Agent Kernel

https://github.com/yaalalabs/agent-kernel
Admin
Agent Kernel is an enterprise platform layer to run, orchestrate, and deploy production AI agents...
Tokens:1,185,198
Snippets:10,966
Trust Score:8.2
License:Apache-2.0
Update:1 month ago
Show doc for...
Tokens:
Raw
### Common Setup Pattern

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/examples/overview.md

Standard workflow for installing dependencies and running examples locally.

```bash
# Install dependencies
./build.sh

# For local development
./build.sh local

# Run the example
python demo.py  # or server.py for API examples
```

--------------------------------

### Install Dependencies and Run Example

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/examples/multi-agent.md

Commands to install the required package, set the OpenAI API key, and execute the multi-agent script.

```bash
pip install agentkernel[crewai]
export OPENAI_API_KEY=sk-...
python multi_agent.py
```

--------------------------------

### Setup Development Environment

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/ak-py/README.md

Clone the repository and install dependencies using uv or pip.

```bash
git clone https://github.com/yaalalabs/agent-kernel.git
cd agent-kernel/ak-py
uv sync  # or: pip install -e ".[dev]"
```

--------------------------------

### Run development setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/DEVELOPER_GUIDE.md

Install prerequisites and sync the virtual environment using the Makefile or script.

```bash
make dev-setup
```

```bash
./scripts/dev-setup.sh
```

--------------------------------

### Run API Hooks Example

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/integrations/hooks.md

Commands to build the environment, start the API server, run tests, or execute the direct usage example for the API hooks demonstration.

```bash
cd examples/api/hooks

# Build environment
./build.sh

# Run the API server
source .venv/bin/activate
python app.py

# Run tests (in another terminal)
source .venv/bin/activate
pytest app_test.py -v

# Or run direct example
python example_usage.py
```

--------------------------------

### Build and Run Commands

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/examples/api/teams/README.md

Commands to install dependencies and start the local server.

```bash
./build.sh
```

```bash
uv run server.py
```

--------------------------------

### Prerequisites Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/ak-deployment/ak-gcp/common/run.md

Install necessary tools, authenticate with Google Cloud, set the project ID, and enable required GCP APIs.

```bash
# Install tools
brew install terraform
brew install google-cloud-sdk

# Login
gcloud auth login
gcloud auth application-default login

# Set project
gcloud config set project YOUR_PROJECT_ID

# Enable APIs
gcloud services enable compute.googleapis.com
gcloud services enable artifactregistry.googleapis.com
gcloud services enable redis.googleapis.com
gcloud services enable firestore.googleapis.com
gcloud services enable vpcaccess.googleapis.com
```

--------------------------------

### Install all features

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/versioned_docs/version-0.2.0/installation.md

Installs all available framework and utility extras.

```bash
pip install agentkernel[openai,crewai,langgraph,adk,api,aws,cli]
```

--------------------------------

### Development Installation

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/installation.md

Clone the repository and install in development mode.

```bash
# Clone the repository
git clone https://github.com/yaalalabs/agent-kernel.git
cd agent-kernel/ak-py

# Install in development mode
./build.sh

# Go to any example and run
./build.sh local
```

--------------------------------

### Interact with Deployed Agents via API Gateway

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/examples/gcp-containerized/openai-auth/README.md

Use curl to send requests to the API Gateway endpoint with JWT authentication. This includes examples for sending messages to agents and querying custom endpoints.

```bash
# Get the API URL from Terraform outputs
API_URL=$(terraform output -raw agent_invoke_url)

# Get a JWT token (example using Google OAuth)
# In production, your application should obtain this through OAuth flow
JWT_TOKEN="your-jwt-token-here"

# Send a math question to the triage agent with JWT authentication
curl -X POST "${API_URL}" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${JWT_TOKEN}" \
  -d '{
    "message": "What is the square root of 144?",
    "session_id": "user123"
  }'

# Send a history question
curl -X POST "${API_URL}" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${JWT_TOKEN}" \
  -d '{
    "message": "Tell me about the American Civil War",
    "session_id": "user123"
  }'

# Use the custom version endpoint
curl -X GET "$(terraform output -raw gateway_url)/api/v1/version" \
  -H "Authorization: Bearer ${JWT_TOKEN}"

# Use the custom app_info endpoint
curl -X POST "$(terraform output -raw gateway_url)/api/v1/app_info" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${JWT_TOKEN}"
```

