Developer · Local MCP server

Agent Memory Os

Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.yamantaka520/agent-memory-os
Version
1.10.1
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI
Published
2026-09-22
Updated
2026-09-22
Publisher
yamantaka520 (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/yamantaka520) · how
Repository
github.com/yamantaka520/Agent-Memory-OS
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIagent-memory-os1.10.1stdioAGENT_MEMORY_AGENT_ID, AGENT_MEMORY_HOME

How to connect Agent Memory Os

Agent Memory Os runs locally from a Python package published to PyPI: agent-memory-os version 1.10.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx agent-memory-os. It reads these environment variables: AGENT_MEMORY_AGENT_ID and AGENT_MEMORY_HOME; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "agent-memory-os": {
      "command": "uvx",
      "args": [
        "agent-memory-os"
      ],
      "env": {
        "AGENT_MEMORY_AGENT_ID": "<value>",
        "AGENT_MEMORY_HOME": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
Agent MemoryPersistent agent memory with a decision layer: replay, restore, verify, or none - explainable.Local · stdioPyPI: agent-memory-sdk
Agent MemoryGit-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.Local · stdionpm: @xchucx/agent-memory
Agent Memory MCPAgent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.Local · stdionpm: @kiraautonoma/agent-memory-mcp
Agent Memory MCPMarkdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.Local · stdionpm: @xultrax-web/agent-memory-mcp
Agent Never Give UpAn escape guide for coding agents, providing structured thinking tools to help agents unstick.Local · stdionpm: agent-never-give-up-mcp
Agent ObservabilityTrace AI agent execution: every tool call, every error, every dollar. Open source, local-first.Local · stdionpm: agent-obs
Agent ObservabilityAI agent observability with deterministic record/replay for debugging agent failures.Local · stdioPyPI: agent-observability-trace-cli
Agent Output GuardValidate and verify data from other agents before acting on it. Zero LLM costs.Local · stdionpm: @agenson-horrowitz/agent-output-guard-mcp