AI & Machine Learning

agentmemo.dev

Manages persistent memory for users or agents, allowing storage, semantic retrieval, deletion, and context injection for LLM systems.

1 endpoint7 known toolsFirst detected July 6, 2026Last detected September 6, 2026

ENDPOINT 1

https://agentmemo.dev/mcp

No auth detected

MCP server metadata

Name: agentmemo
Version: 1.0.0

Capabilities

tools

Server instructions

AgentMemo gives agents persistent memory. Use store_memory to remember facts, retrieve_memory to recall them semantically, forget_memory to delete, and get_usage to check quota.

Known tools 7

store_memory

Store a memory for a user/agent.

Inferred read-only

retrieve_memory

Semantically search a user's memories and return the most relevant ones, ranked by similarity.

Inferred read-only

forget_memory

Delete a specific memory by id, or all memories for a user (optionally an agent).

Potential side effects

get_usage

Get usage for the calling API key: operations used this month, tier, and limit.

Inferred read-only

get_context

Get a user's memories pre-formatted for LLM system-prompt injection.

Inferred read-only

give_feedback

Update a memory's outcome (success/failure) after it was used.

Potential side effects

get_stats

Comprehensive memory statistics and quality score.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentmemo]
url = "https://agentmemo.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentmemo": {
      "type": "http",
      "url": "https://agentmemo.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentmemo
Remote MCP URL: https://agentmemo.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentmemo": {
      "url": "https://agentmemo.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentmemo": {
      "type": "http",
      "url": "https://agentmemo.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentmemo",
  "transport": "streamable-http",
  "url": "https://agentmemo.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agentmemo.dev was fetched 2026-08-20T00:20:16.076Z.

Trust status Neutral

agentmemo.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.