AgentMemorySync: Cross-Client Memory
Sync project context and preferences across AI coding clients
- Problem
- When users switch AI clients (e.g., from Cursor to Claude Code), they must reintroduce project background, test frameworks, and personal preferences from scratch. The experience is fragmented and repetitive.
- Solution
- A local-first memory layer that stores project context, user preferences, and common instructions in a standard format, then syncs them to multiple AI clients via plugins or MCP, letting agents inherit memory seamlessly.
- Users
- Developers who frequently switch AI coding assistants, multi-tool users
- MVP
- JSON-based memory storage; CLI for import/export; VS Code and Claude Code plugins to read memory; basic conflict resolution.
- Revenue
- Free core sync; paid cloud backup, team-shared memory, more client support.
- Why now
- AI coding tools are proliferating, but memory silos are a real pain point. Cross-tool sync is a clear need.
Source discussions · 2
- Hacker NewsShow HN: Rutter – shared decision memory across AI tools1↑ 0
- V2EX[分享创造] 换一个客户端,你的 agent 就重新认识你一遍0↑ 4