Enterprise DNA Enterprise DNA
M MCP Servers Developer low

krimto-labs/krimto

by Various

Open-source team memory layer for AI coding agents — markdown files in git, user→team→org hierarchy, cross-vendor MCP server. Apache-2.0.

MCP

krimto-labs/krimto

Added 7 June 2026

#agent-memory #ai-agents #ai-memory #claude-code #coding-agents #cursor #git #hybrid-search

Overview

Krimto is an open-source team memory layer for AI coding agents. It stores memories as markdown files in a git repository, organized by user, team, and org hierarchy. A cross-vendor MCP server lets agents read and write this shared context.

Best for

Best for
Teams using multiple AI coding agents that need shared, versioned persistent context

Use cases

  • Persisting agent context across coding sessions in git-backed markdown
  • Sharing team-specific knowledge among multiple AI coding agents
  • Structuring memories with user, team, and org levels for multi-agent collaboration

How to use

Install

npx @krimto-labs/krimto init

Tested with

Claude Code, Cursor

Notes

Krimto is an open-source team memory layer for AI coding agents. It stores memories as markdown files in a git repository, organized by user, team, and org hierarchy. A cross-vendor MCP server lets agents read and write this shared context.

5 stars on GitHub. Last updated 2026-06-02. Licensed Apache-2.0.

Use cases

  • Persisting agent context across coding sessions in git-backed markdown
  • Sharing team-specific knowledge among multiple AI coding agents
  • Structuring memories with user, team, and org levels for multi-agent collaboration

Pros

  • Open source with Apache-2.0 license, no vendor lock-in
  • Uses git for version control and familiar workflow
  • Cross-vendor MCP server works with different AI coding tools

Cons

  • Requires a git workflow and repository setup
  • Markdown files may become unwieldy for large or rapidly changing memories
  • Early-stage project with limited adoption (5 stars)

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Open source with Apache-2.0 license, no vendor lock-in
  • Uses git for version control and familiar workflow
  • Cross-vendor MCP server works with different AI coding tools

Cons

  • Requires a git workflow and repository setup
  • Markdown files may become unwieldy for large or rapidly changing memories
  • Early-stage project with limited adoption (5 stars)
Free 27-page guide

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.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks