tools (11)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • forget

    删除一条记忆(SQLite+Chroma+Markdown 三处同步)。用户要求"删掉 / 忘掉"某条记忆时调用。

  • get_memory

    按 id 取单条记忆的完整内容(含 [[link]] 关联)。已知具体 id 时调用。

  • journal_entry

    记录一次交互的工作日记(人读,按时间线翻看 logs/journal.md)。 完成一次用户请求后调用一次。用你自己的话转述:用户问了什么、 你怎么回答 / 做了什么。这是给人翻看的流水日记,不是原始对话存档。 agent 名 / 时间 / 用户名自动补;与 remember 分工:remember 存可检索知识(AI 读), journal_entry 存交互流水(人读时间线)。同一次交互可都调。 open_question:这次结束时留给用户的问题或待定项(可选),记下"停在哪、等用户定什么"。

  • list_memories

    列出记忆(可按分类过滤),按更新时间倒序(不含正文)。浏览 / 概览已有记忆时调用。

  • recall

    语义 + 关键词 + 标题三路融合检索,返回最相关记忆(含正文 + [[link]] 关联)。 当用户问"之前 / 上次 / 有没有记录 / 回忆 / 召回 / 历史决策 / 踩过的坑"时调用。 每条记忆若 content 含 [[其他记忆标题]],返回时附 links 字段(关联记忆 id/title/category)。

  • remember

    存储一条持久化记忆(SQLite+Chroma+Markdown 三处同步,自动 embed)。 当用户说"记住 / 记下 / 沉淀 / 保存"某条信息时调用。content 中可用 [[其他记忆标题]] 引用已有记忆,recall 时会解析为关联记忆。 category:user(用户偏好)/ project(项目知识)/ process(工作过程)/ agent(Agent 协作)。 scope:user / project / session。

  • search_journal

    【兜底专用】在工作日记里搜有界片段(question/answer_summary/key_points)。 仅当 recall() 召回不足、需要还原「某次交互具体做了什么」时调用。 每次返回 ≤ limit 条带 snippet 的片段,非全文。平时不要调用。

  • search_memories

    按分类 / 标签 / 来源 Agent 结构化过滤(不含正文)。需精确筛选时调用。

  • setup_profile

    设置当前用户名(写入 .aamm/profile.json),供 journal_entry 标记"问的人"。 首次使用前调用一次;之后 who_am_i 会回显该用户名。换人用时再调一次覆盖。

  • update_memory

    更新已有记忆;改 content 会重算向量并刷新 Markdown。修改 / 补充已有记忆时调用。

  • who_am_i

    返回当前 Agent 标识、用户名、项目根、数据目录,以及各分类记忆数与日记数。 会话开始时先调用,了解当前 agent 与记忆库概况,并确认 profile 用户名是否已设置。

Signals

Stars
0
Forks
0
Open issues
0
Weekly downloads
97
Last commit
Jul 15, 2026 (3 months ago)
Last release
Jul 14, 2026 (3 months ago)
Last package publish
Jul 15, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.xiangzi1126/ai-agent-memory-mcp
Version
0.1.1
Auth
No auth
Packages
pypi ai-agent-memory-mcp
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

AI Agent Memory MCP server. Agent Mart. https://agentmart.dev/connectors/xiangzi1126-ai-agent-memory-mcp (last updated 2026-10-24)