memini
★ 28
vs
letta
★ 25.2k
memini vs letta
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.; letta: Letta is a powerful platform for building stateful AI agents equipped with advanced memory, enabling them to learn and self-improve over time. It provides both a command-line interface for local agent execution and a comprehensive API with Python and TypeScript SDKs for seamless integration into applications.
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.
lettaMemory & Context · ★ 25.2k
When to choose:
- You want a long-lived agent that remembers past work and rewrites its own memory and context over time.
- You want one agent reachable from CLI, desktop, browser, mobile and messaging apps, with subagents, schedules and hooks.
- You want memory you can inspect: the README says context is tracked in git and can sync to your own repository.
When to skip:
- You only need to add memory to an agent you already use through MCP; a small MCP memory server is a lighter fit.
- You rely on older Letta tutorials or the V1 API server: the project restructured, and the V1 server is retired.
- You want everything to work without signing in: Letta Cloud is the default backend and some features need it.
02
Side-by-Side Comparison
Field
meminilettaCategory
Memory & Context
Memory & Context
Stars
★ 28
★ 25.2k
License
AGPL-3.0
Apache-2.0
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 @letta-ai/letta-code
Updated
3d ago
4d ago
Open Source
Yes
Yes
Tags
AI Agents, Persistent Memory, Vector Search
Stateful AI, Agent Platform, Advanced Memory
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.
letta01Build stateful AI agents with advanced memory
02Agents capable of learning and self-improvement over time
03CLI tool for running agents locally in your terminal
04Comprehensive API for integrating agents into applications
05Support for skills and subagents; fully model-agnostic
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.
letta↳Running AI agents locally in your terminal for coding and general tasks.
↳Integrating stateful AI agents into custom applications using the API and SDKs.
↳Developing self-improving AI systems that adapt and learn continually.
05
Best For
memini—
lettaMost PopularEssentialTrending
FAQ
FAQ
What is the difference between memini and letta?
Both memini and letta are in the Memory & Context category. memini has 28 stars, while letta has 25.2k stars.
Which is better, memini or letta?
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 letta if Running AI agents locally in your terminal for coding and general tasks..
Is memini free or open source?
Yes, memini is open source on GitHub (AGPL-3.0).
Is letta free or open source?
Yes, letta is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→