@aws/agentcore 0.7.1 → 0.8.1

package/README.md

@@ -1,6 +1,12 @@
 <div align="center">
   <h1>AgentCore CLI</h1>
-  <h2>Create, develop, and deploy AI agents to Amazon Bedrock AgentCore</h2>
+  <p><strong>Create, develop, and deploy AI agents to Amazon Bedrock AgentCore</strong></p>
+
+  <p>
+    <a href="https://github.com/aws/agentcore-cli/actions/workflows/build-and-test.yml"><img src="https://img.shields.io/github/actions/workflow/status/aws/agentcore-cli/build-and-test.yml?branch=main&label=build" alt="Build Status"></a>
+    <a href="https://www.npmjs.com/package/@aws/agentcore"><img src="https://img.shields.io/npm/v/@aws/agentcore" alt="npm version"></a>
+    <a href="LICENSE"><img src="https://img.shields.io/github/license/aws/agentcore-cli" alt="License"></a>
+  </p>
 </div>
 
 ## Overview
@@ -60,17 +66,18 @@ agentcore invoke
 | ------------------- | ----------------------------- |
 | Strands Agents      | AWS-native, streaming support |
 | LangChain/LangGraph | Graph-based workflows         |
+| CrewAI              | Multi-agent orchestration     |
 | Google ADK          | Gemini models only            |
 | OpenAI Agents       | OpenAI models only            |
 
 ## Supported Model Providers
 
-| Provider       | API Key Required          | Default Model                 |
-| -------------- | ------------------------- | ----------------------------- |
-| Amazon Bedrock | No (uses AWS credentials) | claude-sonnet-4-5-20250929-v1 |
-| Anthropic      | Yes                       | claude-sonnet-4-5-20250929    |
-| Google Gemini  | Yes                       | gemini-2.5-flash              |
-| OpenAI         | Yes                       | gpt-4o                        |
+| Provider       | API Key Required          | Default Model                                |
+| -------------- | ------------------------- | -------------------------------------------- |
+| Amazon Bedrock | No (uses AWS credentials) | us.anthropic.claude-sonnet-4-5-20250514-v1:0 |
+| Anthropic      | Yes                       | claude-sonnet-4-5-20250514                   |
+| Google Gemini  | Yes                       | gemini-2.5-flash                             |
+| OpenAI         | Yes                       | gpt-4.1                                      |
 
 ## Commands
 
@@ -85,13 +92,22 @@ agentcore invoke
 
 ### Resource Management
 
-| Command  | Description                                       |
-| -------- | ------------------------------------------------- |
-| `add`    | Add agents, memory, identity, evaluators, targets |
-| `remove` | Remove resources from project                     |
+| Command  | Description                                          |
+| -------- | ---------------------------------------------------- |
+| `add`    | Add agents, memory, credentials, evaluators, targets |
+| `remove` | Remove resources from project                        |
 
 > **Note**: Run `agentcore deploy` after `add` or `remove` to update resources in AWS.
 
+### Observability
+
+| Command       | Description                             |
+| ------------- | --------------------------------------- |
+| `logs`        | Stream or search agent runtime logs     |
+| `traces list` | List recent traces for a deployed agent |
+| `traces get`  | Download a trace to a JSON file         |
+| `status`      | Show deployed resource details          |
+
 ### Evaluations
 
 | Command              | Description                                   |
@@ -102,6 +118,16 @@ agentcore invoke
 | `evals history`      | View past eval run results                    |
 | `pause online-eval`  | Pause a deployed online eval config           |
 | `resume online-eval` | Resume a paused online eval config            |
+| `logs evals`         | Stream or search online eval logs             |
+
+### Utilities
+
+| Command        | Description                               |
+| -------------- | ----------------------------------------- |
+| `validate`     | Validate configuration files              |
+| `package`      | Package agent artifacts without deploying |
+| `fetch access` | Fetch access info for deployed resources  |
+| `update`       | Check for and install CLI updates         |
 
 ## Project Structure
 
@@ -129,7 +155,7 @@ my-project/
 
 Projects use JSON schema files in the `agentcore/` directory:
 
-- `agentcore.json` - Agent specifications, memory, identity, evaluators, online evals
+- `agentcore.json` - Agent specifications, memory, credentials, evaluators, online evals
 - `deployed-state.json` - Runtime state in agentcore/.cli/ (auto-managed)
 - `aws-targets.json` - Deployment targets (account, region)
 
@@ -137,7 +163,7 @@ Projects use JSON schema files in the `agentcore/` directory:
 
