Best Ory AI Skills & MCP Servers

Persistent key-value memory — store and recall information across sessions as JSON files.

In-memory file cache — avoid redundant disk reads with mtime-based invalidation.

Agent Model Layer — One-line LLM access with built-in memory. 29 providers, 18 embeddings, zero lock-in.

Provider-neutral agent runtime for coding workflows. Verified DAG execution with evidence gates, worktree isolation, and local graph memory.

Open-source terminal AI agent. 100+ specialist skills + audit-grade finance infra via @kernel.chat/kbot-finance. Content-addressed envelopes, hash-chained audit log, jurisdiction-aware regulatory verifier. The AI Intelligence Layer never produces the numb

MergeMind MCP server — read-only доступ к общей памяти команды агентов (markdown vault с гибридным поиском BM25 + vector + rerank). Запускается через `npx -y @agfpd/mergemind-mcp@latest` из .mcp.json плагина MergeMind (gh-репо agfpd/MergeMind).

Ricord — persistent memory + repo knowledge graph for AI coding assistants. Ships an MCP server (`ricord-mcp`) and a repo ingestion CLI (`ricord init`).

A Model Context Protocol server that acts as an intelligent conversation state manager and development guide for LLMs, featuring comprehensive long-term memory with persistent project artifacts

Research knowledge repository with semantic search, citations, and project lineage tracking

Lightweight local memory layer for AI assistants — MCP server + HTTP API + CLI, backed by SQLite + FTS5. Works with Claude, Cursor, and Codex.

A high-level agentic framework for Model Context Protocol (MCP) with memory and LLM integration.

MCP server that gives Claude Code persistent memory of your codebase, backed by Gemini's 2M-token context. Includes eager `ask`/`code` for cached repo Q&A and `ask_agentic` for agentic file access on repos that exceed the model's input-token limit.

Production payment infrastructure for AI agents — real Stripe/Paystack/Lightning rails, autonomous shopping with escrow, Agent Credit Score (300-850), Ed25519 identity, behavioral finance, Merkle integrity, anomaly detection, human-in-the-loop approval. B

MCP server for Tokenmaxxen — collective episodic memory for AI coding agents. Deposit, retrieve, and comment on session learnings (gotchas, fixes, prompts, configs) over hybrid keyword+semantic search. Agents can post corrections when a learning is wrong

Capybara-tier CLI router — Claude Opus 4.8 with Adaptive Thinking, Strict Write Discipline, and Self-Healing Memory

[PRE-LAUNCH] Agent-native decentralized commerce protocol. Humans and AI agents trade on the same protocol via MCP tools. ⚠️ Repository currently private until W8 public launch — GitHub links may return 404. See https://webaz.xyz for status.

Ricord — knowledge wiki, auto-organized. Ships an MCP server (`ricord-mcp`) and a wiki authoring CLI (`ricord setup`, `ricord build`, `ricord learn`, `ricord push`, `ricord compile`, …).

Memory-native terminal coding agent. Talks to the BrainRouter MCP cognitive engine for recall, skills, capture, persona, focus scenes, and contradiction tracking.

A Model Context Protocol (MCP) server for Storybook.

Fast TypeScript AI agent framework — per-request agents, 30+ model providers, 100+ integrations, 20+ vector DBs, 10+ databases, sessions, memory, knowledge, tracing, evals, HITL, teams, and workflows.

A Model Context Protocol server for coordinating cross-repository changes via Polygraph

MCP server that gives AI coding agents persistent memory — auto-detect mistakes, consolidate lessons, inject context on session start

Powerful MCP server with Tree-sitter WASM parsers for 100% AST accuracy. Zero native dependencies. Production-ready with persistent caching, structured logging, file watching, fuzzy search, rate limiting, file locking, and ReDoS protection. Supports TypeS

Local-first, LLM-agnostic memory layer for AI assistants. Run via npx @psraghuveer/memento.