michielinksee/linksee-memory
by Various
Local-first agent memory MCP - cross-agent brain with token-saving file diff cache. By Synapse Arrows.
MCP
michielinksee/linksee-memory
Added 13 July 2026
Overview
A local-first agent memory MCP that provides a cross-agent brain with a token-saving file diff cache. It is built by Synapse Arrows and written in JavaScript. The tool enables shared memory across multiple AI agents while reducing token usage through diff caching.
Best for
Best for
Developers building multi-agent systems that need local, cost-efficient shared memory
Use cases
- Share memory across multiple AI agents in a local environment
- Reduce token consumption by caching file diffs between agent interactions
- Run agent memory entirely offline without cloud dependencies
How to use
Install
npx -y linksee-memory map where README.md # this file belongs to the README node — and what it touches Tools exposed
Cross-agentread_smartdrift_statuscheck_decisiondeclare_anchorresolve_driftwhere_am_iflag_proposalsresolve_proposalanon_idlinksee_versionsession_turn_countsession_duration_secmcp_serversfile_extensions
Tested with
Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT
Notes
A local-first agent memory MCP that provides a cross-agent brain with a token-saving file diff cache. It is built by Synapse Arrows and written in JavaScript. The tool enables shared memory across multiple AI agents while reducing token usage through diff caching.
13 stars on GitHub. Last updated 2026-07-02. Licensed MIT.
Use cases
- Share memory across multiple AI agents in a local environment
- Reduce token consumption by caching file diffs between agent interactions
- Run agent memory entirely offline without cloud dependencies
Pros
- Local-first design ensures privacy and offline capability
- Token-saving file diff cache reduces API costs
- Enables cross-agent memory sharing for multi-agent systems
Cons
- Small community with only 13 GitHub stars indicates limited adoption
- May lack extensive documentation or support for complex setups
- Early stage project with potential stability or compatibility issues
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Local-first design ensures privacy and offline capability
- Token-saving file diff cache reduces API costs
- Enables cross-agent memory sharing for multi-agent systems
Cons
- Small community with only 13 GitHub stars indicates limited adoption
- May lack extensive documentation or support for complex setups
- Early stage project with potential stability or compatibility issues
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.