AI & Agent Tools MCP Servers

Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

Local-first persistent project memory for AI coding agents across MCP clients and sessions.

Git for AI memory — version-controlled, searchable context that persists across sessions

AI-native Microsoft Teams integration — read chats, send messages, search people

Memi is the design layer for agentic AI.

File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.

Operate local deploy trains for coding-agent worktrees with approval-gated deploys.

MCP server for ML drift detection, MLflow registry diffing, and HMAC-gated model rollback

Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.

Builds Figma from your design system: real components and tokens, enforced, learning every build.

A Model Context Protocol (MCP) server for NuGet.

Let an AI agent read and trade a MetaTrader 5 account over MCP, behind a human-approval gate.

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Local-first, source-traceable agent memory — no LLM at ingest, fully offline

AI-powered database migration. Analyze schemas, generate SQL, calculate risks.

Zero-knowledge persistent memory layer for AI agents. Encrypted client-side, hosted in France.

Zero-knowledge persistent memory for Claude — encrypted, semantic search, EU hosted.

Connect Claude to Microsoft Teams — read/send messages, list channels, search chats.

Real-time prediction market consensus data for AI agents

AI-to-human attention marketplace. Agents pay CPM to reach humans, earn credits by replying.

Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking

Curated knowledge for AI agents — 19K chunks, 121 skills, semantic search via MCP

Add persistent memory to AI assistants. Store and recall info across conversations.