cortex
★ 35
vs
letta
★ 25.2k
cortex vs letta
cortex: Cortex is a private, free, and local memory engine for personal AI agents, built with Rust. It provides multi-tier, self-evolving long-term memory that persists across sessions and devices, offering sub-millisecond performance and end-to-end encrypted cloud synchronization.; 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
cortexMemory & Context · ★ 35
Providing persistent, private long-term memory for AI agents and LLMs across conversation sessions.
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
cortexlettaCategory
Memory & Context
Memory & Context
Stars
★ 35
★ 25.2k
License
MIT
Apache-2.0
Install Command
brew tap gambletan/tap && brew install cortex-mcp-server
npm install -g @letta-ai/letta-code
Updated
1d ago
5d ago
Open Source
Yes
Yes
Tags
AI Agent Memory, Local Storage, Privacy-Preserving AI
Stateful AI, Agent Platform, Advanced Memory
03
Features
cortex01Private by Default: Memories reside in a local SQLite file, ensuring zero telemetry and data privacy.
02Real, Multi-Tier Memory: Features 4 memory tiers (Working, Episodic, Semantic, Procedural), multi-signal retrieval, Bayesian beliefs, and a cross-channel people graph.
03Sub-millisecond Performance: Achieves 156µs ingest and 568µs search speeds, significantly faster than cloud memory APIs.
04Cross-Device End-to-End Encrypted Sync: Optionally syncs memories across devices through your own cloud storage (iCloud, Google Drive, etc.) with AES-256-GCM encryption.
05Drop-in Integration: Serves as an MCP server for Claude, offers Python bindings, and integrates with frameworks like LangGraph, DeerFlow, and OpenClaw.
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
cortex↳Providing persistent, private long-term memory for AI agents and LLMs across conversation sessions.
↳Enabling AI assistants to remember user preferences, facts, and past interactions without sending data to external servers.
↳Building personal AI systems where user data stays entirely on-device or synced via user's own encrypted cloud storage.
↳Integrating advanced memory capabilities (e.g., people graph, Bayesian beliefs, contradiction detection) into agent orchestration platforms like LangGraph or DeerFlow.
↳Developing AI applications that require low-latency, real-time memory access and context generation for prompt injection.
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
cortex—
lettaMost PopularEssentialTrending
FAQ
FAQ
What is the difference between cortex and letta?
Both cortex and letta are in the Memory & Context category. cortex has 35 stars, while letta has 25.2k stars.
Which is better, cortex or letta?
The best choice depends on your use case. Choose cortex if Providing persistent, private long-term memory for AI agents and LLMs across conversation sessions., and letta if Running AI agents locally in your terminal for coding and general tasks..
Is cortex free or open source?
Yes, cortex is open source on GitHub (MIT).
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.
→