memini
★ 28
vs
mex
★ 1.8k
memini vs mex
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.; mex: mex provides persistent, navigable project memory for AI coding agents, allowing every session to start with the right context instead of a cold prompt. It structures agent memory through a markdown scaffold, offers CLI tools for drift detection against the real codebase, and synchronizes context to keep agents aligned and reduce token usage.
01
TL;DR
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.
mexMemory & Context · ★ 1.8k
When to choose:
- Your AGENTS.md or CLAUDE.md has grown too big and you want a small anchor plus routed context files.
- You want memory as plain markdown in the repo, reviewable in pull requests and diffable.
- You want drift checks that run without AI tokens and flag missing paths, stale files and broken scripts.
When to skip:
- You want recall across unrelated projects or conversations; mex lives inside one repository.
- You have a small project: another set of files to maintain may cost more than it saves.
- You expect the AST code-graph feature today: the README marks it as an unreleased preview.
02
Side-by-Side Comparison
Field
meminimexCategory
Memory & Context
Memory & Context
Stars
★ 28
★ 1.8k
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 mex-agent setup
Updated
3d ago
3d ago
Open Source
Yes
Yes
Tags
AI Agents, Persistent Memory, Vector Search
AI Agents, Persistent Memory, Context Management
03
Features
memini01Shared, 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.
mex01Creates a structured markdown scaffold for AI agent memory (e.g., AGENTS.md, ROUTER.md, context/, patterns/).
02CLI tools for drift detection, validating scaffold against the actual codebase without using AI tokens.
03Automatically generates targeted prompts for AI agents to fix stale or broken context.
04Supports task-specific context routing, loading only relevant files for the current task.
05Includes an append-only event log to store decisions, notes, risks, and todos.
04
Use Cases
memini↳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.
mex↳Maintaining consistent project context for AI coding agents across multiple sessions.
↳Significantly reducing token consumption in LLM interactions by providing only relevant context.
↳Onboarding new AI agents or developers to complex codebases with structured, up-to-date project knowledge.
↳Developing persistent AI agents for operational environments (homelab scenarios, system administration) with structured memory.
↳Automating the detection and correction of documentation or contextual drift from the actual codebase.
05
Best For
memini—
mexEssentialTrending
FAQ
FAQ
What is the difference between memini and mex?
Both memini and mex are in the Memory & Context category. memini has 28 stars, while mex has 1.8k stars.
Which is better, memini or mex?
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 mex if Maintaining consistent project context for AI coding agents across multiple sessions..
Is memini free or open source?
Yes, memini is open source on GitHub (AGPL-3.0).
Is mex free or open source?
Yes, mex is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→