The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Codex Yolo
Run parallel OpenAI Codex CLI agents in tmux with automatic permission approval. Auto-approves command execution, file edit, network access, and MCP tool prompts while…
Install
git clone https://github.com/codex-yolo/codex-yoloInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →[!CAUTION] DO NOT USE THIS TOOL ON CORPORATE HARDWARE OR CONNECTED TO A CORPORATE NETWORK.
This tool auto-approves all Codex CLI permission prompts without human review, including destructive commands. For maximum isolation, run it on a dedicated bare-metal server with no personal data, no saved credentials, and no access to sensitive networks. You accept full responsibility for any consequences.
codex-yolo
Run parallel OpenAI Codex CLI agents in tmux with automatic permission approval. Optionally isolate each agent in its own git worktree with real-time merge conflict detection and automated conflict resolution.
Codex CLI can prompt before commands leave the workspace sandbox or require other elevated permissions. Standard agent windows start in Ask for approval mode (workspace-write, on-request, user review); the tmux approver daemon handles those prompts at the terminal level. Command network access is enabled inside that sandbox by default so tools such as git, gh, package managers, and curl can reach public websites.
On launch, codex-yolo also reconciles these user-level defaults in
~/.codex/config.toml (existing unrelated settings are preserved):
approval_policy = "on-request"
sandbox_mode = "workspace-write"
[features]
shell_tool = true
code_mode_host = true
unified_exec is intentionally left unset so the Codex default or an
organization's managed requirement can select the execution backend.
Table of contents
- Installation
- Quick start
- Worktree mode
- Navigation
- Control commands
- Options
- How it works
- File structure
- Prerequisites
- Testing
- Key features
- Development history
Installation
On Linux and WSL2, the installer installs the distribution bubblewrap package
when bwrap is missing from PATH, as recommended by Codex's official sandbox
prerequisites. The bundled helper remains Codex's fallback, but it requires
unprivileged user namespaces. If a namespace or AppArmor warning remains, follow
the official troubleshooting steps,
including the Ubuntu 24.04 AppArmor profile setup when applicable.
One-liner (macOS, Linux, WSL, Termux):
command -v curl >/dev/null || { s=; [ "$(id -u)" != 0 ] && s=sudo; command -v apt-get >/dev/null && { $s apt-get update && $s apt-get install -y curl; } || command -v dnf >/dev/null && $s dnf install -y curl || command -v yum >/dev/null && $s yum install -y curl || command -v apk >/dev/null && $s apk add curl || command -v pacman >/dev/null && $s pacman -S --noconfirm curl || command -v pkg >/dev/null && pkg install -y curl || command -v brew >/dev/null && brew install curl; }; curl -fsSL https://raw.githubusercontent.com/codex-yolo/codex-yolo/refs/heads/main/install.sh | bash && export PATH="${CODEX_YOLO_BIN_DIR:-$HOME/.local/bin}:${CODEX_YOLO_HOME:-$HOME/.codex-yolo}/bin:$PATH"
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.