oldeucryptoboi/Carnival9
Deterministic agent runtime with explicit plans, typed tools, permissions, and replay. Implements Google DeepMind's Intelligent AI Delegation framework. Named after ELP's Karn Evil 9.
This project provides a robust system for automating complex, multi-step tasks using AI agents, ensuring accountability and auditability. It takes a natural-language description of a task and breaks it down into an explicit, structured plan, then executes it using a set of defined tools. Anyone needing to automate intricate workflows with verifiable, controlled AI execution, like an operations engineer managing system changes or a financial analyst performing regulated data processing, would find this useful.
Use this if you need to reliably automate complex, multi-step tasks with AI agents, requiring transparency, detailed audit trails, and built-in safety mechanisms.
Not ideal if your tasks are simple, single-step operations or if you prefer less structured, more exploratory AI prompting without strict governance.
Stars
12
Forks
1
Language
TypeScript
License
MIT
Category
Last pushed
Mar 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/oldeucryptoboi/Carnival9"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
agno-agi/agno
Build, run, manage agentic software at scale.
adaline/gateway
The only fully local production-grade Super SDK that provides a simple, unified, and powerful...
agentscope-ai/agentscope
Build and run agents you can see, understand and trust.
iflytek/astron-agent
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
darrenhinde/OpenAgentsControl
AI agent framework for plan-first development workflows with approval-based execution....