Introducing @supermemory/tools v2.0.0

Supermemory tools v2.0.0 introduces a unified configuration-object API across Vercel AI SDK, OpenAI SDK, Mastra, and VoltAgent, replacing inconsistent positional arguments and conversation identifier names with a required non-empty `customId` for grouping session messages into retrievable conversation records. Memory saving now defaults to “always” for Vercel, OpenAI, and Mastra integrations, while users needing read-only retrieval can explicitly disable saving. The release also adds VoltAgent warnings for irrelevant search settings in profile mode and incorporates capabilities introduced since v1.0, including integrations for OpenAI, Mastra, and VoltAgent; profile, query, and full retrieval modes; customizable memory prompt templates; error-tolerant retrieval and timeouts; browser-compatible API-key configuration; and performance improvements such as deduplication, caching, and parallel tool calls. Migration from v1.4.x primarily involves moving `containerTag` into the options object, renaming conversation fields to `customId`, and explicitly setting memory saving to “never” where the previous default behavior is required.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.