AI / ML Engineer
FeaturedPersist memory across sessions, reason step-by-step, generate images, search the web for papers, cache results in Redis, and query your vector store.
Knowledge graph-based persistent memory system
Persist facts in a knowledge graph across conversations — essential for agentic workflows
npx -y @modelcontextprotocol/server-memoryDynamic problem-solving through sequential thought sequences
Break complex AI reasoning into sequential, trackable steps
npx -y @modelcontextprotocol/server-sequential-thinkingAI image generation using various models
Generate reference images and art via EverArt's diffusion models
npx -y @modelcontextprotocol/server-everartWeb and local search using Brave Search API
Search for papers, model cards, and AI research in real time
npx -y @modelcontextprotocol/server-brave-searchInteract with Redis key-value stores
Cache embeddings and model outputs to reduce latency and cost
npx -y @modelcontextprotocol/server-redis redis://localhost:6379Serverless PostgreSQL management with Neon
Serverless PostgreSQL for storing experiment results and eval scores
A server that provides full web search, summaries and page extration for use with Local LLMs.
Web search optimised for AI assistant workflows