metatron
面向AI编码代理的Git原生上下文层。您团队的真实工程决策——模式、陷阱、约定——作为已审阅的markdown文件存在于仓库中；代理在编写代码前会查阅这些文件并记录所学。文件优先，无需服务器；MCP作为可选服务层。
Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving layer.
怎么安装
git clone https://github.com/kerbelp/metatron ~/.claude/skills/metatron 简介
Metatron captures a codebase's real implementation decisions — preferred patterns, rejected approaches, edge cases, internal conventions — as structured **decisions**: one markdown file per convention, versioned in git next to the code, consulted by any coding agent that can read a file, and curated through your ordinary pull-request review. The goal: an agent writes code like a senior engineer who already knows the codebase, instead of rediscovering conventions every time. bash pip install getmetatron metatron context setup # one command: your repo carries its own agent context For teams that…
推荐参考
信息
- 协议
- MIT
- 语言
- Python
- GitHub 星标
- 24
- 月下载
- –
- 最近更新
- 2026-09-23
- 创建于
- 2026-06-03
基础安全检查
- 检查结果
- curated 收录但无 npm 包/安装命令
- 收录来源
- curated:punkpeye/awesome-mcp-servers
- 主题标签
- agentic-ai, agentic-workflow, ai-agent, ai-coding-assistant, ai-tools, claude-code, cursor-editor, devtools, llm-tools, mcp, mcp-server, mcp-tools, model-context-protocol, tree-sitter
同类推荐
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight：会学习的 Agent 长期记忆系统，自动召回/保存、知识页、深度反思与按仓库隔离的记忆银行。
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 官方Firecrawl MCP服务器 - 为Cursor、Claude及任何其他LLM客户端添加强大的网页抓取和搜索功能。
dsh-mnemon
omdsh-dev/dsh-mnemon
由 Mnemon 驱动的 DeepSeek Harness（DSH）跨 Agent、本地优先的持久记忆插件。它可在支持 Mnemon 的 Agent 之间共享长期记忆，并提供运行时记忆、可检索项目档案、语义召回、知识图谱和 Sidebar UI。
get-shit-done
gsd-build/get-shit-done
由 TÂCHES 开发的轻量且强大的元提示、上下文工程和规格驱动开发系统，适用于 Claude Code。