EverMind-AI/MSA
Scalable sparse attention for 100M token contexts
View on index · View in 3D Map
Related repos
- Operating system for agents with long-term memory
- Context-aware AI assistant for the desktop
- open-source language and vision models with huge context window and hybrid attention
- Context data platform for AI agents
- Background context compression for AI agents
- Model with sparse attention for long-context scenarios
- AI platform for building enterprise assistants and automating tasks
- efficient attention for long-context LLMs
- private AI assistant that runs in your browser
- World’s first open-weight hybrid-attention reasoning model with 1M token context and 456B parameters
