memini
★ 28
vs
claude-mem-lite
★ 67
memini vs claude-mem-lite
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.; claude-mem-lite: claude-mem-lite provides a persistent, cross-session memory system for Claude Code, automatically capturing coding observations and decisions. It uses an MCP server and hooks for efficient, cost-optimized context recall via hybrid full-text and semantic search.
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.
claude-mem-liteMemory & Context · ★ 67
Recalling past bug fixes and coding decisions across sessions.
02
Side-by-Side Comparison
Field
meminiclaude-mem-liteCategory
Memory & Context
Memory & Context
Stars
★ 28
★ 67
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 github:sdsrss/claude-mem-lite
Updated
3d ago
1d ago
Open Source
Yes
Yes
Tags
AI Agents, Persistent Memory, Vector Search
Persistent Memory, LLM Memory Management, Claude Code Plugin
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.
claude-mem-lite01Automatic observation capture via Claude Code hooks.
02Hybrid full-text and semantic search (FTS5 + TF-IDF) with RRF.
03Episode batching for significant LLM cost reduction.
04Error-triggered and proactive file history recall.
05Cross-language synonym expansion (CJK↔EN) for enhanced search.
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.
claude-mem-lite↳Recalling past bug fixes and coding decisions across sessions.
↳Maintaining project context for AI coding agents over long periods.
↳Automatically getting relevant historical context when interacting with files.
↳Optimizing LLM token usage and cost for AI agent memory.
↳Zero-touch documentation of coding workflows and lessons learned.
FAQ
FAQ
What is the difference between memini and claude-mem-lite?
Both memini and claude-mem-lite are in the Memory & Context category. memini has 28 stars, while claude-mem-lite has 67 stars.
Which is better, memini or claude-mem-lite?
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 claude-mem-lite if Recalling past bug fixes and coding decisions across sessions..
Is memini free or open source?
Yes, memini is open source on GitHub (AGPL-3.0).
Is claude-mem-lite free or open source?
Yes, claude-mem-lite 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.
→