Omegacode – an agent agnostic version of Claude Workflows
Cross-agent orchestration with adversarial review patterns — enables workflows impossible with single agents.
Run Claude Code workflow scripts, unmodified, on the OpenAI Codex CLI — fable plans, codex executes, fable verifies. Parallel agent fleets, builder–verifier loops, token budgets, full-screen TUI.
I want Fable to focus on high-value tasks such as planning or verification, and not burn tokens on mundane implementation work. So I built ultracodex, an engine that spawns codex agents to complete the same ultracode workflows and hand off seamlessly to and from Claude. It runs the same workflow scripts that Claude writes. I designed this tool for anyone owning both Claude and Codex subscriptions or anyone who enjoys Fable and wants to make the quota last.
This tool is in early days but I am very excited about the potential. I think it’s also a great “loop engineering” starter pack for us because 1) Claude is great at writing loops and 2) ultracodex runs the loops with Codex agents - given their generous limits, you don’t have to worry about usage much. So “loop engineering” is no longer a mysterious thing but a tool you can throw at any task. I have some examples of “loops” in my repo as well.
Project is completely open-source. Apache-2.0, npm i -g ultracodex, demo video in the README.
Please check it out!
Cross-agent orchestration with adversarial review patterns — enables workflows impossible with single agents.
Separates agent research from deterministic valuation math—no hidden assumptions.
Multi-agent orchestration for two CLIs, but early-stage and AI-generated codebase raises maintenance concerns.
Nested agent summarization cuts token costs ~45% for command-heavy workflows.
TypeScript FSMs enforce agent steps where prompts fail, but locks you into Codex CLI.
Multi-agent tmux orchestrator with receipt ledger, but still early and narrow audience.