engram vs memvid

Persistent AI memory: engram and memvid compared

engram and memvid both give AI applications persistent memory for retrieving useful information across sessions. engram centers on project knowledge stored in SQLite and exposed through several interfaces, while memvid packages content and search structures in a portable `.mv2` file.

engrammemvid
LanguageGoRust
LicenseMITApache-2.0
Stars7k16.6k
Forks7241.4k
Last analyzedOct 3, 2026Oct 3, 2026

Key differences

  • engram is written in Go and uses SQLite with FTS5; memvid is written in Rust and stores memory in `.mv2` files.
  • engram provides MCP, CLI, HTTP API, and terminal UI access; memvid provides Rust, Python, and Node.js SDKs plus a CLI.
  • engram focuses on curated project decisions, discoveries, and handoffs; memvid supports text retrieval with BM25 and optional vector search, plus optional media-related capabilities.
  • engram uses local storage by default and offers Git Sync and optional Cloud replication; memvid emphasizes carrying a single memory file between environments without a separate database service.
  • engram is MIT-licensed; memvid is Apache-2.0-licensed.
  • engram’s README notes Homebrew remains on the stable v1.20.0 line; memvid’s Rust library requires Rust 1.85.0 or newer.

Choose engram if you…

  • need persistent, project-aware knowledge for coding agents across sessions.
  • want MCP access alongside CLI, HTTP API, or terminal UI options.
  • prefer SQLite-backed local storage, with optional Git Sync or Cloud replication for sharing.
Read the engram analysis →

Choose memvid if you…

  • want memory content and retrieval structures packaged in a portable `.mv2` file.
  • need full-text search with optional vector similarity search and versioned memory inspection.
  • are building with Rust, Python, or Node.js and want optional capabilities such as PDF extraction, image embeddings, or audio transcription.
Read the memvid analysis →

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.