v1.0.0
AgentBarrier 1.0.0: keep a human in the loop when AI agents want to take action
AgentBarrier now lets you approve or block what your AI agents do, with dashboards, Slack, and secure record-keeping built in for production use.
Release Stories
AgentBarrier is a deterministic test harness for the control guarantees around AI-agent tool execution. It verifies that approval, rejection, cancellation, timeout, replay, delegation, ambiguous outcomes, audit receipts, and parallel execution controls prevent unintended side effects.
Release archive
3 stories, newest first
v1.0.0
AgentBarrier now lets you approve or block what your AI agents do, with dashboards, Slack, and secure record-keeping built in for production use.
v0.3.0
This release makes it easier to set up custom approval workflows, adds a payment tracking example, and fixes CrewAI compatibility on Python 3.10.
v0.2.1
A small fix ensures AgentBarrier accurately reports which version you're actually running.
Get notified when new releases are published. One email per release, and you can unsubscribe any time.