 - **Runtime** - Managed execution environment for deployed agents
 - **Memory** - Semantic, summarization, and user preference strategies
-- **Identity** - Secure API key management via Secrets Manager
+- **Credentials** - Secure API key management via Secrets Manager
 - **Evaluations** - LLM-as-a-Judge for on-demand and continuous agent quality monitoring
 
 ## Documentation

package/dist/assets/README.md

@@ -58,7 +58,7 @@ The project uses a **flat resource model** where agents, memories, and credentia
 | Command              | Description                                     |
 | -------------------- | ----------------------------------------------- |
 | `agentcore create`   | Create a new AgentCore project                  |
-| `agentcore add`      | Add resources (agent, memory, identity, target) |
+| `agentcore add`      | Add resources (agent, memory, credential, target) |
 | `agentcore remove`   | Remove resources                                |
 | `agentcore dev`      | Run agent locally                               |
 | `agentcore deploy`   | Deploy to AWS                                   |
@@ -70,7 +70,7 @@ The project uses a **flat resource model** where agents, memories, and credentia
 
 ### Agent Types
 
-- **Template agents**: Created from framework templates (Strands, LangChain_LangGraph, GoogleADK, OpenAIAgents)
+- **Template agents**: Created from framework templates (Strands, LangChain_LangGraph, CrewAI, GoogleADK, OpenAIAgents)
 - **BYO agents**: Bring your own code with `agentcore add agent --type byo`
 
 ## Documentation

package/dist/assets/__tests__/__snapshots__/assets.snapshot.test.ts.snap

@@ -357,8 +357,8 @@ exports[`Assets Directory Snapshots > CDK assets > cdk/cdk/package.json should m
     "typescript": "~5.9.3"
   },
   "dependencies": {
-    "@aws/agentcore-cdk": "^0.1.0-alpha.1",
-    "aws-cdk-lib": "2.243.0",
+    "@aws/agentcore-cdk": "0.1.0-alpha.18",
+    "aws-cdk-lib": "^2.248.0",
     "constructs": "^10.0.0"
   }
 }
@@ -1167,6 +1167,7 @@ Thumbs.db
 exports[`Assets Directory Snapshots > Python framework assets > python/python/a2a/langchain_langgraph/base/main.py should match snapshot 1`] = `
 "from langchain_core.tools import tool
 from langgraph.prebuilt import create_react_agent
+from opentelemetry.instrumentation.langchain import LangchainInstrumentor
 from a2a.server.agent_execution import AgentExecutor, RequestContext
 from a2a.server.events import EventQueue
 from a2a.server.tasks import TaskUpdater
@@ -1175,6 +1176,8 @@ from a2a.utils import new_task
 from bedrock_agentcore.runtime import serve_a2a
 from model.load import load_model
 
+LangchainInstrumentor().instrument()
+
 
 @tool
 def add_numbers(a: int, b: int) -> int:
@@ -1382,6 +1385,7 @@ dependencies = [
     {{/if}}{{#if (eq modelProvider "Gemini")}}"langchain-google-genai >= 2.0.0",
     {{/if}}{{#if (eq modelProvider "OpenAI")}}"langchain-openai >= 0.2.0",
     {{/if}}"aws-opentelemetry-distro",
+    "opentelemetry-instrumentation-langchain >= 0.59.0",
     "bedrock-agentcore[a2a] >= 1.0.3",
     "botocore[crt] >= 1.35.0",
     "langgraph >= 0.2.0",
@@ -2526,6 +2530,7 @@ exports[`Assets Directory Snapshots > Python framework assets > python/python/ht
 from langchain_core.messages import HumanMessage
 from langgraph.prebuilt import create_react_agent
 from langchain.tools import tool
+from opentelemetry.instrumentation.langchain import LangchainInstrumentor
 from bedrock_agentcore.runtime import BedrockAgentCoreApp
 from model.load import load_model
 {{#if hasGateway}}
@@ -2534,6 +2539,8 @@ from mcp_client.client import get_all_gateway_mcp_client
 from mcp_client.client import get_streamable_http_mcp_client
 {{/if}}
 
+LangchainInstrumentor().instrument()
+
 app = BedrockAgentCoreApp()
 log = app.logger
 
@@ -2825,6 +2832,7 @@ readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
     "aws-opentelemetry-distro",
+    "opentelemetry-instrumentation-langchain >= 0.59.0",
     "langgraph >= 1.0.2",
     "mcp >= 1.19.0",
     "langchain-mcp-adapters >= 0.1.11",
@@ -3915,7 +3923,7 @@ The project uses a **flat resource model** where agents, memories, and credentia
 | Command              | Description                                     |
 | -------------------- | ----------------------------------------------- |
 | \`agentcore create\`   | Create a new AgentCore project                  |
-| \`agentcore add\`      | Add resources (agent, memory, identity, target) |
+| \`agentcore add\`      | Add resources (agent, memory, credential, target) |
 | \`agentcore remove\`   | Remove resources                                |
 | \`agentcore dev\`      | Run agent locally                               |
 | \`agentcore deploy\`   | Deploy to AWS                                   |
@@ -3927,7 +3935,7 @@ The project uses a **flat resource model** where agents, memories, and credentia
 
