AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
Compare/
Ori-Mnemos vs letta
Ori-Mnemos logo
Ori-Mnemos
★ 306
vs
letta logo
letta
★ 23.0k

Ori-Mnemos vs letta

Ori-Mnemos: Ori Mnemos is an open-source persistent memory infrastructure for AI agents that implements human cognition models on a knowledge graph. It uses ACT-R decay, spreading activation, and Hebbian learning to manage memory, and achieves state-of-the-art retrieval performance while being zero-infrastructure and portable.; 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

Ori-Mnemos logoChoose Ori-Mnemos if…

Multi-hop retrieval QA (e.g., HotpotQA)

letta logoChoose letta if…

Running AI agents locally in your terminal for coding and general tasks.

02

Side-by-Side Comparison

Field
Ori-Mnemos logoOri-Mnemos
letta logoletta
Category
Memory & Context
Memory & Context
Stars
★ 306
★ 23.0k
License
Apache-2.0
Apache-2.0
Updated
3w ago
2w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, ai-agent, ai-agents
Stateful AI, Agent Platform, Advanced Memory
03

Features

Ori-Mnemos logoOri-Mnemos
01Persistent memory across sessions, clients, and machines
02Knowledge graph with wiki-links, PageRank, and community detection
03Three memory spaces with cognitive forgetting (ACT-R decay)
04Four-signal fusion retrieval (semantic, BM25, PageRank, warmth)
05Retrieval intelligence with Q-learning and meta-learning
letta logoletta
01Build 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

Ori-Mnemos logoOri-Mnemos
↳Multi-hop retrieval QA (e.g., HotpotQA)
↳Long-term conversational memory (e.g., LoCoMo)
↳Persistent AI agent identity and knowledge
letta logoletta
↳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

Ori-Mnemos logoOri-Mnemos
Memory & ContextRAG / Knowledge Base
letta logoletta
Most PopularTrendingEssential
FAQ

FAQ

What is the difference between Ori-Mnemos and letta?
Both Ori-Mnemos and letta are in the Memory & Context category. Ori-Mnemos has 306 stars, while letta has 23.0k stars.
Which is better, Ori-Mnemos or letta?
The best choice depends on your use case. Choose Ori-Mnemos if Multi-hop retrieval QA (e.g., HotpotQA), and letta if Running AI agents locally in your terminal for coding and general tasks..
Is Ori-Mnemos free or open source?
Yes, Ori-Mnemos is open source on GitHub (Apache-2.0).
Is letta free or open source?
Yes, letta is open source on GitHub (Apache-2.0).
→

Related

Alternatives to Ori-Mnemos →Alternatives to letta →Ori-Mnemos details →letta details →
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.