# OpenCode (`agentify/opencode`) Actor

Instant access to OpenCode - Open-source AI coding assistant running on Apify.

- **URL**: https://apify.com/agentify/opencode.md
- **Developed by:** [agentify](https://apify.com/agentify) (Apify)
- **Categories:** AI, Agents, Automation
- **Features:** Limited permissions
- **Stats:** 141 total users, 5 monthly users, 21.4% runs succeeded, 1 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## OpenCode

Run [OpenCode](https://opencode.ai) on Apify infrastructure.

### 🔥 What is OpenCode?

OpenCode is an open-source AI coding agent with:

- Open-source and free to use
- Support for multiple AI models (Claude, GPT, Gemini, local models)
- Free built-in models available

### ⚙️ How It Works

This Actor [metamorphs](https://docs.apify.com/platform/actors/development/programming-interface/metamorph) into the [AI Sandbox](https://apify.com/apify/ai-code-sandbox) and automatically launches OpenCode in the terminal.

### 🚀 Quick Start

1. Click **Start** on this Actor
2. OpenCode opens in the console terminal
3. Start coding

### 📦 Configuration

| Input | Description | Default |
|-------|-------------|---------|
| `agentSkills` | Skill packages to install (SKILLS.md files), one per line or JSON array | - |
| `initBashScript` | Bash script to run before OpenCode starts | - |
| `idleTimeoutSecs` | Shutdown after inactivity | 900 |

### 📚 Skills Support

This Actor supports [SKILLS.md](https://skills.sh/) files - specialized instructions that enhance AI coding agent capabilities. Skills are installed automatically at startup.

### 🎯 Use Cases

- Run OpenCode without local installation
- Use free AI models for coding tasks
- Integrate OpenCode into automation workflows

### 🔗 Links

- [OpenCode](https://opencode.ai)
- [OpenCode GitHub](https://github.com/anomalyco/opencode)
- [AI Sandbox](https://apify.com/apify/ai-code-sandbox)

# Actor input Schema

## `agentSkills` (type: `string`):

Skill packages to install for the AI coding agent — SKILLS.md files with specialized instructions (see https://skills.sh/). One skill per line, e.g. `anthropics/skills` (blank lines and `#` comments are ignored), or a JSON array like `["apify/agent-skills", "anthropics/skills"]`.

## `initBashScript` (type: `string`):

Optional bash script to run on startup for installing packages or setting up the environment.

## `envVars` (type: `string`):

Secret environment variables exposed to the sandbox shell, init script, and code execution. Encrypted at rest by Apify, decrypted only at runtime. Accepts `KEY=VALUE` per line or a JSON object like `{"OPENAI_API_KEY": "sk-...", "MY_VAR": "hello"}`.

## `idleTimeoutSecs` (type: `integer`):

Automatically shut down after this many seconds of inactivity. Set to 0 to disable. Recommended: set Actor timeout to 0 (infinite) when using this.

## Actor input object example

```json
{
  "agentSkills": "# One skill per line, e.g. anthropics/skills\n# apify/agent-skills",
  "initBashScript": "#!/bin/bash\n# Runs on startup. Uncomment or add your own:\n# apt-get update && apt-get install -y jq\n# mkdir -p /sandbox/data",
  "idleTimeoutSecs": 900
}
```

# Actor output Schema

## `url` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "agentSkills": `# One skill per line, e.g. anthropics/skills
# apify/agent-skills`,
    "initBashScript": `#!/bin/bash
# Runs on startup. Uncomment or add your own:
# apt-get update && apt-get install -y jq
# mkdir -p /sandbox/data`,
    "idleTimeoutSecs": 900
};

// Run the Actor and wait for it to finish
const run = await client.actor("agentify/opencode").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "agentSkills": """# One skill per line, e.g. anthropics/skills
# apify/agent-skills""",
    "initBashScript": """#!/bin/bash
# Runs on startup. Uncomment or add your own:
# apt-get update && apt-get install -y jq
# mkdir -p /sandbox/data""",
    "idleTimeoutSecs": 900,
}

# Run the Actor and wait for it to finish
run = client.actor("agentify/opencode").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "agentSkills": "# One skill per line, e.g. anthropics/skills\\n# apify/agent-skills",
  "initBashScript": "#!/bin/bash\\n# Runs on startup. Uncomment or add your own:\\n# apt-get update && apt-get install -y jq\\n# mkdir -p /sandbox/data",
  "idleTimeoutSecs": 900
}' |
apify call agentify/opencode --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,agentify/opencode"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/pAzUEZSBGBQMHPJ0M/builds/O51v4TbbOrZM1vK96/openapi.json