> ## Documentation Index
> Fetch the complete documentation index at: https://docs.iearena.org/llms.txt
> Use this file to discover all available pages before exploring further.
# Pre-integrated agents
> Run agents supported by Harbor.
Harbor includes integrations for many agents so that you don't have to install any dependencies.
```bash theme={"system"}
export OPENAI_API_KEY="..."
harbor run \
-t hello-world/hello-world \
-a codex -m openai/gpt-5.6-sol
```
```json config.json theme={"system"}
{
"agents": [
{
"name": "codex",
"model_name": "openai/gpt-5.6-sol"
}
],
"tasks": [
{
"name": "hello-world/hello-world"
}
]
}
```
```bash theme={"system"}
export OPENAI_API_KEY="..."
harbor run --config config.json
```
```python theme={"system"}
import asyncio
from harbor.job import Job
from harbor.models.job.config import JobConfig
from harbor.models.trial.config import AgentConfig, TaskConfig
async def main():
job = await Job.create(
JobConfig(
agents=[
AgentConfig(
name="codex",
model_name="openai/gpt-5.6-sol",
)
],
tasks=[TaskConfig(name="hello-world/hello-world")],
)
)
await job.run()
asyncio.run(main())
```
Use `-a` to select the agent and `-m` to select its model. Run
`harbor run --help` for the current options.
## Available agents
`aider`, `antigravity-cli`, `antigravity-sdk`, `claude-code`, `cline-cli`,
`codex`, `computer-1`, `copilot-cli`, `cortex-code`, `cursor-cli`, `deerflow`,
`devin`, `dspy-rlm`, `eve`, `fx`, `gemini-cli`, `goose`, `grok-build`,
`hermes`, `junie`, `kimi-code`, `kimi-cli`, `langgraph`, `mcode`,
`mimo`, `mini-swe-agent`, `nemo-agent`, `openclaw`, `opencode`, `openhands`,
`openhands-sdk`, `oracle`, `nop`, `pi`, `qwen-coder`, `rovodev-cli`,
`swe-agent`, `terminus-2`, `trae-agent`, `vibe`
You can also run agents from the [ACP registry](/core-concepts/agents/acp) or
add a [custom agent](/core-concepts/agents/custom-agents).
## Agent capabilities
Capabilities describe optional features supported by each integration.
| Capability | Purpose | Supported agents |
| -------------------------------------------------------------------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [ATIF](/core-concepts/agents/atif) | Produce an ATIF trajectory | `acp`, `antigravity-cli`, `antigravity-sdk`, `claude-code`, `cline-cli`, `codex`, `computer-1`, `copilot-cli`, `cortex-code`, `cursor-cli`, `devin`, `eve`, `gemini-cli`, `goose`, `grok-build`, `hermes`, `junie`, `kimi-cli`, `mimo`, `mini-swe-agent`, `nemo-agent`, `openclaw`, `opencode`, `openhands`, `openhands-sdk`, `qwen-coder`, `rovodev-cli`, `swe-agent`, `terminus-2`, `trae-agent`, `vibe` |
| [Resume](/core-concepts/tasks/multi-step) | Continue the native session between task steps | `aider`, `claude-code`, `codex`, `copilot-cli`, `cortex-code`, `gemini-cli`, `goose`, `junie`, `kimi-code`, `kimi-cli`, `mcode`, `mimo`, `opencode`, `pi`, `qwen-coder` |
| [Load native trajectory](/core-concepts/jobs/loading-trajectories#native-trajectories) | Restore an agent's native session | `claude-code`, `codex` |
| [Load ATIF trajectory](/core-concepts/jobs/loading-trajectories#atif-trajectories-1) | Load prior ATIF context | `claude-code`, `codex` |
| [Handoff](/core-concepts/jobs/handoff) | Continue a completed session locally | `claude-code` |
| [Native configuration](#native-configuration) | Accept the agent's native configuration format | `claude-code`, `codex`, `deerflow`, `junie` |
| [Windows](/core-concepts/tasks/windows-tasks) | Run in Windows task containers | `nop`, `oracle` |
| [ACP bridge](/core-concepts/jobs/simulate-a-user#bridge) | Act as the target in a simulated-user trial | `claude-code`, `gemini-cli` |
## Agent options
`--ak` and `--ae` are two of the most commonly used agent flags. Run
`harbor run --help` to see the full set.
| Flag | Purpose |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
| `--ak`, `--agent-kwarg` | Pass a setting to the agent implementation. Values such as numbers, booleans, lists, and objects are parsed into their corresponding types. |
| `--ae`, `--agent-env` | Set an environment variable during agent setup and execution. Values remain strings. |
Each agent supports its own kwargs and environment variables. Check the
agent's integration before setting them.
```bash theme={"system"}
harbor run \
-t hello-world/hello-world \
-a claude-code -m anthropic/claude-sonnet-5 \
--ak max_turns=20 \
--ae MCP_TIMEOUT=20000
```
Here, `max_turns=20` configures the Claude Code integration, while
`MCP_TIMEOUT` is available to the agent process. Both flags can be **repeated**.
### Native configuration
Load native config file for corresponding agent. Check out [Claude Code settings.json](https://code.claude.com/docs/en/settings) and
[Codex configuration config.toml](https://developers.openai.com/codex/config-reference) as example. `claude-code`, `codex`, `deerflow`, and `junie` accept a native config
file:
```bash theme={"system"}
# Config file
harbor run ... -a codex --ak "config=path/to/config.toml"
```
Inline JSON is also supported. Harbor converts inline JSON to the agent's native config file format and passes it to the agent:
```bash theme={"system"}
# Inline config
harbor run ... -a codex --ak 'config={"model_context_window": 200000}'
```