cross-agent-memory

仓库创建 2026年7月26日最近提交 1 天前SkillHot 收录 1 天前

▸ 精选理由

让不同 agent 共享经验证的项目上下文，提升协作一致性。

▸ 风险提示

共享记忆需注意避免泄露敏感项目信息。

这个 Skill 做什么

维护跨代理的项目共享记忆层，保存架构与决策但不合并私有记忆。

把项目里各个智能编码代理能共享的一层长期记忆，记录架构、决策、历史和可复用经验，方便代理理解仓库脉络和设计取舍。需要追溯设计原因、对齐跨代理结论或把可靠知识做持久化时用它。特别之处是由仓库持有并经过验证，不会合并或暴露每个客户端的私有 native memory，也不用于未完成工作的交接。

▸ 展开 SKILL.md 英文原文

Maintain broad, verified, client-neutral project memory across Claude Code, Codex, Kimi Code, Antigravity, and other coding-agent harnesses while preserving each client's native or auto-memory. Use when an agent must understand repository history, architecture, feature outcomes, decisions and rationale, reusable lessons, or memory drift; or when durable knowledge must be promoted, reconciled, consolidated, retired, or audited. Do not use for unfinished-work transfer; use cross-agent-handoff instead.

Skill 开发管理共享记忆多代理项目历史语义索引通用

Stars

Forks

仓库内 Skill

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/VladimirGutuev/cross-agent-memory/main/skills/cross-agent-memory/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/VladimirGutuev/cross-agent-memory/main/skills/cross-agent-memory/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Cross-Agent Memory

Let every harness keep its own model-optimized native memory while all agents
share one verified, repository-owned understanding of the project. Never merge
or mirror proprietary native-memory stores.

## Keep the shared memory broad but retrieval narrow

The shared layer may contain:

- semantic knowledge: architecture, system maps, integrations, feature behavior;
- distilled episodic knowledge: verified outcomes, incidents, and failed approaches;
- reflective knowledge: decisions, rationale, patterns, and reusable lessons.

Keep mandatory procedural rules in the repository's agent instructions. Keep raw
session history and client-specific preferences in native memory.

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有