@oliviscusAI: Someone open-sourced a memory layer that beats every RAG system on the planet. It's called Memvid. +35% SOTA on LoCoMo.…
Summary
A new open-source memory layer called Memvid claims to outperform all existing RAG systems, achieving +35% SOTA on LoCoMo and +76% on multi-hop reasoning, packaged as a single .mv2 file.
View Cached Full Text
Cached at: 05/11/26, 04:48 PM
Someone open-sourced a memory layer that beats every RAG system on the planet.
It’s called Memvid. +35% SOTA on LoCoMo. +76% on multi-hop reasoning. All from a single .mv2 file you can carry anywhere.
100% Open Source. https://t.co/s9lJ6qrE4V
Similar Articles
@hasantoxr: I'm replacing every memory layer I've ever built into an agent with this. SureThing dropped SOTA on LongMemEval. 88.0% …
SureThing has achieved state-of-the-art results on the LongMemEval benchmark, scoring 88.0% overall, prompting developers to replace existing memory layers in their AI agents.
Cognis: Context-Aware Memory for Conversational AI Agents
Lyzr Cognis introduces a unified, open-source memory system for conversational AI that fuses BM25 and Matryoshka vector search with version-aware ingestion, achieving SOTA on LoCoMo and LongMemEval benchmarks.
MemoryOS – AI agent memory with temporal knowledge graph and 9ms ingest and 78ms retrieval
MemoryOS is an open-source, self-hosted AI agent memory tool using a temporal knowledge graph, achieving 86.2% accuracy on LongMemEval-s with fast 78ms retrieval speeds.
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
SuperLocalMemory V3.3 introduces a unified memory and learning system for AI agents with biologically-inspired forgetting, multi-channel retrieval, and P2P mesh coordination. The system achieves 74.8% on LoCoMo benchmarks and features triple-stream learning, lifecycle management, and EU AI Act compliance.
rohitg00/agentmemory
agentmemory is an open-source persistent memory layer for AI coding agents (Claude Code, Cursor, Gemini CLI, Codex CLI, etc.) that uses knowledge graphs, confidence scoring, and hybrid search to give agents long-term memory across sessions via MCP, hooks, or REST API. Built on the iii engine, it requires no external databases and exposes 51 MCP tools.