MemVid: A Portable Single-File Memory Layer for AI Agents
Discover MemVid — a groundbreaking portable AI memory system that replaces complex RAG pipelines with a single file. Built in Rust, it delivers sub-millisecond retrieval and +35% SOTA on LoCoMo benchmarks.
What is MemVid?
MemVid is a groundbreaking portable AI memory system that packages your data, embeddings, search structure, and metadata into a single file. Rather than running complex RAG pipelines or managing server-based vector databases, MemVid enables instant retrieval directly from the file — giving AI agents persistent, long-term memory they can carry anywhere.
Built entirely in Rust, MemVid achieves remarkable performance: 0.025ms P50 and 0.075ms P99 latency with 1,372× higher throughput than standard memory systems. It scores +35% SOTA on the LoCoMo benchmark for long-horizon conversational recall and +76% on multi-hop reasoning.
🚀 Want to deploy MemVid yourself?
Docker configs, system requirements, and installation guides — all on one page.
View MemVid Tool Page →How Smart Frames Work
MemVid draws inspiration from video encoding to organize AI memory as an append-only, ultra-efficient sequence of Smart Frames. Each Smart Frame is an immutable unit storing content along with timestamps, checksums, and metadata. Frames are grouped for efficient compression, indexing, and parallel reads.
This frame-based design enables:
- Append-only writes — no modification or corruption of existing data
- Time-travel queries — inspect past memory states
- Crash safety — committed, immutable frames
- Timeline-style inspection — see how knowledge evolves
Core Features
| Living Memory Engine | Continuously append, branch, and evolve memory across sessions |
| Capsule Context (.mv2) | Self-contained, shareable memory capsules with rules and expiry |
| Time-Travel Debugging | Rewind, replay, or branch any memory state |
| Smart Recall | Sub-5ms local memory access with predictive caching |
| Codec Intelligence | Auto-selects and upgrades compression over time |
Multi-Language SDK Support
MemVid provides SDKs for all major programming languages:
- CLI:
npm install -g memvid-cli - Node.js:
npm install @memvid/sdk - Python:
pip install memvid-sdk - Rust:
cargo add memvid-core
The Docker image tuxed/memvid-mcp:latest is available for containerized deployments, making it easy to integrate with MCP-compatible AI workflows.
🚀 Ready to give your AI agents memory?
Docker configs, system requirements, and installation guides — all on one page.
View MemVid Tool Page →