
Observational Memory by Mastra
Give your AI agents human-like memory
About Observational Memory by Mastra
Observational Memory is a SoTA memory system for AI agents - scoring 95% on LongMemEval, the highest ever recorded. It works like human memory: two background agents act as your agent's subconscious, one observing and compressing conversations, the other reflecting and reorganizing long-term memory. It extracts what matters and lets the rest fade - just like you do. Available in Mastra today - with adapters for LangChain, Vercel AI SDK, OpenCode and others coming soon.
The person behind Observational Memory by Mastra
More Software Engineering launches
SeclaiEverything you need around your LLM calls.Oct 22, 2026 · 1 person
BAND for DevelopersCoding agents, meet teamworkOct 21, 2026 · 1 person
Terraform Automation by BuddyAI moves fast. Keep your infrastructure under control.Oct 21, 2026 · 2 people
RunInfraOpen models, built for agents.Oct 20, 2026 · 1 person- Buildhorn: CI/CD AlertsKnow the instant your build breaksOct 18, 2026 · 1 person
Kerno 1.0The AI Runtime Backend QA EngineerOct 15, 2026 · 1 person
Made Observational Memory by Mastra? Ask us to remove this listing or your details.