Enterprise DNA
M MCP Servers Developer low

ccf/agentcairn

by Various

Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

C

MCP

ccf/agentcairn

Added 13 July 2026

#agentmemory #ai #ai-agents #claude #claude-code #codex #cursor #duckdb

Overview

Agentcairn is a Python tool that gives AI coding agents long-term, cross-project memory by using an Obsidian vault as the source of truth. It operates without a daemon or opaque databases, keeping memory fully under the user's control.

Best for

Best for
Developers who want transparent, file-based memory for AI coding agents using Obsidian

Use cases

  • Persisting agent context across multiple coding sessions
  • Sharing memory between different AI coding agents
  • Maintaining a human-readable, editable memory store in Obsidian

How to use

Install

uvx agentcairn

Tested with

Claude Code, Codex, Cursor

Example client config

auto_recall       = true\nauto_recall_k     = 3\nauto_recall_scope = "project"

Notes

Agentcairn is a Python tool that gives AI coding agents long-term, cross-project memory by using an Obsidian vault as the source of truth. It operates without a daemon or opaque databases, keeping memory fully under the user’s control.

16 stars on GitHub. Last updated 2026-07-13. Licensed Apache-2.0.

Use cases

  • Persisting agent context across multiple coding sessions
  • Sharing memory between different AI coding agents
  • Maintaining a human-readable, editable memory store in Obsidian

Pros

  • Memory is stored in plain Markdown files, not a proprietary database
  • No background daemon required, reducing complexity
  • Cross-project memory helps agents retain context over time

Cons

  • Requires an Obsidian vault, adding a dependency
  • Limited to Python-based agent workflows
  • Small community (16 stars) may mean less support and fewer integrations

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

Pros

  • Memory is stored in plain Markdown files, not a proprietary database
  • No background daemon required, reducing complexity
  • Cross-project memory helps agents retain context over time

Cons

  • Requires an Obsidian vault, adding a dependency
  • Limited to Python-based agent workflows
  • Small community (16 stars) may mean less support and fewer integrations

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

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