AI agent governance for teams. Runtime firewalls tell you what happened; Conduct Guard controls what can happen — signed policy, verified chain, fail-closed by default. Ships with Router (LLM proxy), 20+ compliance packs, canvas UI, and a playbook engine.
Hook Claude Code
Runs before the agent uses a tool for Bash, Read, Grep and Agent tool calls, executing validate-playbooks.py, booster-gate.py, booster-grep-nudge.py and booster-agent-inject.py via sh with --show-toplevel (4 commands). From sseshachala/conductai.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing booster-route.py via sh with --show-toplevel. From sseshachala/conductai.
Hook Claude Code
Runs before the context is compacted, executing guard-precompact.py via python3. From sseshachala/conductai.
Hook Claude Code
Runs when a session starts, executing guard-session-start.py and booster-session-start.py via sh with --show-toplevel (2 commands). From sseshachala/conductai.
Hook Claude Code
Runs when the agent finishes a response, executing booster-stop.py via sh with --show-toplevel (2 commands). From sseshachala/conductai.