AgentIndex icon
AgentIndex
memini logo
memini
★ 28
vs
hippo-memory logo
hippo-memory
★ 784

memini vs hippo-memory

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.; hippo-memory: Hippo is an AI agent memory layer inspired by the human hippocampus, designed to manage agent memory with features like default decay, strengthening through use, and full provenance. It integrates with various AI agents and tools, using SQLite for storage and offering a CLI for memory management, ensuring relevant context is always available without overwhelming the agent.

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 →
hippo-memory logo
hippo-memoryMemory & Context · ★ 784

Ensuring AI agents learn from past mistakes and avoid repetition.

Read hippo-memory full review →
02

Side-by-Side Comparison

Field
memini logomemini
hippo-memory logohippo-memory
Category
Memory & Context
Memory & Context
Stars
★ 28
★ 784
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
npm install -g hippo-memory && hippo init --scan ~
Updated
3d ago
Today
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agents, Persistent Memory, Vector Search
AI Agents, Memory Management, Context Window
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.
hippo-memory logohippo-memory
01Default memory decay with configurable half-life.
02Memories are strengthened through retrieval and use.
03Errors and important decisions are given longer persistence.
04Memory consolidation process ('sleep') merges and prunes memories.
05Context injection with token budgeting and flexible framing.
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.
hippo-memory logohippo-memory
↳Ensuring AI agents learn from past mistakes and avoid repetition.
↳Maintaining consistent memory across different AI agents and development tools.
↳Centralizing and making queryable memories from external systems like Slack and chat exports.
↳Providing short-term memory and task snapshots for continuous workflow.
↳Automating memory creation from git commit history and command failures.
05

Best For

memini logomemini
—
hippo-memory logohippo-memory
TrendingHidden Gem
FAQ

FAQ

What is the difference between memini and hippo-memory?
Both memini and hippo-memory are in the Memory & Context category. memini has 28 stars, while hippo-memory has 784 stars.
Which is better, memini or hippo-memory?
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 hippo-memory if Ensuring AI agents learn from past mistakes and avoid repetition..
Is memini free or open source?
Yes, memini is open source on GitHub (AGPL-3.0).
Is hippo-memory free or open source?
Yes, hippo-memory 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 hippo-memory →memini details →hippo-memory details →