memvid /memvid
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
★ 17,416⑂ 1,467👁 124⑃ 98● 104▤ 12
+6
Daily
+59
Weekly
+825
Monthly
17,416
stars
1,467
forks
124
watchers
98
prs
104
issues
12
releases
README
Memvid is a single-file memory layer for AI agents with instant retrieval and long-term memory.
Persistent, versioned, and portable memory, without databases.
Website
·
Try Sandbox
·
Docs
·
Discussions
Benchmark Highlights
🚀 Higher accuracy than any other memory system : +35% SOTA on LoCoMo, best-in-class long-horizon conversational recall & reasoning
🧠 Superior multi-hop & temporal reasoning: +76% multi-hop, +56% temporal vs. the industry average
⚡ Ultra-low latency at scale 0.025ms P50 and 0.075ms P99, with 1,372× higher throughput than standard
🔬 Fully reproducible benchmarks: LoCoMo (10 × ~26K-token conversations), open-source eval, LLM-as-Judge
What is Memvid?
Memvid is a portable AI memory system that packages your data, embeddings, search structure, and metadata into a single file.
Instead of running complex RAG pipelines or server-based vector databases, Memvid enables fast retrieval directly from the file.
The result is a model-agnostic, infrastructure-free memory layer that gives AI agents persistent, long-term memory they can carry anywhere.
What are Smart Frames?
Memvid draws inspiration from video encoding, not to store video, but to organize AI memory as an append-only, ultra-efficient sequence of Smart Frames.
A Smart Frame is an immutable unit that stores content along with timestamps, checksums and basic metadata.
Frames are grouped in a way that allows efficient compression, indexing, and parallel reads.
This frame-based design enables:
- Append-only writes without modifying or corrupting existing data
- Queries over past memory states
- Timeline-style inspection of how knowledge evolves
- Crash safety through committed, immutable frames
- Efficient compression using techniques adapted from video encoding
The result is a single file that behaves like a rewindable memory timeline for AI systems.
Core Concepts
- 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.
Use Cases
Memvid is a portable, serverless memory layer that gives AI agents persistent memory and fast recall. Because it's model-agnostic, multi-modal, and works fully offline, developers are using Memvid across a wide range of real-world applications.
- Long-Running AI Agents
- Enterprise Knowledge Bases
- Offline-First AI Systems
- Codebase Understanding
- Customer Support Agents
- Workflow Automation
- Sales and Marketing Copilots
- Personal Knowledge Assistants
- Medical, Legal, and Financial Agents
- Auditable and Debuggable AI Workflows
- Custom Applications
SDKs & CLI
Use Memvid in your pTop issues
#243[BUG] Redundant closures in xlsx_chunker and xlsx_table_detect fail clippy::pedantic5 comments · 2026-07-24#218Feature Request: Concurrent Writers Support for Multi-Agent Scenarios5 comments · 2026-04-05#247[BUG] frame_context lowercases the whole document once per query word3 comments · 2026-08-09#143[FEATURE] llama.cpp integration3 comments · 2026-01-12#207[FEATURE] Add builds for `linux-arm64`2 comments · 2026-03-21#189C FFI Layer for memvid-core2 comments · 2026-01-28#240[FEATURE] Configure max index / time index bytes beyond 512MiB1 comments · 2026-07-21#217[FEATURE] Add MCP for Antigravity, ... IDE coding1 comments · 2026-04-05
Discussions
#246External embeddings fail after second put_many2 comments · 2026-07-30#208Kia AP ko lagta he k Iraq ki Jung Sahi he3 comments · 2026-03-22#203Support for reading .mv2 files directly from S3 via HTTP range requests?1 comments · 2026-03-03#144Help translate Memvid README – many languages available2 comments · 2026-01-12#114Dropped out at the capacity-based licensing in the works3 comments · 2026-01-08#92Welcome to memvid Discussions!2 comments · 2026-01-05
Latest release
v2.0.140 v2.0.140 2026-05-27Bug fixes 230 — WAL checksum mismatch after region growth Sustained put + commit workloads that grew the embedded WAL could corrupt it, surfacing as Embedded WAL is corrupted at offset N: wal record checksum mismatch (and, in some reports, runaway sparse-file growth past EOF). grow_wal_region / ensure_wal_capacity shifted the data region right by delta and updated data_end/footer_offset, but left cached_payload_end stale. rebuild_indexes then seeked to that pre-growth offset — now inside the grown WAL region — and overwrote live WAL record payloads. cached_payload_end is now advanced by the