Memory & Knowledge MCP Servers for Perplexity

Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.

BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

MCP server for semantic search over Obsidian vaults with Smart Connections data.

Model Context Protocol server for Mnemo Memory — exposes search/add/update/delete tools to Claude Desktop, Cursor, Windsurf, VS Code, Zed.

Tiered memory MCP server for Claude and AI agents — FTS5 search, dedup, export/import, auto-snapshot

Semantic document memory using Redis vector store. Save and recall files with natural language.

Collective episodic memory for AI coding agents — search, deposit, comment, showcase builds.

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.

Local chronological memory banks you control; Claude recalls them via MCP.

Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.

Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files.

MCP Server — connects Engram brain to any AI client (Claude Code, Cursor, Windsurf, and more)

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

MCP server for searching Notion local cache (SQLite) - Fast, offline, no API limits

Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.

Shared, git-tracked working memory for AI agents on the same codebase.

Local-first AI memory over MCP. No account; you own the store.

Memory-as-a-service MCP server for AI agents. 12 tools, Postgres + pgvector, multi-strategy retrieval. Works with Claude Code, Cursor

Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.

A validated Markdown memory vault your coding agent can recall, project by project.