Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/rmarquesa/agentmemory-offline/agentmemorygit clone --depth 1 https://github.com/rmarquesa/agentmemory-offlineGrade A, and why
agentmemory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to agentmemory — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"agentmemory": {
"command": "agentmemory",
"args": [
"mcp"
],
"env": {
"AGENTMEMORY_URL": "${AGENTMEMORY_URL:-http://localhost:3111}",
"AGENTMEMORY_SECRET": "${AGENTMEMORY_SECRET:-}",
"AGENTMEMORY_TOOLS": "${AGENTMEMORY_TOOLS:-all}"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 13 lines scan A bb210d9476b3
agentmemory is an MCP server published in the GitHub repository rmarquesa/agentmemory-offline (0 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It is 86% identical to agentmemory, differing in 5 lines, and is treated as a copy.
Other mcp servers, from other repositories
agent-memory-control-plane
MCP server "agent-memory-control-plane" as configured in AlekseiUL/agent-memory-control-plane. Runs locally from the agent-memory-control-plane Python package.
personal-model
Local-first macOS Runtime for screen-context memory, personal modeling, and MCP. Runs locally from the personal-model Python package.
compartment
Compartment - high-security, fully offline, encrypted vector memory for AI agents (MCP). Runs locally from the compartment Python package.
paxm
MCP server "paxm" as configured in pax-beehive/paxm. Launched with sh ${CLAUDE_PLUGIN_ROOT}/scripts/paxm-mcp.sh.
plur
Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP. Runs locally from the @plur-ai/mcp npm package.
memoweft
Portable AI memory as MCP tools: five reads and three controlled writes. Runs locally from the @memoweft/mcp-server npm package. Needs 1 environment variable to run.