Zero-config AI project memory with live file watching and MCP integration
Zero-config AI project memory with live file watching and MCP integration. That is what the nova memory mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Local-first persistent memory for AI assistants. Store context across sessions with SQLite.
Nova Memory is an MCP (Model Context Protocol) server that gives AI assistants persistent memory. It stores your project context, decisions, and knowledge locally in SQLite - no cloud, no telemetry. Your data stays on your machine.
@nova-mcp/mcp-nova on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 14 tools. What each one is for:
store_memory — Store content with type, tags, and path trackingmemory_search — Full-text search with BM25 rankingmemory_query — Filter by type, tags, project, or pathmemory_stats — Storage statistics and memory countsmemory_delete — Remove memories by IDmemory_tags — List all tags with usage countsmemory_export — Export memories as JSON or markdownmemory_import — Bulk import memories from JSONsearch_semantic — Semantic similarity searchsearch_patterns — Find recurring patterns in memoriessearch_temporal — Time-based memory analysissearch_relationships — Explore memory connectionsThis sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Nova Memory's toolset — store_memory, memory_search, memory_query and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jagdeepsinghdev; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| store_memory | Store content with type, tags, and path tracking |
| memory_search | Full-text search with BM25 ranking |
| memory_query | Filter by type, tags, project, or path |
| memory_stats | Storage statistics and memory counts |
| memory_delete | Remove memories by ID |
| memory_tags | List all tags with usage counts |
| memory_export | Export memories as JSON or markdown |
| memory_import | Bulk import memories from JSON |
| search_semantic | Semantic similarity search |
| search_patterns | Find recurring patterns in memories |
| search_temporal | Time-based memory analysis |
| search_relationships | Explore memory connections |
| analysis_conflicts | Detect contradictions between memories |
| analysis_memory_map | Generate memory visualization |
{
"mcpServers": {
"nova-memory": {
"command": "npx",
"args": ["-y", "@nova-mcp/mcp-nova"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.