endgegnerbert-tech

muninn

AI 智慧體v2.3.7
作者:endgegnerbert-tech更新於 2026-05-17共 16 個版本 · 最新版本釋出於 2026-02-13@clawhub_endgegnerbert-tech/muninn
上下文管理記憶增強

據 AlphaMoat 統計,截至 2026-09,muninn 累計下載 3,742 次、獲 2 個星標,在全部 5,078 個 AI 技能中排名第 2,851 位,在「AI 智慧體」分類(969 個)中排名第 569 位。

累計安裝
168
累計下載
3742
星標
2
全站排名
#2,851
全站前 57% · 「AI 智慧體」前 59%
平台累計安裝累計下載星標評論
ClawHub ↗122371421
SkillHub ↗16837422—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

Muninn 透過 MCP 服務和 CXP 工作流支援初始化專案、搜尋專案語境並儲存記憶。記憶以 Markdown 檔案形式儲存;它也可能寫入專案狀態或 agent 規則檔案。請限定專案路徑,並在允許其他 agent 採用這些規則前檢查改動。 需要 Node.js 與已審核的 Muninn 套件;核驗 .muninn 索引、記憶寫入及 agent 規則檔案確實限制在目標專案內。

資料釋出於 2026-10-27

可以用來做什麼

  • 初始化專案語境
  • 搜尋程式碼庫中的專案上下文
  • 儲存可檢查的專案記憶

什麼時候用

  • 希望 agent 在專案內查詢上下文或延續專案記憶時
  • 在受控工作區使用,提供明確專案路徑,並檢查產生的記憶、索引與 agent 規則檔案

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

在這個專案中搜尋與當前任務相關的既有上下文,並先列出你準備讀取或修改的檔案;未經確認不要持久化記憶或修改 agent 規則。

月度資料趨勢

累計下載3742
2287306938502026-03 · 累計下載 23952026-05 · 累計下載 30622026-06 · 累計下載 32172026-07 · 累計下載 34692026-08 · 累計下載 35942026-09 · 累計下載 374226-0326-09
星標2
1232026-03 · 星標 22026-05 · 星標 22026-06 · 星標 22026-07 · 星標 22026-08 · 星標 22026-09 · 星標 226-0326-09

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。

月份累計下載環比星標
2026-093742—2
2026-083594+3.6%2
2026-073469+7.8%2
2026-063217+5.1%2
2026-053062—2
2026-032395—2

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 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
展開全部(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 智慧體」分類下的熱門技能

資料月份:2026-09 · 下載/星標/安裝數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。