Open-source control layer for AI agents that checks tool calls against rules, blocks or routes risky actions for human approval, and records tamper-evident audit trails. Supports Claude Code and MCP applications.
Prices and medians update for the tier you select.
Ranked by how closely each one matches Squidbrake's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Market = the products most similar to this one by capability; prices are median / quartiles over its priced members, separated by provider type and buyer tier.