Neural Memory

Memories are stored as interconnected neurons and recalled through spreading activation — 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 — noinitneeded, the MCP server auto-initializes on first use.

Already installed?nmem updateupgrades in place and detects whether you installed via pip or from source.nmem update --checkonly reports what is available.

The CLI isnmem(or the longerneural-memory). There is nonmbinary.

63 MCP tools are available, but you only need three:

Everything else — sessions, context loading, habit tracking, maintenance — works transparently in the background.

Most memory tools are search engines. Neural Memory is agraph that thinks.

When you ask "Why did Tuesday's outage happen?", a vector database returns the most similar sentence. Neural Memory traces the chain:

outage ← CAUSED_BY ← JWT expiry ← SUGGESTED_BY ← Alice's review

Relationships are explicit—CAUSED_BY,LEADS_TO,RESOLVED_BY,CONTRADICTS— so your agent doesn't just find memories, itreasonsthrough them.

Cloud Sync — Your Data, Your Infrastructure

Sync your brain across every machine. Unlike other memory tools,we never store your data.

Laptop ←→ Your Cloudflare Worker ←→ Desktop ↕ Your Phone

You deploy the sync hub toyour own Cloudflare account(free tier). Your D1 database, your encryption key, your data. We provide the code — you own the infrastructure.

nmem sync # push/pull changes nmem sync --auto # auto-sync after every remember/recall

Sync usesMerkle delta— only diffs travel, not the full brain. Fast, efficient, private.

- Train from documents— PDF, DOCX, PPTX, HTML, JSON, XLSX, CSV ingested into permanent brain knowledge
- Import adapters— migrate from ChromaDB, Mem0, Cognee, Graphiti, LlamaIndex in one command

- Memory consolidation— episodic memories mature into semantic knowledge over time
- Compression tiers— full → summary → essence → ghost → metadata (reclaim storage, keep meaning)
- Brain versioning— snapshot, rollback, diff, transplant memories between brains

- Brain Store— browse, import, and publish pre-built brains to the community marketplace
- 3 seed brains— Python Best Practices, Git Workflows, Docker Essentials (ready to import)

# Store memories (type auto-detected) nmem remember "Fixed auth bug with null check in login.py:42" nmem remember "We decided to use PostgreSQL" --type decision nmem todo "Review PR #123" --priority 7 # Recall nmem recall "auth bug" nmem recall "database decision" --depth 2 # Brain management nmem brain list && nmem brain health nmem brain export -o backup.json # Sync across devices nmem sync --full # Web dashboard nmem serve # http://localhost:8000/dashboard

import asyncio from neural_memory import Brain from neural_memory.storage import InMemoryStorage from neural_memory.engine.encoder import MemoryEncoder from neural_memory.engine.retrieval import ReflexPipeline async def main(): storage = InMemoryStorage() brain = Brain.create("my_brain") await storage.save_brain(brain) storage.set_brain(brain.id) encoder = MemoryEncoder(storage, brain.config) await encoder.encode("Met Alice to discuss API design") await encoder.encode("Decided to use FastAPI for backend") pipeline = ReflexPipeline(storage, brain.config) result = await pipeline.query("What did we decide about backend?") print(result.context) # "Decided to use FastAPI for backend" asyncio.run(main())

Free Neural Memory is complete — 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 recalls by keyword. Pro recalls by meaning.

Query: "authentication improvements" Free (FTS5): 2 results — exact matches only Pro (HNSW): 7 results — includes "JWT rotation", "session hardening", "OAuth migration"

- Cone Queries— adjustable semantic recall. Narrow the cone for precision, widen for exploration
- Smart Merge— consolidation that scales to 1M+ neurons using HNSW neighbor clustering
- Directional Compression— compress along multiple semantic axes while preserving meaning
- 5-Tier Auto Lifecycle— memories flow from float32 → float16 → int8 → binary → metadata. Auto-promote on access

pip install neural-memory # Pro features included nmem shared activate --key NM-PRO-XXXX-XXXX-XXXX # activate license nmem shared status # verify: Pro: Active

/plugin marketplace add nhadaututtheky/neural-memory /plugin install neural-memory@neural-memory-marketplace

{ "mcpServers": { "neural-memory": { "command": "nmem-mcp" } } }

Skill — one click via ClawHub.Published on every release:

Plugin — memory slot replacement.Use this if you want NeuralMemory tobeOpenClaw's memory provider rather than a skill it calls:

pip install neural-memory && npm install -g neuralmemory

Set memory slot in~/.openclaw/openclaw.json:

{ "plugins": { "slots": { "memory": "neuralmemory" } } }

Already using Neural Memory? Just activate your key:

nmem shared activate --key NM-PRO-XXXX-XXXX-XXXX # activate license

Then enable InfinityDB (semantic search engine):

# ~/.neuralmemory/config.toml storage_backend = "infinitydb"

Restart your MCP server. Existing memories are auto-migrated from SQLite to InfinityDB on first startup.