endgegnerbert-tech

muninn

AI 智能体v2.3.7
作者:endgegnerbert-tech更新于 2026-05-17共 16 个版本 · 最新版本发布于 2026-02-13@clawhub_endgegnerbert-tech/muninn
上下文管理记忆增强

据 AlphaMoat 统计,截至 2026-09,muninn 累计下载 3,742 次、获 2 个星标,在全部 5,078 个 AI 技能中排名第 2,851 位,在「AI 智能体」分类(969 个)中排名第 569 位。

累计安装
168
累计下载
3,742
星标
2
全站排名
#2,851
全站前 57% · 「AI 智能体」前 59%
平台累计安装累计下载星标评论
ClawHub ↗1223,71421
SkillHub ↗1683,7422—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

Muninn 通过 MCP 服务和 CXP 工作流支持初始化项目、搜索项目语境并保存记忆。记忆以 Markdown 文件形式存储;它也可能写入项目状态或 agent 规则文件。请限定项目路径,并在允许其他 agent 采用这些规则前检查改动。 需要Node.js和已审核的Muninn包;核验.muninn索引、记忆写入及agent规则文件确实限制在目标项目内。

资料发布于 2026-10-27

可以用来做什么

  • 初始化项目语境
  • 搜索代码库中的项目上下文
  • 保存可检查的项目记忆

什么时候用

  • 希望 agent 在项目内查找上下文或延续项目记忆时
  • 在受控工作区使用,提供明确项目路径,并检查生成的记忆、索引与 agent 规则文件

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

在这个项目中搜索与当前任务相关的既有上下文,并先列出你准备读取或修改的文件;未经确认不要持久化记忆或修改 agent 规则。

月度数据趋势

累计下载3,742
2,2873,0693,8502026-03 · 累计下载 2,3952026-05 · 累计下载 3,0622026-06 · 累计下载 3,2172026-07 · 累计下载 3,4692026-08 · 累计下载 3,5942026-09 · 累计下载 3,74226-0326-09
星标2
1232026-03 · 星标 22026-05 · 星标 22026-06 · 星标 22026-07 · 星标 22026-08 · 星标 22026-09 · 星标 226-0326-09

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份累计下载环比星标
2026-093,742—2
2026-083,594+3.6%2
2026-073,469+7.8%2
2026-063,217+5.1%2
2026-053,062—2
2026-032,395—2

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

2.9 KB · ClawHub v2.3.7
---
name: muninn
version: 2.3.7
homepage: https://www.muninn.space
description: Universal Context Protocol (CXP) for AI agents. v2.3.7 includes the latest high-performance CXP engine (compiled 2026-02-13) with fix for memory amnesia, macOS binary support, and pfeilschnell indexing. Created by @Blackknight1dev.
metadata: {"clawdbot":{"emoji":"🐦⬛","requires":{"bins":["node"]},"install":[{"id":"npm","kind":"node","package":"muninn-core","version":"2.3.7","bins":["muninn-core"],"label":"Install Muninn Core"}]}}
---

# Muninn - The Universal Memory Layer
展开全部(共 45 行)
Muninn is an advanced per-project memory system designed for AI agents. It uses the **Context Exchange Protocol (CXP)** to provide high-performance, token-efficient context management.

## 🛡️ Security & Privacy (Local-First)

Muninn is designed with a **Privacy-First** philosophy. 
- **Local Storage**: All project indexes and memories are stored **exclusively on the host machine** within the `.muninn/` folder (per project) or `~/.muninn/` (for global settings).
- **No Data Exfiltration**: Muninn **does not transmit** any code, context, or memories to third-party servers or remote APIs. All processing (semantic search, indexing, and context injection) happens locally using the high-performance Rust-based CXP engine.
- **Transparent Control**: Memories are stored as standard Markdown files. You can inspect, edit, or delete them at any time.

## ⚙️ Integration

Muninn operates as an MCP (Model Context Protocol) server. 

### 🚀 The Muninn Protocol (ENFORCED)

As an agent, you MUST follow the "Brain-First" workflow to remain efficient and accurate. The MCP server ensures project safety by validating context before allowing sensitive tool operations.

1.  **Orient Yourself (`brain_check`)**: Call this at the start of every session or when switching projects. It loads the local project index and identifies key files and patterns.
2.  **Search Before You Code (`search_context`)**: Never assume you know the codebase. Use local semantic search to find existing patterns or prior decisions.
3.  **Learn as You Go (`add_memory`)**: Every significant fix, architectural decision, or user preference should be saved locally as a memory.

## 🛠 Tool Reference (MCP)

- **`init_project`**: Initialize a local Muninn Brain in a project directory.
- **`brain_check`**: MANDATORY orientation step. Loads local context and patterns.
- **`add_memory`**: Persist facts and decisions to the local `.muninn/memories` folder.
- **`search_context`**: Query the local project index semantically.
- **`reindex_context`**: Rebuild the local semantic index.
- **`health_check`**: Verify the status of the local Muninn system.

---

## 🦞 Pro-Tip for Agents
Muninn surgically retrieves only what's needed. Instead of reading large files, use `search_context` to find the exact lines that matter. This significantly reduces context window overhead and token costs while keeping your work strictly local and secure.

「AI 智能体」分类下的热门技能

数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。