AI NPCs that can control their actions along with dialogue. For instance, if I ask an NPC to tell me its favorite magic spell, it not only tells me the spell but also performs it!

Cycles budget and action guard for OpenClaw agents

Open protocol for runtime budget and action authority over AI agents

Documentation for Cycles — AI agent governance, runtime budget, action authority, MCP integration

Self-hosted runtime authority server for AI agents — budgets, risk, actions, tenant isolation

Actra - control what runs before it runs, controls what actions are allowed before they execute. Evaluate policies across APIs, workflows and AI agents in real time.

Runaway AI agent spend prevention — demo using Cycles ($6 in 30s → hard stop at $1)

Admin API for Cycles — tenants, budgets, API keys, webhooks, audit, and governance

Spring Boot starter for Cycles — runtime budget authority for AI agents

Rust client for Cycles — runtime budget authority for AI agents

Signed webhook/event delivery for Cycles — retries, HMAC, replay, audit, governance events

AI agent governance dashboard for Cycles — budgets, action authority, tenants, webhooks, reservations, audit

AI agent action authority — demo of blocking unapproved tool calls with Cycles

Python SDK for Cycles — reserve, commit, release budget and risk for AI agents

Budget governance for OpenAI Agents SDK — enforce cost limits before tools execute

Spring AI starter for Cycles — runtime budget and action authority for Spring AI agents

LangChain agent middleware for Cycles — pre-tool-call authorization and per-tenant budget enforcement for Python agents using create_agent

TypeScript SDK for Cycles — runtime budget and action authority for Node.js AI agents