FrontierMemory FrontierMemory is a continuous benchmark that evaluates AI agent memory through its effect on downstream task performance, efficiency, and capability rather than simple recall. It converts challenging coding and knowledge-work tasks into environments that require learning from prior trajectories.
Visit productFeatured media
Loading media…
View on XCosigns Received
“Letta's new test for AI memory doesn't ask "can it recall the fact?" It asks "did it do the next task better?" That's the only memory test that matters. A team that writes everything down but repeats the same mistake doesn't have memory. It has a filing cabinet.”
“Recommended reading and a super-interesting benchmark for measuring continual learning capabilities through memory. Agent memory is largely unsolved. As agents advance in capabilities like long-horizon work, it's unclear which models or harnesses work best, or which memory systems and types to use. Opus 5.5 at the top is not a surprise. But it's exciting that open-weight models like GLM-5.3 perform so well on memory generation. My big question is how this (better memory systems and persistent agent capabilities) translates into more performant, efficient RSI agents and harnesses.”
“FrontierMemory from @Letta_AI is the first benchmark to measure memory based on performance on downstream tasks. Memory remains one of the biggest unsolved challenges in AI. FrontierMemory ACTUALLY gives us a way to actually measure and compare memory capabilities across different harnesses and models.”
“Most memory benchmarks test recall and not synthesis. My former students just launched an exciting new memory benchmark that evaluates whether agents can continually learn from past experiences.”
“Memory is one of the biggest unsolved challenges in AI today. @Letta_AI’s FrontierMemory is the first benchmark to measure AI memory by downstream task performance, across models and harnesses. Amazing work team @Letta_AI 👏👏 cc @khoslaventures @vkhosla”
“Many harnesses and agent products now support “continual learning”. FrontierMemory from @Letta_AI is the first benchmark to measure how agents can study their past experience to generate memory that improves their capabilities.”