"TUI" matching MCP servers:

Persistent memory for AI agents as a single Go binary: hybrid recall, self-building knowledge graph, and a live TUI dashboard. Zero infra, offline-first — works with Claude Code, Cursor, Codex, OpenCode, and any MCP client.

Turn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.

Enables AI agents to browse, search, and read a curated library of 198 UI/UX and animation design skills across 17 categories, distilled from 10 open-source projects, with a progressive 5-step workflow for guidance.

Enables saving, searching, retrieving, linking and importing AI work as plain markdown files with automatic provenance in a local folder the user owns. Runs entirely on the user's machine with no account, key or network calls, and never deletes anything.

Enables AI assistants to access and search Expo documentation with semantic search and AI-enhanced code examples and explanations using Gemini AI.

Exposes the Chakudya Nutrition Registry API as MCP tools, enabling clients to search Malawian food data, perform clinical nutrition lookups, and query a RAG knowledge base.

Enables offline CRUD and semantic search on Wikipedia ZIM archives via MCP tools for reading, writing, editing, deleting, and searching articles.

Provides an MCP memory system for AI personas with fading strengths, automatic recall, session handoff notes, isolated multi-persona stores, peer messaging, and a browsable star atlas. Runs on Cloudflare Workers and connects to any MCP client over Streamable HTTP.

A Machine Conversation Protocol server that enables AI agents to perform Retrieval-Augmented Generation by querying a FAISS vector database containing Sui Move language documents.

Exposes six tools over stdio that let AI coding assistants add, list, search, synthesize, resolve and delete persistent spec-driven project memory kept as markdown trees in the repository. This gives assistants durable recall of decisions, worklogs, watchpoints and governance laws across sessions without a database or API key.