# OpenAI Codex CLI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/openai-codex-cli
> Markdown URL: https://aitinkerers.org/technologies/openai-codex-cli.md
> Technology record last updated: 2026-03-07T07:22:46Z
> Generated: 2026-09-23T02:26:25Z

OpenAI Codex CLI is a terminal-native coding agent that reads, executes, and modifies local codebases using advanced reasoning models like o3 and gpt-5.4.

Codex CLI transforms the terminal into an interactive development environment by combining OpenAI reasoning models with local execution capabilities. Built in Rust for high performance, it allows developers to scaffold files, run tests, and perform multi-agent code reviews without leaving the command line. The tool prioritizes security through granular approval modes (Auto, Read-only, and Full Access) and a local-first architecture that keeps source code within the user's environment. With support for multimodal inputs like screenshots and integration with the Model Context Protocol (MCP), it serves as a lightweight, open-source alternative to IDE-based agents for terminal-centric workflows.

- Official technology site: https://github.com/openai/codex
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building a Terminal Orchestrator for AI Coding Agents in Rust](https://houston.aitinkerers.org/talks/rsvp_AD3Q9uzasnc)

**Context Foundry** is an autonomous build loop written in Rust. Give it a task list in markdown, and it works through every task using AI agents -- scouting the codebase, planning, building, and verifying with an independent reviewer in a fresh context. Passing tasks get committed. When the list runs out, a discovery agent scans for new work and keeps going. ``` SCOUT ──▶─ PLAN ──▶─ IMPLEMENT ──▶─ DOUBT ``` **The core insight:** every agent starts with a clean context window and receives only curated artifacts from the previous stage -- not a bloated conversation history full of noise. The scout writes a structured report. The planner reads that report and writes a plan. The builder reads that plan and writes code. The verifier reads the code with zero knowledge of why it was written that way. No shared context windows, no accumulated reasoning, no inherited blind spots. Each stage gets signal, not noise. This is how foundry prevents the compounding error problem where task 3 builds on task 2's mistakes. On top of this, **pattern learning** extracts reusable lessons after each task and injects them into future runs across all projects. ``` - [x] T1.1: Set up scaffolding [SPID] ● feat - [x] T1.2: Implement auth [SPID!] ✗ WIP - [ ] T1.3: Write tests [....] ``` You can also race two models against each other -- Claude and Codex each get their own worktree and run the full pipeline independently, so you compare finished solutions, not just raw outputs. Simple tasks skip the planner and reviewer and commit in about 30 seconds. There are three run modes: Auto keeps going forever, Sprint stops when the list is done, Review creates a PR after each task and waits for approval. Foundry has completed 141 tasks on its own codebase across 33 discovery rounds. Most of the features described here were built by the loop itself.

- Event context: AI Tinkerers Houston Meetup (March 10, 2026) — 2026-03-10 — Houston
- Public talk page: https://houston.aitinkerers.org/talks/rsvp_AD3Q9uzasnc

## Related Technologies

- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 216 public demos
- [Claude Code CLI](https://aitinkerers.org/technologies/claude-code-cli) ([Markdown](https://aitinkerers.org/technologies/claude-code-cli.md)) — 5 public demos
- [Opus 4](https://aitinkerers.org/technologies/opus-4) ([Markdown](https://aitinkerers.org/technologies/opus-4.md)) — 10 public demos
- [portable-pty](https://aitinkerers.org/technologies/portable-pty) ([Markdown](https://aitinkerers.org/technologies/portable-pty.md)) — 1 public demo
- [ratatui](https://aitinkerers.org/technologies/ratatui) ([Markdown](https://aitinkerers.org/technologies/ratatui.md)) — 1 public demo
- [Rust](https://aitinkerers.org/technologies/rust) ([Markdown](https://aitinkerers.org/technologies/rust.md)) — 56 public demos
- [serde](https://aitinkerers.org/technologies/serde) ([Markdown](https://aitinkerers.org/technologies/serde.md)) — 1 public demo
- [Tokio](https://aitinkerers.org/technologies/tokio) ([Markdown](https://aitinkerers.org/technologies/tokio.md)) — 3 public demos