Past.dev
A memory layer for AI agents: send it emails, call notes, tickets and chats with timestamps, and it returns current facts with dated sources, limited to what the asking user may see. Pay as you go, or a Flex plan from $99 a month.
About this launch
Past.dev is a memory service for AI agents, introduced by its makers in a post of 30 September 2026 and opened for self-serve sign-up the same day. Teams send it text with timestamps, such as emails, call notes, support tickets and chat messages; Past.dev derives facts from them and, when an agent asks, returns the facts that are current, each with the dated source it came from, and only those the person on whose behalf the agent is acting is allowed to see. It is meant for products where an agent needs long-term context about customers or accounts without re-reading every document. The company presented it on Hacker News on 1 October. Pricing on its own page is pay-as-you-go credit packs (150,000 credits for $45, or 400,000 for $120 with a work email) or a Flex plan from $99 a month with unlimited recall calls, and early-stage start-ups can have six months of Flex free. Past.dev reports a leading result on a long-memory benchmark; that is its own claim.
Not yet independently verified: The launch date rests on the company’s own announcement of 30 September 2026. The site names no operating company or location, its benchmark claim is its own, and no independent report was found. We will update this when it can be confirmed, and remove this note.
Discussion
Questions & answers about Past.dev.
No questions yet. Be the first to ask about Past.dev.
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- All launchesToday's board, this week's and the all-time archive.
- Past.dev on TrustListReviews, pricing, features and alternatives.
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.