Alyx now remembers your work across sessions with long-term memory

Arize AX has added long-term memory to Alyx, its AI engineering agent, enabling it to retain project goals, conventions, preferences and prior decisions across sessions, and the feature is enabled by default for all Arize AX users. Memory is scoped by user and Arize space, is not shared with teammates or across spaces, and users can ask Alyx to show, correct or delete memories in chat. Arize said Alyx stores durable context that is hard to reconstruct from the platform alone while looking up current configurations, IDs and live metrics on demand.

AI engineering rarely happens in one conversation. You might investigate a production issue today, return later to build an eval, compare an experiment https://arize.com/docs/ax/develop/datasets-and-experiments , or refine a prompt. Along the way, you establish context that matters the next time you work. Alyx https://arize.com/docs/ax/alyx , the AI engineering agent in Arize AX https://arize.com/products/ax/ , can now retain that context across sessions with long-term memory . It can remember durable information such as project goals, conventions, preferences, and previous decisions, so you spend less time re-explaining your environment and more time continuing the work. TL;DR: Alyx now includes https://arize.com/products/alyx/ ’s long-term memory that keeps useful context across sessions and is enabled by default for all users of Arize AX. Memories aren’t shared with teammates or across spaces, and you can ask Alyx to show, correct, or delete them in chat. Build better agents with Arize Trace, evaluate, and learn. Build agents that work with Arize AX and start tracing your runs today. Prefer open source? Try Arize Phoenix for self-hosted, open source agent observability https://arize.com/phoenix?utm source=blog&utm medium=referral&utm campaign=ax-inline-cta&utm content=alyx-arize-ax-long-term-memory-inline-cta-phoenix . What Alyx remembers across sessions Alyx can remember things like: - how you define a successful response for your agent - where ground truth lives - a production target you are working toward - dataset or workflow conventions - approaches you rejected and why The focus is on context that is useful across sessions and difficult to reconstruct from the platform alone. Alyx can look up current configurations, IDs, and live metrics when it needs them, so storing those details as memories could mean relying on information that’s already out of date. That leaves memory for the context you shouldn’t have to explain again, such as why you chose a particular approach or which tradeoffs matter and why. Find out how we built long-term memory in Alyx Explore our guide for a full breakdown of the engineering behind long-term memory in Alyx https://arize.com/blog/alyx-agent-long-term-memory-architecture/ plus the considerations and choices we made . Use remembered context across traces, evals, and experiments in Arize AX Alyx is available across traces https://arize.com/docs/ax/instrument/what-are-traces , eval workflows https://arize.com/glossary/evaluations/ , experiments, and other AI engineering surfaces in Arize AX. For example, while investigating a support agent’s traces, you might explain that refund requests require a policy check before the agent recommends an action. When you return in a new session to build an evaluator https://arize.com/docs/ax/evaluate/create-evaluators , Alyx can use that remembered requirement to help define what the evaluator should check. Memory is scoped by user and Arize space , so context stays relevant to the work you are doing. How we built long-term memory for Alyx Building useful memory means deciding what Alyx should remember, what it can retrieve from AX, and how that context should carry across sessions without getting in the way. For a deeper look at the architecture, tradeoffs, and evaluation behind the system, read Priyan Jindal’s How we built long-term memory for Alyx https://arize.com/blog/alyx-agent-long-term-memory-architecture/ . Keep working without starting over Long-term memory gives Alyx more continuity across sessions and workflows, so you can return to a project with more of the important context intact.