
用于外部内存层的 MCP 服务器,用于 AI 代理 + 更多。从 pypi 下载,开始使用
概览
持续记忆,能记住会话中的决策、理由和矛盾。当上下文窗口关闭时,你的AI会忘记一切。Waggle赋予它一个基于图表的大脑,持续存在。 不是代码索引器。是对话式记忆引擎——它存储你做了什么、为什么做了这个决定以及发生了什么变化,这样下一次会话就能从上一次结束的地方继续。 该仓库是公开的 Waggle 产品仓库:Apache-2.0 授权,可在 GitHub 和 PyPI 上发布,专注于本地优先的内存引擎。 - Python 3.11+ 包,使用 pyproject.toml 构建 - 通过 waggle-mcp 暴露的 MCP 服务器 - 默认支持 SQLite 图存储,可选 Neo4j 后端 - 本地句子变换器嵌入,带有确定性离线备选 - 用于 linting、类型检查、格式化和测试的 Ruff、mypy 和 pytest - 用于拉取请求的 CI/CD 检查 - 用于 app/mcp/graph-ui/ 下捆绑 Graph Studio UI 的 Vite/React 资产 (没有pipx?
概述(AI 翻译)
为人类和人工智能智能体投影记忆。 在对话中保留决策、背景及其背后的原因。
安装Waggle · 试试浏览器工作区 · 文献资料
保持上下文,而不仅仅是对话
Waggle 是一个开源、本地优先的 AI 代理内存层。它存储 项目知识作为图表:你决定了什么,为什么重要,取决于什么 关于,以及发生了什么变化。你们下一次的对话可以从这个语境继续 而不是重新开始。
在你的MCP客户端中使用Waggle,在Graph Studio中检查和编辑内存,或者 将可移植内存图带入浏览器工作区。
- 跨会话继续。 回忆项目决策、需求、偏好, 并且在不反复贴上背景的情况下提出开放性问题。
- 理解推理。 探索关系,支持证据, 矛盾,以及决策背后的历史。
- 保持对更正的控制。 在WebMCP工作区中,代理提出变更建议; 人类在内容变得权威之前,先批准其确切内容。
- 带上内存。 导出和导入
.abhi文件,跨支持范围 工作流程,但不绑定一个客户端。
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
Project memory for humans and AI agents. Keep decisions, context, and the reasons behind them across conversations.
Install Waggle · Try the browser workspace · Documentation
Keep the context, not just the conversation
Waggle is an open-source, local-first memory layer for AI agents. It stores project knowledge as a graph: what you decided, why it matters, what it depends on, and what has changed. Your next conversation can pick up from that context instead of starting over.
Use Waggle with your MCP client, inspect and edit memory in Graph Studio, or bring a portable memory graph into the browser workspace.
- Continue across sessions. Recall project decisions, requirements, preferences, and open questions without repeatedly pasting context.
- Understand the reasoning. Explore relationships, supporting evidence, contradictions, and the history behind a decision.
- Keep control of corrections. In the WebMCP workspace, agents propose changes; humans approve the exact content before it becomes authoritative.
- Take memory with you. Export and import
.abhifiles across supported workflows without tying your graph to one client. - Start locally. The default SQLite store lives on your machine. Local use does not require a Waggle account or an external database.
Quick Start
The Python package requires Python 3.11+ and pipx. On macOS, you can install
pipx with brew install pipx; see the installation guide
for client-specific options.
pipx install waggle-mcp
pipx ensurepath
Restart your terminal after the first pipx ensurepath, then run:
waggle-mcp setup --yes
waggle-mcp doctor
Restart your MCP client to load Waggle. Setup detects supported clients and writes their configuration; automatic memory behavior uses the client’s installed hooks, skills, or project instructions.
To check continuity, ask your agent to remember a project decision, then open a fresh session in the same project and ask what was decided. Keep the same project identifier across sessions.
Choose your client
| Client | Setup guide |
|---|
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手?先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"waggle": {
"command": "waggle-mcp",
"args": ["serve", "--transport", "stdio"]
}
}
}