Skip to main content
Glama

kiro-recall

一个本地 MCP 记忆服务器,适用于 Kiro CLI,为你的 AI 助手提供跨会话的持久化、语义化记忆。

Kiro Crew 记忆架构启发——重新实现为轻量级、自包含系统,使用 SQLite + Ollama 嵌入,以 Obsidian 作为人类可读的同步目标。

功能

  • 语义记忆 — 结构化键值事实(pref.editor: Neovimproject.active: MyProject

  • 情景记忆 — 随时间衰减的对话片段(约 23 天半衰期)

  • 经验教训 — 覆盖所有其他记忆的修正和规则(最高优先级)

  • 语义召回 — 通过 Qwen3-Embedding 进行向量相似度搜索(1024 维,本地运行)

  • Obsidian 同步 — 将记忆渲染为带 [[wikilinks]] 的 Markdown,用于图谱导航

Related MCP server: tartarus-mcp

架构

┌──────────────────────────────────────────┐
│  Kiro CLI / any MCP client               │
│  Tools: Remember, Recall, Learn, Forget  │
└──────────────┬───────────────────────────┘
               │ stdio (MCP protocol)
       ┌───────▼───────┐          ┌─────────────────┐
       │  memory.db    │  sync →  │  Obsidian Vault  │
       │  (SQLite)     │          │  (Markdown)      │
       └───────┬───────┘          └─────────────────┘
               │
       ┌───────▼───────┐
       │  Ollama       │
       │  qwen3-embed  │
       │  (localhost)   │
       └───────────────┘

系统要求

  • macOS 或 Linux

  • Python 3.10+

  • Ollama(用于本地嵌入)

  • uv(推荐)或 pip

安装

git clone https://github.com/YOUR_USERNAME/kiro-recall.git
cd kiro-recall
bash install.sh

安装脚本将:

  1. 安装 Ollama(如果不存在)并将其作为服务启动

  2. 拉取 qwen3-embedding:0.6b 模型

  3. 创建 Python 虚拟环境并安装依赖

  4. 将 MCP 服务器配置安装到 ~/.kiro/settings/mcp.json

  5. 将引导文件安装到 ~/.kiro/steering/obsidian-memory.md

  6. 可选:从现有 Obsidian 仓库导入记忆

手动设置

如果你不想使用安装脚本:

# 1. Install Ollama and the embedding model
brew install ollama  # or: curl -fsSL https://ollama.com/install.sh | sh
brew services start ollama
ollama pull qwen3-embedding:0.6b

# 2. Create venv and install deps
uv venv .venv
uv pip install "mcp[cli]>=1.0.0" "httpx>=0.27.0"

# 3. Copy to ~/.kiro/memory
mkdir -p ~/.kiro/memory
cp server.py db.py embed.py obsidian_sync.py ~/.kiro/memory/

# 4. Add to MCP config (see install.sh for the JSON patch)

MCP 工具

工具

描述

Remember

存储事实、情景或经验教训

Recall

跨所有记忆进行语义搜索

Learn

存储高优先级修正/规则

Forget

按键或 ID 删除记忆

MemoryStats

显示各记忆层级的数量

记忆层级

层级

优先级

衰减

使用场景

经验教训

最高

"始终使用 wikilinks"、"绝不假设区域"

语义

无(原地更新)

关于用户/项目的结构化事实

情景

exp(-0.03 × 天数)

对话片段、决策

键格式

  • pref.* — 用户偏好(pref.themepref.voicepref.editor

  • project.* — 活跃项目(project.activeproject.stack

  • user.* — 用户事实(user.roleuser.companyuser.tools

Obsidian 同步

手动运行或通过 cron 运行:

~/.kiro/memory/.venv/bin/python ~/.kiro/memory/obsidian_sync.py

输出:

  • Memory/Semantic.md — 按前缀分组的所有事实

  • Memory/Lessons.md — 按类别分组的修正

  • Sessions/YYYY-MM-DD.md — 今日的情景记忆

配置

通过环境变量设置 Obsidian 仓库路径(安装时提示,保存到 ~/.kiro/memory/.env):

export KIRO_MEMORY_VAULT="$HOME/Documents/Obsidian/My Vault"

默认值为 ~/Documents/Obsidian/Kiro Knowledge Base

Ollama 端点在 embed.py 中设置:

OLLAMA_URL = "http://localhost:11434/api/embed"
MODEL = "qwen3-embedding:0.6b"

许可证

MIT

A
license - permissive license
Not graded
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    A local, fully-offline MCP memory server that enables persistent storage and retrieval of information using SQLite with both keyword and semantic vector search capabilities.
    10
    78
    12
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    A local-first MCP memory server providing persistent, searchable memory for AI agents, powered by SQLite.
    5
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    A fully local, self-hosted memory server for MCP clients (Claude Code, Cursor, etc.) that provides persistent memory storage with semantic search, using local embeddings and a local Qdrant vector store.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    MCP server that provides semantic memory with search, related-content traversal, and write-back capabilities, all powered by local embeddings of your notes, documents, and chat histories.
    14
    MIT

View all related MCP servers

Related MCP Connectors

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fredluckham/kiro-recall'

If you have feedback or need assistance with the MCP directory API, please join our Discord server