memvid vs cortex-mem
Persistent AI memory projects compared
memvid and cortex-mem both help AI applications retain and retrieve information across sessions. memvid packages memory and search structures into a portable file, while cortex-mem combines layered memory organization with semantic search in a system that uses Qdrant and model services.
memvid: Store Persistent AI Memory in a Single File
Memvid is a Rust-based memory layer that stores content, search indexes, and metadata in a portable .mv2 file. It suits developers building agents that need local, persistent retrieval without operating a separate database service.
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.
| memvid | cortex-mem | |
|---|---|---|
| Language | Rust | Rust |
| License | Apache-2.0 | MIT |
| Stars | 16.6k | 311 |
| Forks | 1.4k | 24 |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- memvid stores content, metadata, and search structures in a single `.mv2` file; cortex-mem stores Markdown memories in a `cortex://` virtual filesystem and uses Qdrant for semantic search.
- memvid supports full-text BM25 search and optional vector search; cortex-mem focuses on semantic search with metadata filtering and extracts structured memories using an LLM.
- memvid offers optional local ONNX embeddings or OpenAI embeddings; cortex-mem depends on configured compatible LLM and embedding services.
- memvid provides Rust, Python, and Node.js SDKs plus a CLI; cortex-mem provides Rust integration, a CLI, REST API, MCP server, and Svelte dashboard.
- memvid uses the Apache-2.0 license and has 16.6k stars; cortex-mem uses the MIT license and has 311 stars.
Choose memvid if you…
- want portable memory and retrieval structures in one file.
- need local or offline operation without running a separate database service.
- want full-text search with optional vector search and Rust, Python, or Node.js interfaces.
Choose cortex-mem if you…
- need layered memories with abstracts, overviews, and detailed content.
- want LLM-based memory extraction and automated indexing or cleanup.
- need tenant-aware memory spaces or access through a REST API, MCP server, or dashboard.
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.