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。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 122 | 3,714 | 2 | 1 |
| SkillHub ↗ | 168 | 3,742 | 2 | — |
各平台的计数口径不同,统计时间不一致。
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
以下是根据技能文档生成的示例,不代表实际运行结果。
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 |
|---|---|---|---|
| 2026-09 | 3,742 | — | 2 |
| 2026-08 | 3,594 | +3.6% | 2 |
| 2026-07 | 3,469 | +7.8% | 2 |
| 2026-06 | 3,217 | +5.1% | 2 |
| 2026-05 | 3,062 | — | 2 |
| 2026-03 | 2,395 | — | 2 |
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。
---
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.
把开发过程中的经验、错误与纠正记录为 Markdown 文件,供后续复用并晋升为工作区记忆。
用自然语言描述需求,在本地与远程技能市场里找技能并给出推荐的技能。
给 AI agent 用的浏览器自动化命令行技能。
把用户纠正与自我复盘沉淀成分层记忆、并按使用情况升降级的技能。
在安装第三方技能之前,按清单审查来源、权限与危险模式的技能。
把 agent 的记忆与跨技能状态存成带类型和约束的知识图谱的技能。
一份为 AI 代理规划主动跟进、工作记忆与复盘流程的工作区配置指南。
指导如何创建与更新有效 Claude 技能的写作指南。
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。