 ### Agent Types
 
-- **Template agents**: Created from framework templates (Strands, LangChain_LangGraph, GoogleADK, OpenAIAgents)
+- **Template agents**: Created from framework templates (Strands, LangChain_LangGraph, CrewAI, GoogleADK, OpenAIAgents)
 - **BYO agents**: Bring your own code with \`agentcore add agent --type byo\`
 
 ## Documentation
@@ -4019,7 +4027,7 @@ file maps to a JSON config file and includes validation constraints as comments.
 - **LangChain_LangGraph** - Works with Bedrock, Anthropic, OpenAI, Gemini
 - **GoogleADK** - Gemini only
 - **OpenAIAgents** - OpenAI only
-- **AutoGen** - Works with Bedrock, Anthropic, OpenAI, Gemini
+
 
 ### Specific Context
 

package/dist/assets/agents/AGENTS.md

@@ -79,7 +79,7 @@ file maps to a JSON config file and includes validation constraints as comments.
 - **LangChain_LangGraph** - Works with Bedrock, Anthropic, OpenAI, Gemini
 - **GoogleADK** - Gemini only
 - **OpenAIAgents** - OpenAI only
-- **AutoGen** - Works with Bedrock, Anthropic, OpenAI, Gemini
+
 
 ### Specific Context
 

package/dist/assets/cdk/package.json

@@ -23,8 +23,8 @@
     "typescript": "~5.9.3"
   },
   "dependencies": {
-    "@aws/agentcore-cdk": "^0.1.0-alpha.1",
-    "aws-cdk-lib": "2.243.0",
+    "@aws/agentcore-cdk": "0.1.0-alpha.18",
+    "aws-cdk-lib": "^2.248.0",
     "constructs": "^10.0.0"
   }
 }

package/dist/assets/python/a2a/langchain_langgraph/base/main.py

@@ -1,5 +1,6 @@
 from langchain_core.tools import tool
 from langgraph.prebuilt import create_react_agent
+from opentelemetry.instrumentation.langchain import LangchainInstrumentor
 from a2a.server.agent_execution import AgentExecutor, RequestContext
 from a2a.server.events import EventQueue
 from a2a.server.tasks import TaskUpdater
@@ -8,6 +9,8 @@ from a2a.utils import new_task
 from bedrock_agentcore.runtime import serve_a2a
 from model.load import load_model
 
+LangchainInstrumentor().instrument()
+
 
 @tool
 def add_numbers(a: int, b: int) -> int:

package/dist/assets/python/a2a/langchain_langgraph/base/pyproject.toml

@@ -15,6 +15,7 @@ dependencies = [
     {{/if}}{{#if (eq modelProvider "Gemini")}}"langchain-google-genai >= 2.0.0",
     {{/if}}{{#if (eq modelProvider "OpenAI")}}"langchain-openai >= 0.2.0",
     {{/if}}"aws-opentelemetry-distro",
+    "opentelemetry-instrumentation-langchain >= 0.59.0",
     "bedrock-agentcore[a2a] >= 1.0.3",
     "botocore[crt] >= 1.35.0",
     "langgraph >= 0.2.0",

package/dist/assets/python/http/langchain_langgraph/base/main.py

@@ -2,6 +2,7 @@ import os
 from langchain_core.messages import HumanMessage
 from langgraph.prebuilt import create_react_agent
 from langchain.tools import tool
+from opentelemetry.instrumentation.langchain import LangchainInstrumentor
 from bedrock_agentcore.runtime import BedrockAgentCoreApp
 from model.load import load_model
 {{#if hasGateway}}
@@ -10,6 +11,8 @@ from mcp_client.client import get_all_gateway_mcp_client
 from mcp_client.client import get_streamable_http_mcp_client
 {{/if}}
 
+LangchainInstrumentor().instrument()
+
 app = BedrockAgentCoreApp()
 log = app.logger
 

package/dist/assets/python/http/langchain_langgraph/base/pyproject.toml

@@ -10,6 +10,7 @@ readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
     "aws-opentelemetry-distro",
+    "opentelemetry-instrumentation-langchain >= 0.59.0",
     "langgraph >= 1.0.2",
     "mcp >= 1.19.0",
     "langchain-mcp-adapters >= 0.1.11",