You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -345,7 +345,7 @@ You can customize the namespace (where the memories are stored) by configuring t
345
345
```hcl
346
346
module "agentcore" {
347
347
source = "aws-ia/agentcore/aws"
348
-
version = "0.0.2"
348
+
version = "0.0.3"
349
349
350
350
# Enable Agent Core Memory
351
351
create_memory = true
@@ -449,7 +449,7 @@ The Browser construct supports the following network modes:
449
449
```hcl
450
450
module "agentcore" {
451
451
source = "aws-ia/agentcore/aws"
452
-
version = "0.0.2"
452
+
version = "0.0.3"
453
453
454
454
# Enable Agent Core Browser Custom
455
455
create_browser = true
@@ -477,6 +477,160 @@ module "agentcore" {
477
477
}
478
478
```
479
479
480
+
### AgentCore Gateway Target
481
+
482
+
The Amazon Bedrock AgentCore Gateway Target enables you to define the endpoints and configurations that a gateway can invoke, such as Lambda functions or MCP servers. Gateway targets allow agents to interact with external services through the Model Context Protocol (MCP).
483
+
484
+
```hcl
485
+
module "agentcore" {
486
+
source = "aws-ia/agentcore/aws"
487
+
version = "0.0.3"
488
+
489
+
# First, create a gateway
490
+
create_gateway = true
491
+
gateway_name = "MyGateway"
492
+
493
+
# Then create a gateway target for Lambda
494
+
create_gateway_target = true
495
+
gateway_target_name = "MyLambdaTarget"
496
+
gateway_target_description = "Lambda function target for processing requests"
The Amazon Bedrock AgentCore Workload Identity enables you to manage identity configurations for resources such as AgentCore runtime and AgentCore gateway. Workload identities provide secure access management and OAuth2 integration capabilities for your Bedrock AI applications.
The Amazon Bedrock AgentCore Code Interpreter enables AI agents to write and execute code securely in sandbox environments, enhancing their accuracy and expanding their ability to solve complex end-to-end tasks. This is critical in Agentic AI applications where the agents may execute arbitrary code that can lead to data compromise or security risks. The AgentCore Code Interpreter tool provides secure code execution, which helps you avoid running into these issues.
@@ -507,7 +661,7 @@ The Code Interpreter construct supports the following network modes:
0 commit comments