Persistent memory for AI agents β 55 MCP tools, spreading activation recall.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Your AI agent forgets everything between sessions. Neural Memory gives it a brain.
Website Β· Quickstart Β· MCP Tools Β· Pro Β· Changelog
Memories are stored as interconnected neurons and recalled through spreading activation β the same way the human brain works. No vector database. No API calls. No monthly embedding bill.
Restart your AI tool. Your agent now remembers β no init needed, the MCP server auto-initializes on first use.
Already installed? nmem update upgrades in place and detects whether you installed via pip or from source. nmem update --check only reports what is available.
The CLI is
nmem(or the longerneural-memory). There is nonmbinary.
63 MCP tools are available, but you only need three:
| Tool | What it does |
|---|---|
nmem_remember | Store a memory β auto-detects type, tags, and connections |
nmem_recall | Recall through spreading activation β related memories surface naturally |
nmem_health | Brain health score (AβF) with actionable fix suggestions |
Everything else β sessions, context loading, habit tracking, maintenance β works transparently in the background.
Most memory tools are search engines. Neural Memory is a graph that thinks.
When you ask "Why did Tuesday's outage happen?", a vector database returns the most similar sentence. Neural Memory traces the chain:
Relationships are explicit β CAUSED_BY, LEADS_TO, RESOLVED_BY, CONTRADICTS β so your agent doesn't just find memories, it reasons through them.
| Search-based (RAG) | Neural Memory | |
|---|---|---|
| Retrieval | Similarity score | Graph traversal |
| Relationships | None | 24 explicit types |
| LLM required | Yes (embedding) | No β fully offline |
| Multi-hop reasoning | Multiple queries | One traversal |
| Memory lifecycle | Static | Decay, reinforcement, consolidation |
| Cost per 1K queries | ~$0.02 | $0.00 |
Sync your brain across every machine. Unlike other memory tools, we never store your data.
You deploy the sync hub to your own Cloudflare account (free tier). Your D1 database, your encryption key, your data. We provide the code β you own the infrastructure.
Sync uses Merkle delta β only diffs travel, not the full brain. Fast, efficient, private.
nmem config preset {balanced,safe-cost,max-recall,chat-heavy} tune the brain for SaaS, frugal mode, deep retention, or conversational agentsnmem_causal exposes temporal_range and temporal_neighborhood actions; see the Temporal Recall Recipes guide.db files to Telegram for offsite backupFree Neural Memory is complete β 63 tools, unlimited memories, fully offline. You never have to pay.
But past 10K memories, things change. Keyword matching misses semantically related content. Consolidation slows to minutes. Storage grows unbounded. If your agent's brain is getting big, Pro makes it smart.
| Free (SQLite) | Pro (InfinityDB) | |
|---|---|---|
| Recall | Keyword match (FTS5) | Semantic similarity (HNSW) |
| Speed at 1M neurons | ~500ms | <5ms |
| Scale tested | ~50K neurons | 2M+ neurons |
| Compression | Text-level trimming | 5-tier vector compression (97% savings) |
| Consolidation | O(NΒ²) brute-force | O(NΓk) HNSW clustering |
| Storage per 1M | ~5 GB | ~1 GB |
| Cloud sync | Manual push/pull | Merkle delta (auto, diffs only) |
$9/mo β 30-day money-back guarantee. All free tools keep working. Downgrade anytime, keep your data.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/neural-memory)<a href="https://allmcps.com/mcp/neural-memory"><img src="https://allmcps.com/api/badge/neural-memory?style=directory" alt="Neural Memory on AllMCPs" /></a>