### Setup

- Before using the AWS Bedrock LLM, make sure you have the appropriate model access from [Bedrock Console](https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/modelaccess).
- Model availability is per-region. `anthropic.claude-sonnet-4-20250514-v1:0` supports on-demand inference in `us-east-1` and `ap-southeast-4`; from any other region, use the cross-region inference profile ID `us.anthropic.claude-sonnet-4-20250514-v1:0` instead.
- Install the AWS SDK for your language: `pip install boto3` (Python) or `npm install @aws-sdk/client-bedrock-runtime` (TypeScript).
- Both SDKs fall back to the standard AWS credential chain (environment variables, `~/.aws/credentials`, or an attached IAM role), so exporting `AWS_REGION`, `AWS_ACCESS_KEY_ID`, and `AWS_SECRET_ACCESS_KEY` is the quickest way to get started. In TypeScript you can also pass credentials inline with `awsRegion`, `awsAccessKeyId`, `awsSecretAccessKey`, and `awsSessionToken`, as shown below.

### Usage

Python

```python
import os
from mem0 import Memory

os.environ['AWS_REGION'] = 'us-east-1'
os.environ["AWS_ACCESS_KEY_ID"] = "xx"
os.environ["AWS_SECRET_ACCESS_KEY"] = "xx"

config = {
    "llm": {
        "provider": "aws_bedrock",
        "config": {
            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
            "temperature": 0.2,
            "max_tokens": 2000,
        }
    }
}

m = Memory.from_config(config)
m.add([\
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},\
    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},\
    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},\
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}\
], user_id="alice", metadata={"category": "movies"})
```

TypeScript

```typescript
import { Memory } from 'mem0ai/oss';

const config = {
  llm: {
    provider: 'aws_bedrock',
    config: {
      model: 'anthropic.claude-sonnet-4-20250514-v1:0',
      temperature: 0.2,
      maxTokens: 2000,
      // Optional. Omit these to use the default AWS credential chain.
      awsRegion: process.env.AWS_REGION,
      awsAccessKeyId: process.env.AWS_ACCESS_KEY_ID,
      awsSecretAccessKey: process.env.AWS_SECRET_ACCESS_KEY,
    },
  },
};

const memory = new Memory(config);
const messages = [\
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},\
    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},\
    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},\
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}\
];
await memory.add(messages, { userId: 'alice', metadata: { category: 'movies' } });
```

`@aws-sdk/client-bedrock-runtime` is an optional peer dependency of `mem0ai`, so npm will not install it for you. The TypeScript provider loads it lazily and throws a clear error on the first request if the package is missing.

The TypeScript provider calls the Bedrock [Converse API](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html), a single uniform interface across the current Bedrock model families. Streaming and `InvokeModel`-only models are not supported yet.

### Config

All available parameters for the `aws_bedrock` config are present in [Master List of All Params in Config](https://docs.mem0.ai/components/llms/config).