codex-chief

All projects

Agents / Skills

Budget-disciplined multi-agent setup for OpenAI Codex.

byEmre Canik

Open source

codex-chief media is blocked

Allow external media to connect to the provider and play this content.

Description

An orchestration framework for OpenAI Codex that optimizes API costs by routing tasks to specific flavors of the GPT-5.6 model family. It employs a cheap orchestrator (Terra) with specialized subagents for exploration (Luna), implementation (Luna XHigh), and architectural judgment (Sol) to manage context recall and token burn.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: A sophisticated example of multi-agent orchestration that addresses real-world LLM constraints like context recall…
Attributed to: Emre Canik@emrecengdev
Built with: GPT-5.6 Sol GPT-5.6 Terra GPT-5.6 Luna K2.7 Code North Mini Code GPT Image 2 GPT-5 Codex GPT-5 Codex
Links: View tweet
Tags: #codex #multi-agent #cost-optimization #developer-tools

Discovered: X
First posted: X · Jul 12, 2026
Listed: Added 48d ago
Build: Strong
Models: Strong

codex-chief

Description

Timeline

codex-chief

Description

Timeline