Teamday
OpenAI logo

Harness · OpenAI

Codex.

OpenAI's agentic harness. The one we reach for when a mission crosses modalities — text, screenshots, audio, video — or needs to drive software that has no clean API.

Run Codex agents in TeamDay →Read the GPT-6 Astra launch noteAll harnesses

What it is

Codexis OpenAI's agentic harness — the runtime that wraps GPT models with planning loops, tool use, browser automation, and computer use. Originally pitched as a coding agent, it has grown into the general-purpose harness for any mission that requires "use this software until the task is finished."

Models it runs

  • GPT-6 Astra — rolled out September 3, 2026, the recommended default. 1.05M context, 128K output, text and image input, reasoning effort low → max. Read the launch note.
  • GPT-6 Sol — complex coding and agent work ($2 / $10 per million tokens).
  • GPT-6 Luna — focused, high-volume work ($0.10 / $0.50).
  • GPT-5.6 Sol — the value flagship at 40% of Astra's price ($4 / $20 per million tokens, promo through November 21, 2026).
  • GPT-5.6 Terra — balanced capability, cost, and latency ($2 / $12).
  • GPT-5.6 Luna — the efficient tier for fast, high-volume work ($0.20 / $1.20).

What makes it distinct

  • Unified multimodal. One call processes text, screenshots, audio, and video — no stitching together GPT + Whisper + Sora behind the agent.
  • Computer use. Operates software, fills forms, drives a browser end-to-end. Strongest of the three harnesses on this dimension.
  • Knowledge work. Researching online, analyzing data, creating documents and spreadsheets — moving across tools until the task is done.
  • Web search built in. Real-time fact-checking without a separate connector.

Capabilities at a glance

  • Sub-agents: yes — parent agents call spawn_agent, message child agents, and await completion.
  • Skills: yes — system skills and per-project skills with per-tool approval modes.
  • MCP servers: yes — both as client (config.toml, parallel tool calls toggle) and as server (codex mcp-server for other MCP clients to consume Codex tools).
  • Hooks: partial — only a notify hook fires on turn completion; no full lifecycle event system.
  • Slash commands: yes — /apps, /exec, /sandbox, /mcp, /debug, plus user-defined via skills and AGENTS.md.
  • Permissions / sandboxing: three modes (read-only, workspace-write, danger-full-access); OS-level sandboxing via seatbelt (macOS), landlock (Linux), AppContainer (Windows).
  • Plugins: yes — marketplace system with OpenAI-curated and bundled marketplaces; installable from remote sources.
  • Multi-model: OpenAI Responses API, Amazon Bedrock, Ollama, and any OpenAI-compatible endpoint via config.toml.
  • Sessions: persisted to disk via SQLite; codex exec --ephemeral for stateless runs; rollout-trace bundle for diagnostics.
  • Surfaces: Ratatui TUI, headless CLI, web app, desktop app, IDE extensions (VS Code/Cursor/Windsurf), and an HTTP App Server.
  • Headless / SDK: yes — codex exec, the App Server protocol, plus TypeScript and Python client SDKs.
  • License: Apache 2.0; full Rust source on github.com/openai/codex.

How TeamDay uses it

Selecting Codex as a Teamday agent's harness offers GPT-6 Astra, Sol, and Luna, plus GPT-5.6 Sol, Terra, and Luna. We verify new provider models before adding them to the picker.

  1. Open an agent → Settings → Harness → Codex.
  2. Pick the model. GPT-6 Astra is the recommended default; GPT-6 Sol or Luna offer lower-cost options.
  3. Attach MCP servers — including the media MCP for visual generation.
  4. Run a mission. Codex agents play well alongside Claude Code agents on the same workspace.

When to pick Codex

  • Mixed-modality missions — process a customer call, transcribe, extract action items, draft follow-up email — in one mission.
  • Computer-use heavy work — drive software, fill forms, navigate dashboards.
  • Knowledge work that ranges across tools (research → spreadsheet → document → email).
  • Anything where you want the agent to watch a screen and react.

How it's benchmarked

Codex is evaluated on Terminal-Bench(tbench.ai) — the standard suite for measuring how well a model-plus-harness combination completes real terminal tasks end-to-end. The leaderboard tracks how each new GPT-5 release moves Codex's score on Terminal-Bench Pro and Verified.

When to pick something else

  • Claude Code — for long-horizon coding and missions requiring self-verification.
  • Gemini CLI — when you need 2M context or Google-stack integration.

Run Codex agents in TeamDay.

Pick Codex in the harness picker to unlock the whole GPT-5 family, then connect an OpenAI key or any OpenAI-compatible provider — usage is billed by your own provider at direct rates. And because you bring your own provider, Teamday is free for your first 14 days — then Starter is $99/mo, backed by a 14-day money-back guarantee.

Get started