SkillAgentSearch skills...

aura-memory

Local cognitive memory runtime for AI agents — durable recall, temporal versioning, provenance, contradiction governance, and portable encrypted storage. Pure Rust, offline-first, with no required LLM or cloud. Patent pending.

Install / Use

claude mcp add teolex2020 -- npx -y github:teolex2020/aura-memory

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

46/100

Supported Platforms

Claude Code
Claude Desktop

{ "name": "aura-memory", "version": "1.5.2", "description": "Cognitive memory layer for AI agents. Gives Claude persistent, self-organizing memory with hierarchical decay, belief formation, and causal reasoning. Zero LLM calls, sub-millisecond recall.", "author": "Alexander Tepliuk", "license": "MIT", "homepage": "https://github.com/teolex2020/aura-memory", "repository": "https://github.com/teolex2020/aura-memory", "keywords": ["memory", "cognitive", "ai", "agents", "llm", "persistent-memory", "rag"], "transport": ["stdio"], "install": { "pip": "pip install aura-memory" }, "run": { "command": "python", "args": ["-m", "aura", "mcp", "{brainPath}"] }, "tools": [ { "name": "recall", "description": "Retrieve relevant memories as context for a query. Call BEFORE answering to check existing knowledge." }, { "name": "recall_structured", "description": "Retrieve memories as structured data with scores, levels, and metadata." }, { "name": "store", "description": "Store a new memory. Levels: working (hours), decisions (days), domain (weeks), identity (months+)." }, { "name": "store_code", "description": "Store a code snippet at DOMAIN level with language metadata." }, { "name": "store_decision", "description": "Store a decision with reasoning and rejected alternatives at DECISIONS level." }, { "name": "search", "description": "Search memory by filters (exact/tag-based). Use for browsing or counting." }, { "name": "insights", "description": "Get memory health stats: decay risks, promotion candidates, conflicts, trends." }, { "name": "consolidate", "description": "Merge similar memory records to reduce bloat." }, { "name": "delete", "description": "Delete a memory record by ID." }, { "name": "get", "description": "Get a specific memory record by ID with full metadata (level, tags, strength)." }, { "name": "maintain", "description": "Run a full maintenance cycle: decay, promote, consolidate, archive. Returns a summary report." } ], "config": { "brainPath": { "type": "string", "description": "Path to brain data directory", "default": "./aura_brain", "required": false }, "password": { "type": "string", "description": "Optional encryption password for encrypted brain", "required": false, "sensitive": true } }, "examples": [ { "title": "Claude Desktop", "description": "Add to claude_desktop_config.json", "config": { "mcpServers": { "aura": { "command": "python", "args": ["-m", "aura", "mcp", "C:\Users\YOUR_NAME\aura_brain"] } } } }, { "title": "Cursor / VS Code", "description": "Add to .cursor/mcp.json or .vscode/mcp.json", "config": { "servers": { "aura": { "command": "python", "args": ["-m", "aura", "mcp", "./aura_brain"], "type": "stdio" } } } } ] }

Related Skills

View on GitHub
GitHub Stars0
CategoryAI
UpdatedNaNy ago
Forks0

Security Score

68/100

Audited on Invalid Date

2 medium1 low