engram-memory
★ 38
vs
cortex
★ 35
engram-memory vs cortex
engram-memory: Engram Memory provides AI agents with persistent, self-hosted memory, eliminating session-end forgetfulness and API costs. It features a three-tiered recall engine for efficient storage, search, and retrieval of semantic embeddings on your own hardware.; 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.
01
TL;DR
engram-memoryMemory & Context · ★ 38
Providing long-term memory for AI agents (e.g., Claude Code, Cursor) to remember codebase details, user preferences, and architectural decisions across sessions.
cortexMemory & Context · ★ 35
Providing persistent, private long-term memory for AI agents and LLMs across conversation sessions.
02
Side-by-Side Comparison
Field
engram-memorycortexCategory
Memory & Context
Memory & Context
Stars
★ 38
★ 35
License
NOASSERTION
MIT
Install Command
docker run -d --name engram-memory --restart unless-stopped -p 6333:6333 -p 11435:11435 -p 8585:8585 -v engram_data:/data engrammemory/engram-memory:latest
brew tap gambletan/tap && brew install cortex-mcp-server
Updated
4mo ago
5d ago
Open Source
Yes
Yes
Tags
AI Agent Memory, Self-hosted, Vector Database
AI Agent Memory, Local Storage, Privacy-Preserving AI
03
Features
engram-memory01Three-tiered recall engine (Hot-Tier Cache, Multi-Head Hash Index, Hybrid Vector Search) for fast and efficient memory retrieval.
02Persistent memory management with semantic embedding (store, search, recall, forget, consolidate) for AI agents.
03Local-first operation with self-hosted components (Qdrant, FastEmbed, MCP server) for data privacy and zero API costs.
04Kuzu-backed entity graph for tracking entities, co-retrieval patterns, and spreading activation.
05Advanced memory capabilities including conflict detection, temporal queries, and an "answer from memory" function.
06Hive Memory for multi-device sharing, enabling shared memory pools across different agents and devices.
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.
04
Use Cases
engram-memory↳Providing long-term memory for AI agents (e.g., Claude Code, Cursor) to remember codebase details, user preferences, and architectural decisions across sessions.
↳Enabling multi-agent systems to share a common knowledge base and collaborate effectively through shared memory pools (Hive Memory).
↳Answering complex questions by synthesizing information from an agent's stored memories, both locally and optionally with cloud enhancement.
↳Auditing an agent's knowledge at specific points in time or over date ranges using temporal queries for incident analysis or historical context.
↳Storing and retrieving user preferences, facts, decisions, goals, and insights efficiently and semantically for personalized agent interactions.
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.
FAQ
FAQ
What is the difference between engram-memory and cortex?
Both engram-memory and cortex are in the Memory & Context category. engram-memory has 38 stars, while cortex has 35 stars.
Which is better, engram-memory or cortex?
The best choice depends on your use case. Choose engram-memory if Providing long-term memory for AI agents (e.g., Claude Code, Cursor) to remember codebase details, user preferences, and architectural decisions across sessions., and cortex if Providing persistent, private long-term memory for AI agents and LLMs across conversation sessions..
Is engram-memory free or open source?
Yes, engram-memory is open source on GitHub (NOASSERTION).
Is cortex free or open source?
Yes, cortex 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.
→