--------------------------------

### Langfuse Tracing Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/core-concepts/configuration.md

Configures Langfuse tracing and installs the required extra.

```bash
# Enable Langfuse tracing
export AK_TRACE__ENABLED=true
export AK_TRACE__TYPE=langfuse

# Langfuse credentials
export LANGFUSE_PUBLIC_KEY=pk-lf-...
export LANGFUSE_SECRET_KEY=sk-lf-...
export LANGFUSE_HOST=https://cloud.langfuse.com
```

```bash
pip install agentkernel[langfuse]
```

--------------------------------

### Langfuse Observability Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/versioned_docs/version-0.2.10/core-concepts/configuration.md

Configures Langfuse tracing and installs the required Python package.

```bash
# Enable Langfuse tracing
export AK_TRACE__ENABLED=true
export AK_TRACE__TYPE=langfuse

# Langfuse credentials
export LANGFUSE_PUBLIC_KEY=pk-lf-...
export LANGFUSE_SECRET_KEY=sk-lf-...
export LANGFUSE_HOST=https://cloud.langfuse.com
```

```bash
pip install agentkernel[langfuse]
```

--------------------------------

### Install All Features

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/installation.md

Installs everything including all frameworks and cloud providers.

```bash
pip install agentkernel[openai,crewai,langgraph,adk,smolagents,pydanticai,api,aws,azure,gcp,cli]
```

--------------------------------

### OpenLLMetry Tracing Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/core-concepts/configuration.md

Configures OpenLLMetry (Traceloop) tracing and installs the required extra.

```bash
# Enable OpenLLMetry tracing
export AK_TRACE__ENABLED=true
export AK_TRACE__TYPE=openllmetry

# Traceloop credentials
export TRACELOOP_API_KEY=your-api-key
# Optional: for self-hosted
export TRACELOOP_BASE_URL=https://api.traceloop.com
```

```bash
pip install agentkernel[openllmetry]
```

--------------------------------

### Run the Demo

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/examples/sandbox/daytona/README.md

Set the required OpenAI and Daytona API keys, then execute the demo script.

```bash
export OPENAI_API_KEY=sk-...
export DAYTONA_API_KEY=dtn_...
uv run demo.py
```

--------------------------------

### Pydantic Logfire Tracing Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/core-concepts/configuration.md

Configures Pydantic Logfire tracing and installs the required extra.

```bash
# Enable Logfire tracing
export AK_TRACE__ENABLED=true
export AK_TRACE__TYPE=logfire

# Logfire credentials (optional — without a token, Logfire runs locally and does not ship traces)
export LOGFIRE_TOKEN=your-write-token
```

```bash
pip install agentkernel[logfire]
```

--------------------------------

### Setup Backend Infrastructure with Defaults

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/scripts/deploy/README.md

Run the backend setup script using default values defined in state-config.yaml.

```bash
./scripts/deploy/setup_backend.sh gcp
```

--------------------------------

### Run the application

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/examples/api/multimodal/thread-openai/README.md

Set the OpenAI API key and start the application using uv.

```bash
export OPENAI_API_KEY="your-openai-api-key"
uv run python app.py
```

--------------------------------

### Setup Virtual Environment with Conda

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/installation.md

Create and activate a conda environment, then install Agent Kernel.

```bash
# Create conda environment
conda create -n .venv python=3.12

# Activate
conda activate .venv

# Install Agent Kernel
pip install agentkernel[openai,api]
```

--------------------------------

### Run the local CLI

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/use-cases/waste-sorting-assistant/README.md

Set the OpenAI API key and start the local demonstration agent.

```bash
export OPENAI_API_KEY="sk-..."
uv run python demo.py
```

--------------------------------

### GET /api/v1/threads Response

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/versioned_docs/version-0.8.0/api/rest-api.md

Example response for listing conversation threads, which is available when thread support is enabled.

```json
{
  "threads": [{"session_id": "user-123", "name": "Trip planning", "user_id": "anne", "...": "..."}],
  "next_cursor": null
}
```

--------------------------------

### Deploy Authorizer Lambda Script

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/deployment/aws-serverless.md

Example script for installing dependencies for the authorizer Lambda function into a distribution directory.

```bash
# Install authorizer dependencies
uv pip install --force-reinstall --no-deps agentkernel[api,aws] --target=auth_dist
```

