Action-aware permissions for coding agents. A deterministic safety guard that keeps you in the flow.
-
Updated
May 11, 2026 - Python
Action-aware permissions for coding agents. A deterministic safety guard that keeps you in the flow.
Three packages: @kernel.chat/agent-os (POSIX for AI agents — capabilities, namespaces, quotas, taint, audit, vault, outcomes), @kernel.chat/kbot (terminal AI agent, MCP-native, BYOK), @kernel.chat/kbot-finance (audit-grade AI for regulated industries). Provenance-engineering substrate.
On-chain spending policies for AI agent wallets. 14 testnets + 2 mainnets. 4 audits. ASP-1 spec.
Policy enforcement for AI agents, centralized and consistent. Define your rules once in umbod.toml, hook in your agents, and every one of them plays by the same rulebook.
Permission manifest schema, validator, and evaluator for AI agents.
MCP server for Agent Ready — scan any URL for AI agent readability against the Vercel Agent Readability Spec, llmstxt.org, and agent protocols (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance.
Add a description, image, and links to the agent-permissions topic page so that developers can more easily learn about it.
To associate your repository with the agent-permissions topic, visit your repo's landing page and select "manage topics."