🧠 𝑴𝒆𝒎𝒐𝒓𝒚-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.
Local JSON memory store for context engineering with GitHub Copilot and MCP clients. Includes CLI, MCP server, and custom VS Code agent.
Embedded long-term memory runtime & vector search engine for AI agents
Long-term memory for AI apps that keeps evidence, inference, and conflicts distinct.
AWS DynamoDB implementation for LangGraph Memory Store and Checkpoint Saver in TypeScript
🧠 Universal long-term memory for AI agents. GraphRAG-powered knowledge base with vector search + graph traversal. Privacy-first, local-only, MCP-compatible. Connect Claude, Copilot, or any AI assistant.
⚡ Instantly index, deduplicate, and search your code, docs, and web content in a blazing-fast Qdrant vector DB for AI & RAG.
GameCenter which has games in it
Long-term memory for AI agents that survive between sessions. One index file, one pointer per topic, everything else plain Markdown. Portable, git-friendly, framework-agnostic knowledge base - no database required.
Local-first AI memory store with synaptic dynamics (strengthen/decay/prune) and neighbor-based pattern expansion (L2).
Testing framework for AI agent memory systems — validates persistence, recall accuracy, staleness, benchmarking, and pruning
Namespaced in-memory key-value store for JS/TS with dot-path access and synchronous subscribe — zero dependencies, ESM.
Local-first inspectable memory and work-trace store for human/agent collaboration
Simple REST API for managing shared and persistent GPT memories through GPT Actions.
To associate your repository with the memory-store topic, visit your repo's landing page and select "manage topics."