engram-mcp
★ 18
vs
cortex
★ 35
engram-mcp vs cortex
engram-mcp: Engram is an MCP server that provides persistent, Git-aware session memory for coding agents, allowing structured handoffs between sessions and branches. It helps agents retain context, decisions, and tasks, backed by local SQLite and ONNX embeddings without cloud dependencies.; 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-mcpMemory & Context · ★ 18
Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover.
cortexMemory & Context · ★ 35
Providing persistent, private long-term memory for AI agents and LLMs across conversation sessions.
02
Side-by-Side Comparison
Field
engram-mcpcortexCategory
Memory & Context
Memory & Context
Stars
★ 18
★ 35
License
Apache-2.0
MIT
Install Command
cargo install engram_mcp
brew tap gambletan/tap && brew install cortex-mcp-server
Updated
5d ago
6d ago
Open Source
Yes
Yes
Tags
Git-aware Memory, Coding Agent Tools, Context Management
AI Agent Memory, Local Storage, Privacy-Preserving AI
03
Features
engram-mcp01Provides Git-aware session memory that scopes context to specific git branches, preventing information leakage.
02Enables structured session handoffs to capture summaries, decisions, todos, blockers, and mental models for continuity.
03Offers local-first persistent storage using SQLite and ONNX embeddings, ensuring no cloud or LLM calls are needed for storage.
04Features advanced memory retrieval with hybrid scoring (cosine, recency, importance), hierarchical clustering, and branch-aware queries.
05Includes automated memory management capabilities such as decay, semantic deduplication, and auto-pruning of low-relevance memories.
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-mcp↳Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover.
↳Automatically retrieve relevant context and prior session details when resuming work on the same or a different Git branch.
↳LLM agents can proactively load relevant memories at the start of a conversation, building context from recent Git activity.
↳Passively capture coding decisions and session summaries into memory through integrated hooks without explicit tool calls.
↳Maintain a centralized, searchable, and structured memory of project-specific decisions, recurring patterns, and past debug solutions.
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-mcp and cortex?
Both engram-mcp and cortex are in the Memory & Context category. engram-mcp has 18 stars, while cortex has 35 stars.
Which is better, engram-mcp or cortex?
The best choice depends on your use case. Choose engram-mcp if Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover., and cortex if Providing persistent, private long-term memory for AI agents and LLMs across conversation sessions..
Is engram-mcp free or open source?
Yes, engram-mcp is open source on GitHub (Apache-2.0).
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.
→