Name: mem0-vercel-ai-sdk
Author: mem0ai

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamTex

Mem0 Vercel AI SDK Provider Memory enhanced AI provider for Vercel AI SDK. Automatically retrieves and stores memories during LLM calls. Step 1: Install ai and the @ai sdk/ provider packages ship as regular dependencies of @mem0/vercel ai provider , so nothing else needs installing. The only peer dependency is zod (optional, ^3.0.0 ). Step 2: Set up environment variables Get a Mem0 API key at: https://app.mem0.ai/dashboard/api keys?utm source=oss&utm medium=skill mem0 vercel ai sdk Pattern 1: Wrapped Model The wrapped model approach is the simplest. createMem0 returns a provider that wraps any supported LLM with automatic memory retrieval and storage. What happens under the hood: 1. The prompt is stored to Mem0 ( POST /v3/memories/add/ ), awaited before the LLM call (a failed write is logged and ignored) 2. The prompt is sent to Mem0 search ( POST /v3/memories/search/ ) to retrieve relevant memories 3. If any memories are found, they are injected as a system message at the start of the prompt 4. The underlying LLM (e.g., OpenAI gpt 5 mini) generates a response using the enriched prompt For generateText , the retrieved memories are also attached to the result as a source: The source has title: "Mem0 Memories" and providerMetadata.mem0 holds memories (array of memory objects) and memoriesText . It is only present when at least one memory was retrieved. Pattern 2: Standalone Utilities Use standalone utilities when you want full control over the memory retrieve/store cycle, or you want to use a provider that is already configured separately. Pattern 3: Streaming Use streamText for streaming responses with memory augmentation: The wrapped model stores the conversation and retrieves memories before streaming begins. Supported Providers Provider Config value Required env var OpenAI (default) "openai" OPENAI API KEY Anthropic "anthropic" ANTHROPIC API KEY Google "google" (alias "gemini" ) GOOGLE GENERATIVE AI API KEY Groq "groq" GROQ API KEY Cohere "cohere" COHERE API KEY Select a provider when creating the Mem0 instance: How It Works Internally Wrapped model flow Standalone flow Key Differences Between the 4 Utility Functions Function Returns Use when retrieveMemories Formatted system prompt string Injecting directly into system parameter getMemories Raw memory array Processing memories programmatically searchMemories Raw search response (as returned by the API) Need scores and full metadata addMemories API response Storing new messages to Mem0 retrieveMemories , getMemories , and searchMemories accept LanguageModelV3Prompt string as the first argument; addMemories is typed as LanguageModelV3Prompt (a string also works at runtime). All four take optional Mem0ConfigSettings as the second argument. Common Edge Cases and Tips Always provide user id (or agent id / app id / run id ) for consistent memory retrieval. The search endpoint requires at least one entity ID in filters ; the provider places these IDs there for you. Standalone utilities require explicit API key : pass mem0ApiKey in the config object, or set the MEM0 API KEY environment variable. This uses Vercel AI SDK v6 (LanguageModelV3 / ProviderV3 interfaces, @mem0/vercel ai provider 3.x). Provider 2.x targeted AI SDK v5. It is not compatible with AI SDK v4 or earlier. processMemories awaits addMemories before searching and calling the LLM, so each wrapped call includes one memory write and one memory search. If either request fails, the error is logged and the LLM call proceeds without memories. "google" and "gemini" are both accepted and map to @ai sdk/google . Removed in 3.0.0 : org id , project id , org name , project name , output format , filter memories , async mode , enable graph , version , api version . Graph memory is now a Mem0 Platform project setting, not a provider option. Default top k is 10. threshold and rerank are only sent when set (the API default for rerank is false ; threshold is a server side cutoff, not a floor on the returned score). Custom host : set host in the config to point to a different Mem0 API endpoint (default: https://api.mem0.ai ). References Topic File Provider API ( createMem0 , Mem0Provider , types) [local](references/provider api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0 vercel ai sdk/references/provider api.md) Memory utilities ( addMemories , retrieveMemories , etc.) [local](references/memory utilities.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0 vercel ai sdk/references/memory utilities.md) Usage patterns and examples [local](references/usage patterns.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0 vercel ai sdk/references/usage patterns.md) Related Mem0 Skills Skill When to use Link mem0 Python/TypeScript SDK, REST API, framework integrations [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) mem0 cli Terminal commands, scripting, CI/CD, agent tool loops [local](../mem0 cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0 cli)