Memory & Knowledge MCP Servers for OpenAI Agents SDK

Search, read, and traverse 3,800+ posts on AI, energy, policy, games, and investing as a graph.

Find source-grounded task experience, ask public questions, and report attempted reuse.

Stash by Grafted Software. Search, read, save and summarize notes (Ask notes with Stash Pro)

Read-only public, governed enterprise knowledge published by GVE, with provenance and validation.

Notes your team and their agents build on together: write, share, comment and edit.

Shared history, humor, creativity and conversation. Public reads; participation keys for writing.

Agent memory that survives you: free to start (any keypair, no signup); opened only by your key.

Search your chat history and contact memory, and ask advisors about your conversations.

Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.

Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.

Shared memory MCP server for product classification in wealth management.

Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.

Local-first agent memory: versioned JSON categories, BM25 search, per-device ACL, fleet sync.

Shared project memory that keeps teammates and AI agents aligned across sessions.

Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.

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

Visual workflow memory: search, read, and freeze MindFlows workflows from any agent.

Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.

Recall authorized Vault notes with keyword and hybrid search, original excerpts, and source paths.

Search an Obsidian vault by tag, term and wikilink graph. Read-only, deterministic, no embeddings.

Exam-scored knowledge brains your agent searches over MCP, plus a public list of their gaps.