MCP App StoreMCP App Store
from memories20
Guides developers integrating with the memories.sh SDKs (@memories.sh/core and @memories.sh/ai-sdk) for programmatic memory reads, writes, and AI-context inject
The memories-sdk skill documents how to integrate the memories.sh SDKs into application code. It covers choosing between @memories.sh/core for backend typed access and @memories.sh/ai-sdk when using the Vercel AI SDK, shows quick start examples, and provides patterns for scoping (tenantId/userId/projectId), middleware usage, and safe API key handling.
Use this skill when you are implementing memory-backed features: injecting prior context into AI prompts, persisting agent outputs as memories, performing programmatic reads/writes from server code, or debugging memory scoping and permissions. It's useful for backend engineers building intelligent features or agents that rely on historical context.
Developer-facing agents that can provide code examples and run TypeScript/Node.js snippets (e.g., Copilot-style assistants, Claude Code, or local dev runners).
Memories SDK is a guidance-only skill (no bundled scripts) that instructs developers on integrating @memories.sh/core and @memories.sh/ai-sdk into their applications. The SKILL.md is well-structured with clear workflow steps, concrete TypeScript examples for both the core client and Vercel AI SDK middleware, and a decision guide for choosing the right integration pattern. Security posture is strong — explicitly advises keeping API keys server-side and not exposing them to browser code. No scripts were present to execute or test.
Clean, well-documented guidance skill with no security concerns. The progressive disclosure pattern (lean SKILL.md → reference files) is well-executed. Would benefit from a troubleshooting section or common errors reference.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Navan Migration — Deep Dive
End-to-end migration playbook for moving from SAP Concur or legacy TMC to Navan: data export, user provisioning (SCIM/CSV), policy recreation, parallel running
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
FastAPI Project Templates
Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.
Websocket Client Creator
Generates and guides websocket client integrations: configuration, code samples, best practices, and validation for production-ready websocket clients.
Clerk Vue Patterns
Vue 3 integration patterns for Clerk: composables, router guards, and Pinia auth store integration.