AI Security Toolset - A toolset repository for AI agents
Overview
This toolset is intended for AI agents builders, to simplify your work, and reduce the level of boilerplate code you need to write.
Features
Secured environment variables provisioning
This toolset can populate API keys and secrets as environment variables. The secrets are stored in your secret management of choice and are provisioned at runtime into your process memory.
The secrets can be populated and depopulated, for a specific context: Agent, Tool, HTTP call.
Currently supported secret providers:
- AWS Secret Manager
- CyberArk Conjur
- Local
.envfile (for development purposes)
However, this functionality is extensible, by implementing a SecretsProvider interface.
Example
For full, runnable examples, please see the examples directory.
...
from secure_ai_toolset.secrets.aws_secrets_manager_provider import AWSSecretsProvider
from secure_ai_toolset.secrets.environment_manager import EnvironmentVariablesManager
# Populate the environment variables from AWS Secrets Manager
@EnvironmentVariablesManager.set_env_vars(AWSSecretsProvider())
async def main() -> None:
runtime = SingleThreadedAgentRuntime()
tools: List[Tool] = [
FunctionTool(get_stock_price, description='Get the stock price.')
]
await ToolAgent.register(runtime, 'tool_executor_agent',
lambda: ToolAgent('tool executor agent', tools))
await ToolUseAgent.register(
runtime,
'tool_use_agent',
lambda: ToolUseAgent(
AzureOpenAIChatCompletionClient(
model='gpt-4o',
azure_endpoint=os.getenv('AZURE_OPENAI_ENDPOINT'),
azure_deployment='gpt-4o',
api_version='2024-02-01',
api_key=os.getenv('AZURE_OPENAI_KEY')),
[tool.schema for tool in tools], 'tool_executor_agent'),
)
...
Getting Started
pip
pip3 install secure-ai-toolset
poetry
poetry add secure-ai-toolset
Note: Please ensure you are using Poetry version >=2.1.1.
Contribution
Please make sure to read the CONTRIBUTING.md file if you want to contribute to this project.
Contact
Feel free to contact us via github issues. If there are any feature requests or issues in the project you may contact me through linkedin: Gil Adda
Metadata
Release files for secure-ai-toolset 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| secure_ai_toolset-0.1.1.tar.gz | 14.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| secure_ai_toolset-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 34.5 kB
Release files / secure_ai_toolset-0.1.1.tar.gz
| Download URL | secure_ai_toolset-0.1.1.tar.gz |
|---|---|
| Size | 14.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
531837cf85b5676ee3623c37de6120145c4c9908aecc8dc093d66add3d9b761a
|
|
BLAKE2b-256 checksum How to use checksums |
42bb12db3bb745427a678d460d48593a0a7839a685797edd3aa13741aa11f028
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|
Release files / secure_ai_toolset-0.1.1-py3-none-any.whl
| Download URL | secure_ai_toolset-0.1.1-py3-none-any.whl |
|---|---|
| Size | 20.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
352ede7d9cdb042b861e19cc6ea408b4851d643f7669f2590ad4382ca00f194c
|
|
BLAKE2b-256 checksum How to use checksums |
f39abd86a516530ca4cf185fc2706f937c553f7d6c48037589e5f0f233243334
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|