🚨 Announcing a new coding agent that rivals Claude Code but with no compaction needed 🚨
The feeling of using it: run your coding sessions forever, don't worry at all, and get shit done!
We're calling it Mastra Code, it's powered by @mastra's new observational memory, and
Thanks everyone for the huge amount of interest/excitement about observational memory @mastra this week. It's amazing seeing folks try it and have the realizations we've had internally the last couple months!
@andefred we should compare notes again! Last time we met up, a lot of your feedback helped with how we created agent message processors (which this feature is built ontop of!)
Damnit @tylbar ! I hate it when you go and secretly build something that I’ve also just built (extending Mastra) and yours is 100x better than what I did 😂🤩! Amazing work and looking forward to migrating to this!
🚨 Announcing a new SOTA memory system, Observational Memory (OM), available in latest @mastra version now.
It achieves the highest scores ever recorded on LongMemEval (gpt-4o 84.2%, gpt-5-mini 94.9%)
No RAG, no graphs, no input based retrieval, just a simple constantly evolving
