engram vs cortex-mem
Persistent memory for AI agents compared
engram and cortex-mem both help AI systems retain and retrieve useful information across sessions. engram focuses on curated project knowledge with local SQLite storage, while cortex-mem combines file-based memory, LLM extraction, and semantic search for agents and applications.
engram: Give AI Coding Agents Persistent Memory
Engram is a Go-based memory system that helps AI coding agents retain useful project knowledge between sessions. It stores memories locally in SQLite and makes them available through MCP, a CLI, an HTTP API, and a terminal UI.
cortex-mem: Give AI Agents Persistent Long-Term Memory
Cortex Memory is a Rust framework for storing, extracting, and searching long-term memories for AI agents and applications. It combines durable file-based storage with semantic search, and offers CLI, REST API, and MCP access.
| engram | cortex-mem | |
|---|---|---|
| Language | Go | Rust |
| License | MIT | MIT |
| Stars | 7k | 311 |
| Forks | 724 | 24 |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- engram is written in Go and stores memories in SQLite with FTS5; cortex-mem is written in Rust and stores Markdown in a virtual filesystem with vector search.
- engram emphasizes project decisions, conventions, and handoffs; cortex-mem supports structured extraction and layered memory for user and conversation context.
- engram defaults to local storage and offers optional Git Sync or Cloud replication; cortex-mem uses Qdrant and compatible LLM and embedding services.
- Both provide CLI and MCP access, while engram also offers an HTTP API and terminal UI, and cortex-mem offers a REST API, Rust integration, and Svelte dashboard.
- Both use the MIT license and are not archived; the supplied facts list 7k stars for engram and 311 for cortex-mem.
Choose engram if you…
- need locally stored project knowledge backed by SQLite.
- want memory access through MCP, a CLI, an HTTP API, or a terminal UI.
- prefer to make sharing optional through Git Sync or Cloud replication.
Choose cortex-mem if you…
- need semantic search, metadata filtering, and layered memory summaries.
- want LLM-based extraction and automated memory indexing and updates.
- are building an AI application and want REST API or Rust integration options.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.