Yagami AI Context Firewall
io.github.MatthewTracy/yagami
Govern model, retrieval, memory, and tool access for AI applications and agents.
Install surfaces
How Yagami AI Context Firewall runs, per the official MCP registry entry.
- pypi
uvx [email protected]
Governed execution
How KLA gates calls to Yagami AI Context Firewall once it is connected.
A published policy defines which Yagami AI Context Firewall actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agents and model providers you already run. See integrations.