Show HN: FastRecall, ultra-cheap memory across AI models

A former OpenAI memory engineer launched FastRecall, an API that stores and recalls context across different AI models, with free recalls and paid plans starting at $2 per month. FastRecall respects provider caching when the same model is reused to cut inference costs and offers model-free context compaction via FlashCompact. The tool targets users of model aggregators such as OpenRouter who lose context when switching between AI models.

Hi everyone After working on memory at OpenAI, I built FastRecall to solve one problem: using different AI models results in clunky ad-hoc context management systems or lost context entirely. With the model layer becoming commoditized, your context should travel seamlessly across models whether you are using OpenRouter or some other model aggregator. FastRecall offers a simple API that stores your context cheaply and efficiently. In fact, we are so cheap that recalls are entirely free, with generous plans starting at only $2/month If you use the same model again, FastRecall respects provider caching to save you inference costs. We also have SOTA model-free compaction of context with FlashCompact, in case you don't need full-fidelity context. Hopefully this is useful for some of your projects. Let me know what you think Comments URL: https://news.ycombinator.com/item?id=49735358 https://news.ycombinator.com/item?id=49735358 Points: 1 Comments: 0