--------------------------------

### Run Session Context Example

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/integrations/hooks.md

Commands to build the environment, run the session context demo, and execute tests.

```bash
cd examples/cli/session-context

# Build environment
./build.sh

# Run the demo
python demo.py

# Run tests (in another terminal)
uv run pytest -s
```

--------------------------------

### Deploy Main Lambda Script

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/deployment/aws-serverless.md

Example script for installing dependencies for the main Lambda function into a distribution directory.

```bash
# Install main Lambda dependencies
uv pip install -r requirements.txt --target=dist/data
uv pip install --force-reinstall --target=dist/data agentkernel[openai,redis]
```

--------------------------------

### Run the server

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/examples/api/instagram/README.md

Starts the server on http://localhost:8000.

```bash
uv run server.py
```

--------------------------------

### Daytona Sandbox Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/versioned_docs/version-0.8.0/advanced/sandbox.md

Install the Daytona dependency, set your API key, and configure the sandbox type to daytona.

```bash
pip install "agentkernel[daytona]"
export DAYTONA_API_KEY=dtn_...
```

```yaml
sandbox:
  enabled: true
  type: daytona
  daytona:
    image: python:3.12-slim         # container image for the sandbox...
    # snapshot: my-warm-snapshot    # ...OR a named Daytona snapshot (mutually exclusive)
    env_vars:                       # environment variables set inside the sandbox
      APP_ENV: demo
    # target: us                    # Daytona target/region; omitted = SDK default
    # api_key_env: DAYTONA_API_KEY  # env variable holding the API key
  broker:
    flavor: thread
```

--------------------------------

### E2B Sandbox Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/versioned_docs/version-0.8.0/advanced/sandbox.md

Install the E2B dependency, set your API key, and configure the sandbox type to e2b.

```bash
pip install "agentkernel[e2b]"
export E2B_API_KEY=e2b_...
```

```yaml
sandbox:
  enabled: true
  type: e2b
  e2b:
    template: base              # E2B sandbox template
    # api_key_env: E2B_API_KEY  # env variable holding the API key
  broker:
    flavor: thread
```

--------------------------------

### Manual development setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/DEVELOPER_GUIDE.md

Manually build the environment from the ak-py directory.

```bash
cd ak-py
./build.sh
```

--------------------------------

### Docker Sandbox Setup

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/versioned_docs/version-0.8.0/advanced/sandbox.md

Install the Docker sandbox dependency and configure the sandbox type to docker in your YAML file.

```bash
pip install "agentkernel[sandbox-docker]"
```

```yaml
sandbox:
  enabled: true
  type: docker
  docker:
    image: python:3.12-slim     # any image with python
  broker:
    flavor: thread
```

--------------------------------

### Install dependencies and set API key

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/examples/memory/valkey/README.md

Prepares the environment by installing dependencies and setting the required OpenAI API key.

```bash
./build.sh
export OPENAI_API_KEY=<OPENAI_API_KEY>
```

--------------------------------

### Setup Virtual Environment with venv

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/docs/installation.md

Create and activate a virtual environment using venv, then install Agent Kernel.

```bash
# Create virtual environment
python -m venv .venv

# Activate (Linux/macOS)
source .venv/bin/activate

# Activate (Windows)
.venv\Scripts\activate

# Install Agent Kernel
pip install agentkernel[openai,api]
```

--------------------------------

### Full Test Session Example

Source: https://github.com/yaalalabs/agent-kernel/blob/develop/docs/versioned_docs/version-0.2.0/testing/cli-testing.md

A complete example demonstrating how to initialize a test, perform multiple interactions, and clean up resources.

```python
import asyncio
from agentkernel.test import Test

async def test_cricket_knowledge():
    test = Test("demo.py", match_threshold=60)
    
    try:
        await test.start()
        
        # Test basic question
        await test.send("Who won the 1996 cricket world cup?")
        await test.expect("Sri Lanka won the 1996 cricket world cup.")
        
        # Test follow-up question
        await test.send("Which country hosted the tournament?")
        await test.expect("Co-hosted by India, Pakistan and Sri Lanka.")
        
        print("All tests passed!")
        
    finally:
        await test.stop()

if __name__ == "__main__":
    asyncio.run(test_cricket_knowledge())
```
Tokens:
Raw