Skip to main content

Python toolkit for orchestrating Parallel Codex agents across isolated worktrees.

Project description

parallel-codex

Primary implementation of Parallel Codex - Python toolkit for orchestrating Parallel Codex agents working in isolated Git worktrees.

Current Status: This package currently provides a Textual TUI for managing parallel agent sessions.

Install

uv tool install parallel-codex
# or: pip install parallel-codex

This installs the parallel-codex CLI.

Prerequisites:

  • The codex command must be available on your PATH.
  • Codex CLI must be logged in: run echo $OPENAI_API_KEY | codex login --with-api-key once before using the TUI.

TUI Usage

The TUI is the main entry point. It allows you to manage multiple Codex sessions, where each session operates on its own git worktree.

# Run the TUI
parallel-codex tui

Development Mode

To see internal logs and debug information (MCP activity, stdout/stderr) inside the application:

parallel-codex tui --dev-log-panel

TUI Features

  • Multiple Sessions: Create and switch between up to three visible sessions (Ctrl+N, Ctrl+Tab).
  • Isolated Worktrees: Each session creates a git worktree under ./.agents/<session-name> and checks out a branch pcx/<session-name>.
  • Codex Integration: Chats are sent to the codex MCP server, with file edits applied to the specific session's worktree.

Development

From packages/python-package:

# Install dependencies
uv sync

# Run TUI from source
uv run src/main.py tui --dev-log-panel

Or from the repo root:

uv run --project packages/python-package python -m parallel_codex.cli tui --dev-log-panel

To configure the repository root used by the TUI when running from source:

export PARALLEL_CODEX_REPO_ROOT=/path/to/your/repo

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

parallel_codex-1.0.2.tar.gz (43.4 kB view details)

Uploaded Source

Built Distribution

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

parallel_codex-1.0.2-py3-none-any.whl (21.4 kB view details)

Uploaded Python 3

File details

Details for the file parallel_codex-1.0.2.tar.gz.

File metadata

  • Download URL: parallel_codex-1.0.2.tar.gz
  • Upload date:
  • Size: 43.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for parallel_codex-1.0.2.tar.gz
Algorithm Hash digest
SHA256 9329138ad09e3c8c4498ae7253972a0c3a59bd6c76db79f8f4337c579dda3389
MD5 11a539535c24c67da10b529917cf69b5
BLAKE2b-256 e04e4c724ed01c8f0f163bffd6c05a5fed64d461da27cfd4aae83900a4457e3c

See more details on using hashes here.

Provenance

The following attestation bundles were made for parallel_codex-1.0.2.tar.gz:

Publisher: deploy-python.yml on parallel-codex/parallel-codex

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file parallel_codex-1.0.2-py3-none-any.whl.

File metadata

  • Download URL: parallel_codex-1.0.2-py3-none-any.whl
  • Upload date:
  • Size: 21.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for parallel_codex-1.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 e0f8c23685e34bf344c13ffca8e82761bbad7c802b86409a019c334bbe103ed0
MD5 c72fdca82de5c316f23602466d57e10c
BLAKE2b-256 fc37ec17835c06c99615a077e7250d1851c37088dcd3fca823a0c6859ef97a94

See more details on using hashes here.

Provenance

The following attestation bundles were made for parallel_codex-1.0.2-py3-none-any.whl:

Publisher: deploy-python.yml on parallel-codex/parallel-codex

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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