Memory & Knowledge MCP Servers

A Model Context Protocol (MCP) server for indexing and semantically searching PDF research papers

PIL: local-first knowledge base for your Instagram saved posts, with a read-only MCP server.

A Python MCP server that gives LLMs persistent, searchable access to project context — documentation, architecture decisions, and session

Outcome-based persistent memory for AI coding tools (Claude Code, OpenCode)

Git-aware memory store for AI coding agents; memories are anchored to git blob hashes.

SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

MCP connector for Snipara, the Project Brain for AI coding agents

MCP server for Obsidian vaults with vector search

Lightweight, injectable knowledge bundles for AI agents. Git-versioned markdown, MCP-native, lives in your filesystem.

SOTA-level agent memory at zero infrastructure cost.

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

Local-first, source-backed continuity for AI agents via stdio MCP.

Capture dev context on interrupt; replay it as a 30-second resume card. Git stash for your head.

MCP server for Karpathy-style LLM Wiki — turn your markdown notes into an AI-powered knowledge graph

Local memory your AI tools share: decisions, notes and corrections that carry across sessions.

Persistent memory, self-evolving playbooks, and sandboxed REPL for AI agents

Local MCP server to sync, clean, and index AI chat logs locally. Saves up to 40% context tokens.

Cross-project memory sharing for Claude Code and Cowork. Namespaces let projects share knowledge without polluting global scope.

Cross-session memory for Claude Code — context capture, semantic search, recall

A FastMCP-based Model Context Protocol server for intelligent multi-agent code coordination

User-owned, cross-agent AI memory — open-source memory MCP server.