Memory & Knowledge MCP Servers for Gemini CLI

Local deterministic project memory for AI agents with context packs, gates and checkpoints.

Light MCP server for Obsidian vault — no plugins, no open app required

MCP server for integrating Limitless AI Pendant recordings with AI assistants

Local-first MCP sidecar for Markdown artifacts, review intents, and supervised knowledge growth.

Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.

Persistent cross-project memory for Cursor and Claude Code using local semantic search.

Unified knowledge management MCP server with document intelligence and research workflows

MCP server for Mem0 agent memory management with multi-backend support

Git-native project memory for AI assistants with enterprise-grade audit compliance

SQLite-backed Memory MCP implementing the SOA-Harness §8.1 6-tool protocol. Zero external services; ships the spec-canonical 'hits' wire

Convert, validate, and inspect AI agent memories across formats

Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.

Model Context Protocol server for Obsidian Vaults with write/append capabilities

Local-first personal memory and model server for trusted MCP agents on macOS.

Governed memory for AI agents (Paramind AI): conflict-checked writes, time-travel reads, ACL, audit.

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

Agent-native MCP server over the public saagarpatel.dev corpus — read-only, stateless.

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

RAG-based skill retrieval system for AI agents. Scalable long-term storage with semantic search via MCP.

MCP server for Cortex AI — State-of-the-art agentic memory with recall, ingest, and knowledge graph context

Local-first MCP memory server for multi-agent systems. Hybrid search (BM25 + semantic embeddings), SQLite-backed, zero-config.