Metadata-Version: 2.4
Name: agent-anything
Version: 0.1.0
Requires-Python: >=3.13
Description-Content-Type: text/markdown

# agent-anything

`agent-anything` is a command-line tool for running AI coding agents and writing their final responses to the terminal or a specified file.

Currently supported providers:

- Codex (default)

## Installation

### Requirements

- [uv](https://docs.astral.sh/uv/) is installed
- Codex CLI is installed and authenticated, and the `codex` command is available in your terminal

Run the following command to verify that Codex CLI is available:

```bash
codex --version
```

### Install

```bash
uv tool install agent-anything
```

After installation, run:

```bash
agent-anything --help
```

You can also run it temporarily with `uvx` without installing it:

```bash
uvx agent-anything "Summarize the directory structure of the current project"
```

## Usage

```bash
agent-anything "Review the current project and suggest improvements"
```

### Write the result to a file

```bash
agent-anything "Generate a code review report for the current project" \
  --output review.md
```

### Output JSON

JSON output requires a JSON Schema provided through `--json-schema`. You can pass either a JSON object directly or the path to a Schema file.

Pass a JSON Schema directly:

```bash
agent-anything "Summarize the current project" \
  --format json \
  --json-schema '{"type":"object","properties":{"summary":{"type":"string"}},"required":["summary"],"additionalProperties":false}'
```

Use a JSON Schema file:

```bash
agent-anything "Summarize the current project" \
  --format json \
  --json-schema schema.json \
  --output result.json
```

### Specify the model and reasoning effort

```bash
agent-anything "Analyze this problem" \
  --model <model-name> \
  --reasoning_effort high
```

Available reasoning effort levels are `low`, `medium`, `high`, `xhigh`, `max`, and `ultra`. Actual support depends on the selected model and Codex CLI version.

### Command-line options

```text
agent-anything [--format {text,json}]
               [--output OUTPUT]
               [--json-schema JSON_SCHEMA]
               [--provider {codex}]
               [--model MODEL]
               [--reasoning_effort {low,medium,high,xhigh,max,ultra}]
               [--verbose]
               prompt
```

| Argument | Description |
| --- | --- |
| `prompt` | Task description sent to the agent |
| `--format` | Output format: `text` or `json` (default: `text`) |
| `--output` | Write the final response to the specified file instead of the terminal |
| `--json-schema` | JSON Schema object or file path; only used for JSON output |
| `--provider` | Agent provider to use; currently only `codex` is supported |
| `--model` | Model to use for the current task |
| `--reasoning_effort` | Reasoning effort to use for the selected model |
| `--verbose` | Stream provider execution progress to standard error |
| `--version` | Show the current version |
| `--help` | Show the help message |

## Features

- Run AI coding agents non-interactively
- Capture and output the agent's final response
- Support plain text and JSON Schema-based structured output
- Write results to the terminal or save them to a file
- Select the model and reasoning effort for each task
