Skip to main content

CLI to orchestrate AI agents (Claude, Codex, Gemini, Grok)

Project description

hire-ai

CLI to orchestrate AI agents (Claude, Codex, Gemini, Grok).

⚠️ Warning: By default, CLI agents run in auto-approve mode:

  • Claude Code: --dangerously-skip-permissions
  • Codex: --full-auto
  • Gemini CLI: -y

This means agents can execute commands and modify files without confirmation. You can customize this in ~/.config/hire/config.json.

Installation

# Using pipx (recommended)
pipx install hire-ai

# Using pip
pip install hire-ai

# Using Homebrew (macOS)
brew install nichiki/tap/hire-ai

Prerequisites

You need at least one of the following:

Usage

# Basic usage - hire an agent
hire codex "Design a REST API for a todo app"
hire gemini "Research the latest React 19 features"
hire claude "Review this code for security issues"
hire grok "Analyze this codebase"

# Continue a session
hire -c codex "Tell me more about the authentication"
hire -s SESSION_ID "Follow up question"

# Name a session for later
hire -n my-project codex "Start designing the architecture"
hire -s my-project "What about the database schema?"

# Pipe input
cat main.py | hire codex "Review this code"
git diff | hire claude "Explain these changes"
echo "What is 2+2?" | hire gemini

# Attach files (using @filepath)
hire claude "Review @src/main.py for security issues"
hire codex "Explain @package.json and @tsconfig.json"
hire grok "Summarize @report.pdf"

# Output as JSON
hire gemini "Summarize this" --json

# Copy to clipboard
hire codex "Write a function" --clip

# Write to file
hire claude "Generate a README" -o README.md

# Session management
hire sessions              # List all sessions
hire sessions codex        # List sessions by agent
hire show SESSION_ID       # Show session details
hire delete SESSION_ID     # Delete a session
hire delete --all          # Delete all sessions

# Check environment
hire doctor                # Check installed agents and config

Options

Option Description
-c, --continue Continue the latest session
-s, --session ID Continue a specific session
-n, --name NAME Name the session
-m, --model MODEL Specify model to use
--json Output in JSON format
--clip Copy output to clipboard
-o, --out FILE Write output to file

Configuration

Config is stored at ~/.config/hire/config.json:

{
  "adapters": {
    "claude": {
      "command": "claude",
      "args": ["--dangerously-skip-permissions"]
    },
    "codex": {
      "command": "codex",
      "args": ["--full-auto"]
    },
    "gemini": {
      "command": "gemini",
      "args": ["-y"]
    },
    "grok": {
      "model": "grok-4-latest",
      "api_key": "xai-..."
    }
  },
  "defaults": {
    "agent": "claude"
  }
}

Data Storage

Sessions are stored at ~/.local/share/hire/sessions/.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hire_ai-0.1.8.tar.gz (15.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hire_ai-0.1.8-py3-none-any.whl (22.6 kB view details)

Uploaded Python 3

File details

Details for the file hire_ai-0.1.8.tar.gz.

File metadata

  • Download URL: hire_ai-0.1.8.tar.gz
  • Upload date:
  • Size: 15.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for hire_ai-0.1.8.tar.gz
Algorithm Hash digest
SHA256 25b65e1f7eec5c0b29ae1a0942fccce0f93a070b03ff39ad9a43d1c07c89fd89
MD5 8a935630ee9bb3ea00ca92c48b3cc10d
BLAKE2b-256 5b81d854758350a0d58ac216c375275d02ce40817ebdd1b792deb976c02a6ecd

See more details on using hashes here.

File details

Details for the file hire_ai-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: hire_ai-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 22.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for hire_ai-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 5114f63bf71191a4f8f84bbc664008a7fa41f001d5e5b8c6ed179d9e2dbc5b10
MD5 fd9e84674fdeb94dc87c6db7c8326fc3
BLAKE2b-256 912521df9b294084b207a51b14ebf1cffbf98194b8263c521c31b1799fd2407d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page