An open-source TUI coding agent with observational memory that compresses context without losing it.
Define test cases, run experiments, and track response quality for every change you make.
Learn how Mastra is optimized for modern AI systems, and how to implement a similar approach.
Observational memory async buffering (default-on) with new structured streaming events, workspace mounts with CompositeFilesystem for unified multi-provider file access
A human-inspired memory system that scores ~95% on LongMemEval — with a completely stable context window.
File access, command execution, and reusable skills for agents that actually get things done.
Agents can pause before tool calls. Workflows can suspend at steps. But when they're working together, where's the right place for a human-in-the-loop?
When should an agent ask for permission? How to think about approval, suspension, and the trust spectrum in your agent design.