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。
| 平台 | 累計安裝 | 累計下載 | 星標 | 評論 |
|---|---|---|---|---|
| ClawHub ↗ | 122 | 3714 | 2 | 1 |
| SkillHub ↗ | 168 | 3742 | 2 | — |
各平台的計數口徑不同,統計時間不一致。
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
以下是根據技能文件生成的示例,不代表實際執行結果。
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 |
|---|---|---|---|
| 2026-09 | 3742 | — | 2 |
| 2026-08 | 3594 | +3.6% | 2 |
| 2026-07 | 3469 | +7.8% | 2 |
| 2026-06 | 3217 | +5.1% | 2 |
| 2026-05 | 3062 | — | 2 |
| 2026-03 | 2395 | — | 2 |
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。
---
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
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.
將開發過程中的經驗、錯誤與修正記錄為 Markdown 檔案,供日後重用並提升為工作區記憶。
用自然語言描述需求,在本機與遠端技能市場尋找技能並取得推薦。
給 AI agent 用的瀏覽器自動化命令列技能。
將使用者明確糾正與自我檢視整理成分層記憶,並依使用情況升級或封存。
在安裝第三方技能之前,按清單審查來源、許可權與危險模式的技能。
將代理記憶與跨技能狀態整理成具型別與約束的知識圖譜。
規劃 AI 代理主動跟進、工作記憶與回顧流程的工作區設定指南。
指導如何建立與更新有效 Claude 技能的寫作指南。
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。