Global Agent Memory logo

Global Agent Memory

Local-first Markdown MCP memory with human review, Obsidian vault, and owner dashboard.

Open source

Global Agent Memory is an open-source local-first memory system (PyPI `global-memory-mcp` 0.1.6, MIT) that keeps Markdown as the canonical vault, exposes a frozen MCP v1 contract to Claude Code, Codex, and other MCP clients, and lets owners approve candidates, protect sensitive memories, and administer projects from a local dashboard—with SQLite FTS5 keyword search and optional Ollama + sqlite-vec hybrid ranking.

Selection advice

Choose Global Agent Memory when multiple coding agents should share one owner-controlled Markdown vault with explicit approval and access controls. Choose EverOS for a broader Markdown memory OS surface, or Mem0 when memory must live inside application code you ship.

Quick comparison

Global Agent Memory centers a human-reviewed Markdown vault shared across MCP coding agents. EverOS also treats Markdown as source of truth, while Mem0 embeds memory primarily through application SDKs.

Global Agent MemoryEverOSMem0
Best forShared, reviewable project memory across Claude Code, Codex, and other MCP clientsPortable Markdown-native memory OS across local agent workflowsEmbedding user memory inside a product you ship
Storage modelCanonical Markdown vault + rebuildable SQLite/FTS indexes; optional Ollama vectorsMarkdown source of truth with SQLite and LanceDB indexesSDK-managed memory with self-hosted and managed options
GovernanceCandidates require owner approval; Standard/Protected/Sealed visibility levelsLocal-first runtime with reflection and knowledge-wiki surfacesApplication-controlled APIs rather than an owner review dashboard
TradeoffStrong local control and review workflow; requires installing and running a local daemonBroad coding-assistant portability; less emphasis on candidate approval queuesFast product embedding; less file-native Obsidian-style ownership

Best for

  • local-first shared agent memory
  • human-reviewed durable knowledge
  • Obsidian-compatible Markdown vaults
  • MCP coding agents on macOS or Linux

Not ideal for

  • teams that want a fully managed memory SaaS
  • Windows-only workflows (installer targets macOS and Linux)
  • products that need an embeddable hosted memory API for end users

Core concepts

Markdown vault as source of truthcandidate review before durable memoryfrozen MCP v1 contractproject-aware retrievalProtected and Sealed visibility

Minimal implementation shape

Install with `uv tool install global-memory-mcp`, run `global-memory setup`, then ask a connected agent to load project context or propose a candidate via MCP tools such as `memory_context` and `memory_remember`.

Sources