Aura Memory MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
pip install aura-memory
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add aura-memory -- node "<FULL_PATH_TO_AURASDK>/dist/index.js"

Replace <FULL_PATH_TO_AURASDK>/dist/index.js with the actual folder you prepared in step 1.

README.md

Cognitive Layer That Makes Your AI Model Smarter Over Time

AuraSDK

Cognitive Layer That Makes Your AI Model Smarter Over Time
Self-learning · No fine-tuning · No cloud training · <1ms recall · ~3 MB

     


Your AI model is smart. But it forgets everything after every conversation — and it never gets smarter from experience.

AuraSDK is a cognitive layer that runs alongside any LLM. It observes every interaction, builds beliefs from patterns, discovers causal relationships, and derives behavioral policies — all locally, without fine-tuning or cloud training. The longer it runs, the smarter your agent becomes.

pip install aura-memory
from aura import Aura, Level

brain = Aura("./agent_memory")
brain.enable_full_cognitive_stack()  # activate all 5 cognitive layers

# store what happens
brain.store("User always deploys to staging first", level=Level.Domain, tags=["workflow"])
brain.store("Staging deploy prevented 3 production incidents", level=Level.Domain, tags=["workflow"])

# recall — cognitive layer automatically surfaces relevant patterns
context = brain.recall("deployment decision")  # <1ms, no API call

# after enough interactions, the system derives this on its own:
hints = brain.get_surfaced_policy_hints()
# → [{"action": "Prefer", "domain": "workflow", "description": "deploy to staging first"}]

No API keys. No embeddings. No cloud. The model stays the same — your agent gets smarter.

⭐ If AuraSDK is useful to you, a GitHub star helps us get funding to continue development from Kyiv.


Why Aura?

Aura Mem0 Zep Cognee Letta/MemGPT
Architecture 5-layer cognitive engine Vector + LLM Vector + LLM Graph + LLM LLM orchestration
Self-learning without LLM Yes — Belief→Causal→Policy No No No No
Behavioral policies from experience Yes — automatic No No No No
LLM required No Yes Yes Yes Yes
Recall latency <1ms ~200ms+ ~200ms LLM-bound LLM-bound
Works offline Fully Partial No No With local LLM
Cost per operation $0 API billing Credit-based LLM + DB cost LLM cost
Binary size ~3 MB ~50 MB+ Cloud service Heavy (Neo4j+) Python pkg
Memory decay & promotion Built-in Via LLM Via LLM No Via LLM
Trust & provenance Built-in No No No No
Encryption at rest ChaCha20 + Argon2 No No No No
Language Rust Python Proprietary Python Python

The Core Idea: Cheap Model + Aura > Expensive Model Alone

Fine-tuning costs thousands of dollars and weeks of work. RAG requires embeddings and a vector database. Context windows are expensive per token.

Aura gives you a third path: a cognitive layer that accumulates experience between conversations — free, local, sub-millisecond.

Week 1: GPT-4o-mini + Aura                Week 1: GPT-4 alone
  → average answers                          → average answers

Week 4: GPT-4o-mini + Aura                Week 4: GPT-4 alone
  → knows your workflow                      → still forgets everything
  → surfaces patterns you repeat             → same cost per token
  → warns before risky actions

Tools (8)

recallSurfaces relevant patterns from memory with sub-millisecond latency.
recall_structuredRetrieves structured memory data based on specific criteria.
storeStores information into the cognitive memory layer.
store_codeStores code snippets into the cognitive memory layer.
store_decisionStores a decision-making event for future pattern recognition.
searchPerforms a search across stored cognitive memories.
insightsRetrieves derived insights from accumulated memory patterns.
consolidateTriggers the consolidation of memory layers to refine behavioral policies.

Configuration

claude_desktop_config.json
{"mcpServers": {"aura-memory": {"command": "python", "args": ["-m", "aura.mcp"]}}}

Try it

Store the fact that I prefer to deploy to staging before production.
Recall any patterns related to my recent deployment decisions.
What insights have you derived from my recent project interactions?
Store this code snippet as a reusable pattern for my authentication module.
Search my memory for previous warnings about risky actions in this codebase.

Frequently Asked Questions

What are the key features of Aura Memory?

Sub-millisecond recall of stored patterns. Fully offline operation with no cloud training required. Automatic derivation of behavioral policies from experience. Encryption at rest using ChaCha20 and Argon2. Self-learning cognitive engine with 5 distinct layers.

What can I use Aura Memory for?

Maintaining long-term context of user preferences across sessions. Building a personalized agent that learns specific project workflows. Storing and retrieving code patterns without external vector databases. Automating the identification of causal relationships in user behavior.

How do I install Aura Memory?

Install Aura Memory by running: pip install aura-memory

What MCP clients work with Aura Memory?

Aura Memory works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Aura Memory docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare