# Memorable launches procedural memory for AI agents > YC S27 startup Memorable says it turns successful agent runs into reusable workflow graphs. The company reports up to 98% less context per prompt in one customer benchmark. - Publication: Go Big News - By Nifal Adam, Go Big News Staff (Staff News) - Category: Startups - Published: 2026-09-18T14:40:29.146+00:00 - Canonical: https://www.gobignews.com/startups/memorable-launches-procedural-memory-for-ai-agents --- Memorable, a Y Combinator Summer 2027 company, announced procedural memory for AI agents in a post on X by co-founder and CTO Advaiyt Sane. The two-person startup says its system turns successful agent runs into reusable graphs, rather than requiring agents to start over on repeat tasks. The product addresses a practical constraint for agent builders: work completed in one context window may not carry forward to the next. Memorable says it records a session, turns successful runs into workflows, connects those workflows in a graph and retrieves relevant workflows for new tasks. The company contrasts the approach with vector-search and RAG memory. It says its stored procedures contain steps, preconditions, postconditions and the result that determined whether a run passed, rather than text fragments. According to the [Memorable product site](https://www.memorable.sh/), retrieval uses exact, lexical and semantic matching. The company says recall takes about 60 milliseconds and lists Claude Code, Codex, Cursor, gbrain and QM among compatible tools; custom agents can submit JSON traces. Memorable also says procedures remain in customer-controlled storage, including local files, gbrain databases and Postgres instances. It says only prompts and allow-listed tool arguments leave the machine, while session IDs, user emails, working directories and file contents stay local. Memory use is opt-in and fail-closed, the company says. The startup reported several customer benchmarks that were not independently verified. It said OpenHome's task-completion rate rose to 100% from 70%; gstack used 293 tokens per prompt versus 15,593, a 98% reduction; and Quartermaster made 40% fewer tool calls, with a 91% pass rate compared with 80% without memory. Memorable was founded in 2026 and is based in the San Francisco Bay Area, according to its [Y Combinator company profile](https://www.ycombinator.com/companies/memorable). Its founders are CEO Nikhil Krishnaswamy, a Stanford CS graduate, and Sane, a Carnegie Mellon CS student. Krishnaswamy previously built an iOS Model Context Protocol tool at AGI Inc, while Sane previously built Nvidia developer tools that generate roughly 50,000 autonomous-vehicle tests per month. The company announced the news in a post on X. --- ## Companies in this story - Memorable: https://www.gobignews.com/company/memorablesh --- ## X profiles in this story - @advaiytsane: https://www.gobignews.com/profile/advaiytsane