AI Briefing#codex-cli
The latest AI and developer news about #codex-cli, with the original source and a short summary.
The latest AI and developer news about #codex-cli, with the original source and a short summary.
The update introduced a persistent background daemon that copies the platform package and runs an hourly updater, causing conflicts with package manager installations.
The MIT-licensed tool allows users to monitor and respond to permission prompts from Claude Code, Codex CLI, and OpenCode across multiple folders via desktop or phone.
The HarnessTax study reveals that even with the same AI model, costs can differ by up to 2x depending on the harness choice, with the simple open-source harness Pi demonstrating competitive performance.
hip-agent, a prompt-embedded harness, achieved performance similar to Codex CLI and demonstrated its potential as a model evaluation tool.
An open-source proxy has been released that lets coding agents like Codex and Claude Code use a variety of LLMs.
A problem has been reported where Subagent logs abnormally accumulate in resumed long-running Codex CLI sessions, exhausting disk space.
MultiAgentV2 in Codex CLI encrypts prompts, causing a regression that degrades audit trail functionality.
It's an MCP-based plugin that delegates heavy code generation tasks to a local LLM to reduce token consumption in Claude Code and Codex CLI.
Introduced an Agent loop that automatically repairs outdated API/SDK examples using Codex.
Datasette 1.0a29 was released, including the addition of the `_r` utility and a segfault bug fix.
Codex CLI has introduced a `/goal` feature to prevent long-running AI agents from drifting off task.
The analysis found that the same model's performance varies significantly depending on the execution harness.
Codex CLI 0.128.0 adds `/goal`, a goal-based automatic iteration execution feature.
Codex CLI 0.128.0 adds /goal, which repeats execution until the goal is achieved.
The pipeline structures of 6 Codex CLI workflows were compared in a single table.
multi-codex separates Codex CLI into per-account sandboxed profiles.
Codex CLI hooks has moved to stable, and a PermissionRequest hook has been added.
llm-openai-via-codex 0.1a0, which calls OpenAI models using an existing Codex subscription, has been released.
Gemma 4 was connected to the local Codex CLI to verify its tool-calling performance and stability.
The Vercel plugin now supports OpenAI Codex and Codex CLI.