Teamday
opencode logo

Harness · Open source

live

opencode.

The open-source, model-agnostic agentic coding harness. Runs any LLM you point it at — Claude, GPT, Gemini, local Llama. It's live in TeamDay: pick OpenCode in the chat model picker to run Moonshot AI Kimi K3.

Run opencode agents in TeamDay →Visit opencode.aiAll harnesses

What it is

opencode is an open-source agentic coding harness — a terminal-native runtime that wraps any LLM with a planning loop, tool calls, file I/O, and shell execution. The defining trait is model-agnostic: opencode doesn't ship with a specific provider lock-in. You point it at whichever frontier model fits your budget and your stack.

That makes it interesting for teams that want a fully open stack, prefer to self-host, or run local/open-weight models like Llama 4, DeepSeek V4, or Qwen.

Why we support it

  • Open-source. The harness itself is auditable, forkable, and not gated by a vendor.
  • Model-agnostic. Same harness behavior across Claude, GPT, Gemini, and open-weight models — useful for fair benchmarking.
  • Terminal-native. Designed for the same shell + file + build loop that Claude Code and Codex evaluate on.

Capabilities at a glance

  • Sub-agents: yes — build (primary), plan (read-only), general subagent; mode field per agent.
  • Skills: yes — SKILL.md with frontmatter, searched in workspace, ~/.opencode, and project dirs.
  • MCP servers: yes — stdio / HTTP / SSE; prompts and resources surface as commands.
  • Hooks: yes — extensive plugin hook system: chat.message, chat.params, tool.execute.before/after, permission.ask, shell.env, session compaction, experimental transforms.
  • Slash commands: yes — built-ins (/init, /review) plus user-defined and skill-derived commands.
  • Permissions / sandboxing: per-agent rulesets; build permissive, plan read-only; file-pattern denials (e.g. .env).
  • Plugins: yes — first-class @opencode-ai/plugin SDK with workspace adaptors, auth (OAuth/API), provider hooks, tool registration, OpenTUI components.
  • Multi-model: 12+ providers — Anthropic, OpenAI, Google/Vertex, GitHub Copilot, Bedrock, Azure, OpenRouter, Mistral, GitLab, OpenCode Zen; custom via plugin ProviderHook.
  • Sessions: partial — LLM-summary compaction (goal/progress/blockers/next steps); SQLite persistence; no explicit checkpoint API.
  • Surfaces: TUI (OpenTUI + Solid), web (Vite + SolidJS), Electron desktop, IDE extensions; opencode serve for headless.
  • Headless / SDK: yes — createOpencodeServer / createOpencodeClient in @opencode-ai/sdk; HTTP API; usable from Node or browser.
  • License: MIT; github.com/sst/opencode.

Status in TeamDay

Live. opencode is a selectable harness in the TeamDay chat model picker, running Moonshot AI's Kimi K3 (1M context) and Kimi K2.7 Coding through the Kimi for Coding endpoint. Connect a Kimi API key under Settings → Runner auth and any agent can reply through opencode, alongside Claude Code, Codex, and Gemini CLI.

How it fits

Selecting opencode as an agent's harness unlocks the models the harness supports — starting with Moonshot AI's Kimi family, with more open-weight options to follow. The MCP server attachment story stays identical: the same Teamday MCP servers that power media generation and workspace tools work behind opencode agents.

Learn more

Run opencode agents in TeamDay.

Pick opencode in the model picker and connect a Kimi API key — usage is billed by your own provider at direct rates. Starter is $99/mo with a 14-day money-back guarantee.

Get started