AI Agent Governance Toolkit โ Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents.
docker pull microsoft/agent-governance-toolkit
docker run -d --name agent-governance-toolkit -p 8501:8501 --restart always microsoft/agent-governance-toolkit:latest
podman run -d --name agent-governance-toolkit -p 8501:8501 --restart always microsoft/agent-governance-toolkit:latest
skopeo inspect docker://docker.io/microsoft/agent-governance-toolkit:latest
oras pull microsoft/agent-governance-toolkit:latest
docker compose up -d
services:
dev:
build:
context: .
target: dev
command: ["sleep", "infinity"]
init: true
stdin_open: true
tty: true
# Match the host UID/GID so files created inside the bind-mounted
# workspace land with host ownership (not root). Override on the host
# with `HOST_UID=$(id -u) HOST_GID=$(id -g)` if your IDs differ.
user: "${HOST_UID:-1000}:${HOST_GID:-1000}"
working_dir: /workspace
volumes:
- .:/workspace
- typescript_node_modules:/workspace/agent-governance-typescript/node_modules
test:
build:
context: .
target: test
command: ["bash", "/workspace/scripts/docker/run-tests.sh"]
init: true
user: "${HOST_UID:-1000}:${HOST_GID:-1000}"
working_dir: /workspace
volumes:
- .:/workspace
- typescript_node_modules:/workspace/agent-governance-typescript/node_modules
dashboard:
profiles: ["dashboard"]
build:
context: .
target: dev
command:
- streamlit
- run
- agent-governance-python/agent-hypervisor/examples/dashboard/app.py
- --server.address=0.0.0.0
- --server.port=8501
init: true
# Match the host UID/GID so any files Streamlit writes back to the
# bind-mounted workspace are owned by the host user, not root.
user: "${HOST_UID:-1000}:${HOST_GID:-1000}"
ports:
- "8501:8501"
working_dir: /workspace
volumes:
- .:/workspace
- typescript_node_modules:/workspace/agent-governance-typescript/node_modules
volumes:
typescript_node_modules: