AgentIndex icon
AgentIndex
memini logo
memini
★ 28
vs
local-memory-mcp logo
local-memory-mcp
★ 15

memini vs local-memory-mcp

memini: memini is a shared, persistent memory service designed for AI agents, providing a single location for agents to remember and recall information with continuously improving retrieval quality. It's built as a Go binary, offers zero-configuration startup, and scales from embedded SQLite on a laptop to Postgres in Kubernetes.; local-memory-mcp: local-memory-mcp provides persistent local memory for AI assistants like Claude, Cursor, and Codex, addressing the issue of AI forgetting past conversations. It stores learnings, decisions, and knowledge graphs in a single SQLite file on your machine, utilizing hybrid retrieval and multilingual embeddings for robust information recall without cloud services or API keys.

01

TL;DR

memini logo
meminiMemory & Context · ★ 28

Enhancing AI Agents with Long-Term Memory: Integrate memini to give AI agents (like Claude Code, opencode, Hermes) the ability to remember past interactions and learn over time.

Read memini full review →
local-memory-mcp logo
local-memory-mcpMemory & Context · ★ 15

Provide persistent memory for AI assistants, ensuring they remember past conversations and context across sessions.

Read local-memory-mcp full review →
02

Side-by-Side Comparison

Field
memini logomemini
local-memory-mcp logolocal-memory-mcp
Category
Memory & Context
Memory & Context
Stars
★ 28
★ 15
License
AGPL-3.0
MIT
Install Command
export MEMINI_EMBED_BASE_URL=http://localhost:8081/v1 && export MEMINI_EMBED_MODEL=bge-m3 && export MEMINI_EMBED_DIMS=1024 && mise run run
npx -y @studiomeyer/local-memory-mcp
Updated
3d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agents, Persistent Memory, Vector Search
Local Memory, Hybrid Retrieval, Vector Embeddings
03

Features

memini logomemini
01Shared, Persistent Memory: Provides a dedicated service for AI agents to store and retrieve memories, designed for long-term persistence.
02Hybrid Retrieval & Re-ranking: Employs a hybrid (vector + keyword) retrieval method, fused with Reciprocal Rank Fusion (RRF), and re-ranks results by relevance, recency, and importance, not just similarity.
03Tiered Memory System: Implements a tiered memory structure (working, episodic, semantic, procedural) with decay mechanisms.
04Pluggable Storage: Supports flexible storage options, including embedded SQLite-vec for local use and Postgres with VectorChord for scalable deployments.
05Optional LLM Consolidation: Features an opt-in LLM consolidation pipeline for background deduplication and contradiction resolution, but can run headless (without an LLM) using marker heuristics.
06Model Context Protocol (MCP) Support: Compatible with MCP-capable agents, offering both Streamable HTTP and stdio transports.
local-memory-mcp logolocal-memory-mcp
01Knowledge Graph with entities, bi-temporal observations, and typed relations.
02Hybrid retrieval combining BM25 keyword search with vector cosine via Reciprocal Rank Fusion.
03Duplicate gatekeeper using FTS5 similarity to prevent storing identical information.
04Automatic session context loading, allowing AI to pick up from previous conversations.
05Local-first design with zero configuration, running entirely on your machine without cloud services or API keys.
04

Use Cases

memini logomemini
↳Enhancing AI Agents with Long-Term Memory: Integrate memini to give AI agents (like Claude Code, opencode, Hermes) the ability to remember past interactions and learn over time.
↳Self-Hosting a Shared Memory Service: Deploy memini for a team or homelab environment to provide a centralized, persistent memory store for multiple AI agents.
↳Improving AI Recall Quality: Tune memini's retrieval parameters to fix bad recall and achieve higher accuracy in retrieving relevant information for AI models.
↳Managing Multi-Agent Namespaces: Lay out distinct namespaces within memini to provide isolation and organized memory management for several different AI agents.
↳Backend for Open WebUI Memory: Utilize memini as a robust memory backend for platforms like Open WebUI, integrating its memory and tool capabilities.
local-memory-mcp logolocal-memory-mcp
↳Provide persistent memory for AI assistants, ensuring they remember past conversations and context across sessions.
↳Store and retrieve structured knowledge like learnings, decisions, and entity observations in a local knowledge base.
↳Perform unified, hybrid semantic search across various memory types to quickly recall relevant information.
↳Log and review important decisions along with their reasoning and considered alternatives.
↳Enable LLM-free reflection to identify most-used learnings, stale information, and open decisions.
FAQ

FAQ

What is the difference between memini and local-memory-mcp?
Both memini and local-memory-mcp are in the Memory & Context category. memini has 28 stars, while local-memory-mcp has 15 stars.
Which is better, memini or local-memory-mcp?
The best choice depends on your use case. Choose memini if Enhancing AI Agents with Long-Term Memory: Integrate memini to give AI agents (like Claude Code, opencode, Hermes) the ability to remember past interactions and learn over time., and local-memory-mcp if Provide persistent memory for AI assistants, ensuring they remember past conversations and context across sessions..
Is memini free or open source?
Yes, memini is open source on GitHub (AGPL-3.0).
Is local-memory-mcp free or open source?
Yes, local-memory-mcp is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to memini →Alternatives to local-memory-mcp →memini details →local-memory-mcp details →