{"domain":"kiff.dev","status":"valid","tier":"listed","authority":45,"verified":false,"title":"KIFF","summary":"KIFF gives each AI agent a Card: which actions it may take, how much per action and in total over a window, and what happens to a call outside those limits. KIFF decides every proposed consequential action before it runs, against the business's own state and the agent's Card. A call outside the Card waits for the owner or is refused. The owner changes or revokes the Card without changing the agent, and every decision has a signed, tamper-evident receipt.","country":"IE","country_source":"ip","publisher_country":null,"publisher_country_source":null,"hosting_country":"IE","llms_txt":"https://kiff.dev/llms.txt","llms_full_txt":"https://kiff.dev/llms-full.txt","last_checked":"2026-10-27T09:55:21.378Z","agent_terms":null,"categories":["ai-ml","ai-agents-mcp","cybersecurity","apis-sdks"],"capabilities":[],"inferred_tags":["ai agent authority","spending limits","agent governance","decision api","signed receipts","human approval"],"audience":"developers","agent_uses":["read_docs","call_api"],"language":"en","platform_generated":false,"agent_summary":"KIFF gives AI agents a business-controlled Card of limits; its decision API (POST /v1/proposals/decide) allows, escalates or blocks consequential actions with s","llms_txt_cached":"https://agentwebmap.com/v1/domain/kiff.dev/llms.txt","agentic":"interface","section_keys":["core","key-facts","kiff-cloud-hosted-runtime-and-studio-the-domain-s-rendered-view","kiff-guard-the-on-ramp-for-existing-agents","legal-and-trust","optional","product-notes","the-framework-open-source-mit-go","tutorials"],"section_partial":false,"section_indexed_at":"2026-10-27T09:55:26.163Z"}