Harness encyclopedia

The harnesses, running on a server.

TeamDay runs the agentic harnesses developers already trust — server-side, around the clock. Pick a harness per agent. Mix them on a single mission. New models from each vendor light up the moment they ship — no integration sprint.

Claude Code logo

Anthropic

Claude Code

The harness for long-horizon, verifiable engineering work.

Anthropic's official agentic coding harness. Runs the Claude family — Fable 5, Opus 4.8, Sonnet 4.6. Strong on multi-hour missions, tool use, and self-verification.

Models

Claude Fable 5Claude Opus 4.8Claude Sonnet 4.6

Read the encyclopedia entry

Codex logo

OpenAI

Codex

The harness for unified multimodal and computer-use missions.

OpenAI's agentic harness. Runs the GPT-5 family — including GPT-5.5 and GPT-5.5 Pro. First-class computer use, browser automation, and a unified text/image/audio/video architecture.

Models

GPT-5.5GPT-5.5 ProGPT-5.3 CodexGPT-5

Read the encyclopedia entry

Gemini CLI logo

Google

Gemini CLI

The harness for huge-context reasoning and Google-stack work.

Google's agentic harness. Runs the Gemini family — Gemini 3.1 Pro, Gemini 2.5 Pro. Industry-leading 2M context window and tight integration with Google Workspace, Drive, and BigQuery.

Models

Gemini 3.1 ProGemini 2.5 ProGemini 2.5 Flash

Read the encyclopedia entry

Grok Build logo

xAI

Grok Build

The harness for Grok-powered terminal work and fast model routing.

xAI's Grok Build CLI runs headless from TeamDay with streaming JSON events, session resume, and optional model selection through the xAI account or API key configured on the runner.

Models

Grok BuildGrok 4xAI account models

Read the encyclopedia entry

Pi logo

Earendil Works

Pi

The harness for provider-agnostic CLI work through third-party tokens.

Pi is a minimal terminal coding harness with JSON mode, durable session IDs, and provider selection. TeamDay runs it with your Pi auth file or provider API-token environment.

Models

Pi defaultProvider-selected modelsCustom model IDs

Read the encyclopedia entry

Side-by-side

Capability matrix

What each harness actually ships, verified against the upstream source. Updated April 2026.

CapabilityClaude CodeCodexGemini CLIopencodePiForge
Sub-agentsyesyes (spawn_agent)yesyesyesyes (Forge/Sage/Muse)
Skillsyesyesyesyes (SKILL.md)yesyes
MCP clientyesyes (+ MCP server)yesyesyesyes
Hooksrich lifecyclenotify onlyrichest lifecyclerich plugin hooksyesevent flag only
Slash / custom cmdsyesyesyes (TOML)yesyesyes (:prefix)
Permissions / sandboxfine-grainedOS-level (seatbelt/landlock)Policy Engineper-agent rulesetsgates + path protectworktree sandbox
Pluginsmarketplacemarketplaceextensionsplugin SDKTS extensions
Multi-modelAnthropic + Bedrock + Vertex + FoundryOpenAI + Bedrock + Ollama + customGemini only12+ providers15+ providers8+ providers
Sessions--resume, /branch, RemoteSQLite, ephemeralcheckpoints + git snap, /restoreLLM-summary compactiontree-structured (branchable)resume + :compact / :clone
SurfacesCLI/VS Code/JetBrains/Desktop/Web/iOSTUI/CLI/Web/Desktop/IDE/AppServerTUI/VS Code/GH ActionsTUI/web/desktop/IDETUI/JSON/RPC/SDKTUI/ZSH/CLI
Headless / SDKAgent SDK (TS+Py)codex exec + AppServer + SDKs-p, JSONL, @google/gemini-cli-sdkcreateOpencodeServer/Client (HTTP)4 modes incl. SDKCLI only
Licenseproprietary engineApache 2.0Apache 2.0MITOSSApache 2.0

Sourced from each upstream repo (Claude Code, openai/codex, google-gemini/gemini-cli, sst/opencode, badlogic/pi-mono, antinomyhq/forge).

How harnesses fit in TeamDay

Each agent on the roster has a harness, a set of MCP servers, and a mission. The harness handles reasoning, planning, and tool calls. The MCP servers expose your data, your platforms, and visual models like Seedance 2.0 and gpt-image-2. The mission tells the agent what success looks like.