Loading MCP server directory, please wait...
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
npx @getmcp/cli add io.github.ayushcodes10/echo-memRequires Python 3.10+. Community-contributed server. Review source before installing.
ECHO_MEMORY_DATABASE_URLPostgres connection string. `echo-memory quickstart` starts a suitable database and prints this.
ECHO_MEMORY_USER_IDWhose memory this is. Scopes every read and write.
ECHO_MEMORY_AGENT_IDWhich tool is writing: claude-code, cursor, codex, claude-desktop. Recorded on every fact, and what makes a cross-tool recall visible afterwards.
Config file: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"io.github.ayushcodes10/echo-mem": {
"command": "uvx",
"args": [
"echo-mem"
],
"env": {
"ECHO_MEMORY_DATABASE_URL": "",
"ECHO_MEMORY_USER_ID": "",
"ECHO_MEMORY_AGENT_ID": ""
}
}
}
}Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.
Ephemeral data sandbox for AI workflows with guardrails and security
MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect.
Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.