mcp-local-memory
Active·★ 60·MIT·Updated 2026-09-14
mcp-local-memory is a local-first MCP server designed to provide AI agents with shared, durable memory without relying on Docker or cloud services. It achieves this through a powerful combination of hybrid semantic search, SQLite FTS5, and a structured knowledge graph, supporting features like temporal recall and adaptive ranking.
#AI Agents#Memory Management#Knowledge Graph#Semantic Search#SQLite#Context Management#Local-first#Hybrid Search
01
Features
01Shared memory across multiple AI agents
02Hybrid semantic and keyword recall
03Structured knowledge graph for context management
04Temporal memory recall with natural language dates
05Adaptive memory ranking based on multiple factors
02
Compatibility
Node.js
Runtime
Verified via docs
Linux
Platform
Verified via docs
MacOS
Platform
Verified via docs
Windows
Platform
Verified via docs
03
Quick start
1
$ npm install -g @beledarian/mcp-local-memory@2
04
Use cases
↳Provide persistent and shared memory for AI agents in local environments.
↳Build knowledge bases and manage context for complex AI applications.
↳Facilitate local-first AI agent development and testing without external dependencies.
↳Serve as a centralized memory server for distributed AI agent systems via HTTP/SSE.
05
Alternatives
MAMA★ 15
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.
squish-memory★ 12
Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.
remnic★ 228
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
Waggle-mcp★ 44
MCP server for external memory layer for AI agents + more . Download from pypi , and get started
state-memory-mcp★ 48
Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.
Comments
Log in to leave a comment
No comments yet. Be the first!