Enterprise DNA
M MCP Servers Developer low

teolex2020/AuraSDK

by Various

Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.

T

MCP

teolex2020/AuraSDK

Added 1 June 2026

#agent #ai #ai-agents #cognitive #embedded #encryption #llm #memory

Overview

AuraSDK provides cognitive memory for AI agents as a pure Rust library. It supports sub-millisecond recall, weighs 2.7MB, and runs entirely offline with no cloud dependency. The project is patent pending as of its last update.

Best for

Best for
Developers building privacy-focused, local AI agents in Rust who need minimal latency memory

Use cases

  • Embedding fast memory recall into local AI agents
  • Building privacy-preserving agent workflows without cloud latency
  • Lightweight memory layer for resource-constrained Rust-based agents

How to use

Install

pip install aura-memory

Tools exposed

  • recall_structured
  • store_code
  • store_decision

Tested with

Claude Desktop, Cursor, Continue, VS Code, ChatGPT

Notes

AuraSDK provides cognitive memory for AI agents as a pure Rust library. It supports sub-millisecond recall, weighs 2.7MB, and runs entirely offline with no cloud dependency. The project is patent pending as of its last update.

69 stars on GitHub. Last updated 2026-05-15. Licensed MIT.

Use cases

  • Embedding fast memory recall into local AI agents
  • Building privacy-preserving agent workflows without cloud latency
  • Lightweight memory layer for resource-constrained Rust-based agents

Pros

  • Extremely fast recall under 1ms for real-time agent interactions
  • Zero cloud dependencies ensure privacy and offline operation
  • Small footprint (2.7MB) ideal for edge or embedded deployments

Cons

  • Early stage with only 69 GitHub stars, limited community or third-party support
  • Only available in Rust, narrowing integration for non-Rust agent stacks
  • Patent pending may impose future licensing constraints

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Extremely fast recall under 1ms for real-time agent interactions
  • Zero cloud dependencies ensure privacy and offline operation
  • Small footprint (2.7MB) ideal for edge or embedded deployments

Cons

  • Early stage with only 69 GitHub stars, limited community or third-party support
  • Only available in Rust, narrowing integration for non-Rust agent stacks
  • Patent pending may impose future licensing constraints
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks