diff --git a/docs/docs.json b/docs/docs.json index 6d2fc0123..e4f2630a3 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -325,6 +325,7 @@ "integrations/google-ai-adk", "integrations/mastra", "integrations/vercel-ai-sdk", + "integrations/vercel", "integrations/chatdev", "integrations/strands" ] diff --git a/docs/integrations/vercel.mdx b/docs/integrations/vercel.mdx new file mode 100644 index 000000000..b755bca70 --- /dev/null +++ b/docs/integrations/vercel.mdx @@ -0,0 +1,130 @@ +--- +title: Vercel +description: "Add persistent memory to your Vercel apps with the Mem0 Vercel Marketplace integration. Install from the Marketplace, get an API key, and start building." +--- + +The **Mem0 Vercel integration** provisions managed Mem0 access directly from the [Vercel Marketplace](https://vercel.com/marketplace). Installing it creates a Mem0 account for you and injects a `MEM0_API_KEY` into your Vercel project, so you can add long-term memory to your AI apps and agents in minutes, with no separate signup and billing handled through Vercel. + + + This is the managed Marketplace integration. If you instead want to use Mem0 with the Vercel AI SDK in code, see [Vercel AI SDK](/integrations/vercel-ai-sdk). + + +## Overview + +When you install Mem0 from the Vercel Marketplace: + +- A Mem0 account and project are created for you (Vercel Native). +- Mem0 environment variables (`MEM0_API_KEY`, `MEM0_ORG_ID`, `MEM0_PROJECT_ID`, `MEM0_BASE_URL`) are added to your connected Vercel project. +- Billing is handled through your Vercel account, with no separate Mem0 subscription. + +You call Mem0 from your app with the injected key. There is nothing else to wire up. + +## Install + + + + From the [Vercel Marketplace](https://vercel.com/marketplace), find **Mem0** and click **Install**. Choose **Create New Mem0 Account** (Vercel Native). + + + Select **Hobby** (free) or **Starter** ($20/month). You can change this anytime from the installation settings in your Vercel dashboard. + + + Connect the Mem0 resource to a Vercel project. Mem0 injects its environment variables into that project. + + + Redeploy so the variables are available at runtime, or run `vercel env pull` to use them locally. + + + +## Environment variables + +The integration sets the following on your connected project: + +| Variable | Description | +| --- | --- | +| `MEM0_API_KEY` | Your Mem0 API key, scoped to the org and project created for this installation. This is what you authenticate with. | +| `MEM0_ORG_ID` | The Mem0 organization id for this installation. | +| `MEM0_PROJECT_ID` | The Mem0 project id for this installation. | +| `MEM0_BASE_URL` | The Mem0 API base URL (`https://api.mem0.ai`). | + +The API key is scoped to your org and project, so the SDK needs only `MEM0_API_KEY` to get started. + +## Quickstart + +Install the SDK: + + +```bash npm +npm install mem0ai +``` + +```bash pip +pip install mem0ai +``` + + +Add and search memories using the injected key: + + +```typescript JavaScript +import MemoryClient from "mem0ai"; + +const memory = new MemoryClient({ apiKey: process.env.MEM0_API_KEY }); + +// Store a memory +await memory.add( + [{ role: "user", content: "I'm a vegetarian and allergic to nuts." }], + { userId: "user123" }, +); + +// Retrieve relevant memories +const results = await memory.search("What are my dietary restrictions?", { + filters: { user_id: "user123" }, +}); +console.log(results); +``` + +```python Python +import os +from mem0 import MemoryClient + +memory = MemoryClient(api_key=os.environ["MEM0_API_KEY"]) + +# Store a memory +memory.add( + [{"role": "user", "content": "I'm a vegetarian and allergic to nuts."}], + user_id="user123", +) + +# Retrieve relevant memories +results = memory.search("What are my dietary restrictions?", filters={"user_id": "user123"}) +print(results) +``` + + +See the [platform quickstart](/platform/quickstart) for the full API. + +## Plans and billing + +| Plan | Price | Memories | Retrieval calls | Projects | Support | +| --- | --- | --- | --- | --- | --- | +| Hobby | Free | 10,000 | 1,000 / month | 1 | Community | +| Starter | $20 / month | 50,000 | 5,000 / month | 1 | Community | + +Billing runs through your Vercel account; Mem0 never charges your card directly. You can upgrade or downgrade anytime from the installation's settings in the Vercel dashboard. + +## Managing the integration + +- **Change plan:** open the installation in your Vercel dashboard and update the billing plan. +- **Open in Mem0:** use the **Open in Mem0** link to sign in to the Mem0 dashboard for this installation. +- **Uninstall:** removing the integration deactivates the API key and tears down the resource. Any usage for the current period is invoiced before removal. + +## Notes + +- The integration creates a **new** Mem0 account for the installation. Linking an existing Mem0 account is not supported yet. +- The injected `MEM0_API_KEY` is scoped to the org and project created for this installation, so you do not manage keys by hand. + +## Related + +- [Platform quickstart](/platform/quickstart) +- [Vercel AI SDK integration](/integrations/vercel-ai-sdk) diff --git a/docs/llms.txt b/docs/llms.txt index 67ccbf257..7310f6c1b 100644 --- a/docs/llms.txt +++ b/docs/llms.txt @@ -263,6 +263,7 @@ If the user is on a pre-current major (Python < 2, TS < 3, or a Platform call st - [Mastra](https://docs.mem0.ai/integrations/mastra) [Platform]: Use when the user is on Mastra (TypeScript). - [OpenClaw](https://docs.mem0.ai/integrations/openclaw) [Both]: Use when wiring Mem0 into Claude Code or editors via OpenClaw. - [Vercel AI SDK](https://docs.mem0.ai/integrations/vercel-ai-sdk) [Both]: Use when the user is on the Vercel AI SDK. +- [Vercel](https://docs.mem0.ai/integrations/vercel) [Platform]: Use when deploying on Vercel and installing Mem0 from the Vercel Marketplace. - [Strands Agents](https://docs.mem0.ai/integrations/strands) [Both]: Use when the user is on AWS Strands and wants a native MemoryStore. ### AI Coding Tools