Local-first memory engine for AI agents — MCP-native, graph-linked, spaced repetition. Provides episodic memory with retrieval, validation, consolidation, and scoring. CLI + MCP server + local dashboard. AGPL-3.0-or-later. Install: pip install mnemoq. Open-core: proprietary cloud sync tier planned.
View on GitHub →
Try with Claude — $10 free →
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"mnemoq": {
"command": "uvx",
"args": [
"mnemoq"
]
}
}
}
Run in terminal:
claude mcp add mnemoq uvx mnemoq
Add to .cursor/mcp.json:
{
"mcpServers": {
"mnemoq": {
"command": "uvx",
"args": [
"mnemoq"
]
}
}
}
Or install with pip: pip install mnemoq
README Excerpt
Local-first memory engine for AI agents — MCP-native, graph-linked, spaced repetition. ``` Agent ──log──▶ MnemoQ Engine ──store──▶ learnings.jsonl Agent ◀──retrieve── MnemoQ Engine ◀──read── learnings.jsonl Agent ──MCP──▶ mnemoq-mcp ──read/write──▶ learnings.jsonl ``` ```bash pip install mnemoq ``` CLI-only users (no Python project needed):
Tools (20)
actionapi_keycomponentsdomaindomain_mappingsembedding_cache_dirembedding_modelengine_min_versionfiles_touchedimportancemax_stepmnemoqproject_namereasonrerankerreranker_llm_endpointreranker_llm_modelreranker_modelreranker_top_nretrieval_only_agents