Skip to main content

pycodex

中文

pycodex brings the Codex agent loop to Python, with a CLI, reusable Agent API and browser workspace. It aims to follow upstream behavior; supported features and deliberate differences are documented in Alignment.

Package Provides Python
python-codex Agent, runtime, CLI, tools, Responses compatibility server and portable storage 3.6.2+
pycodex-ws Browser workspace, Canvas, file/diff viewers and optional Feishu integration 3.7+

The workspace package installs the matching core version. Python imports use pycodex; the commands are pycodex and pycodex-ws.

Install and run

Install the core CLI:

python3 -m pip install python-codex
pycodex

Or install the browser workspace, which includes core:

python3 -m pip install pycodex-ws
pycodex-ws --help

Use python3 -m pip install --upgrade pycodex-ws to upgrade both packages together. If a command is missing from PATH, use python3 -m pycodex or python3 -m workspace_server with the interpreter used for installation.

Model configuration

pycodex reads ~/.codex/config.toml and the adjacent .env. Configure model, model_provider, and the provider's base_url and env_key as needed. The built-in openai provider uses OPENAI_API_KEY. Authentication uses API keys; ChatGPT sign-in credentials from auth.json or the OS keychain are not loaded.

pycodex --profile my_profile "Summarize this repository."
pycodex --config /path/to/config.toml
pycodex doctor

Models use the streaming Responses API. For a Chat Completions backend, set use_chat_completion = true in its provider table. Other backend options include:

pycodex --vllm-endpoint http://127.0.0.1:18000
pycodex --profile my_profile --use-messages

See context and configuration and the Responses compatibility server.

CLI

Run pycodex without a prompt for an interactive session, or supply a prompt for a single turn:

pycodex "Summarize this repository in one sentence."
printf 'Reply with exactly OK.' | pycodex
pycodex --json "Reply with exactly OK."
Command Purpose
/model, /effort Show or change the model and reasoning effort
/cd <directory> Change the session's working directory while idle
/title, /history Manage the title and inspect conversation history
/resume List saved sessions; pass an index or session UUID to resume
/compact Summarize history to free context
/fork Continue the current history under a new session ID
/queue <message> Wait for the active turn to finish before submitting

Ordinary input during a turn steers at the next safe sampling boundary. Slash input uses Codex's command rules: /data/project and /tmp/ are ordinary messages, while an unknown single-component name such as /modle or /tmp reports a command error. Start the input with a space to send any slash-prefixed text literally, including known commands such as /model. These rules also apply to the browser workspace and Feishu. Sessions are saved under CODEX_HOME/sessions. Set model_auto_compact_token_limit in the configuration to compact automatically.

Ctrl+D or Ctrl+C closes the CLI after accepted work finishes. A second Ctrl+C during closing exits immediately. Use pycodex --help for startup options.

Browser workspace

Create workspaces.json:

{
  "workspaces": [
    {"id": "demo", "work_dir": ".", "state_path": "demo", "enable_board": true}
  ]
}
pycodex-ws --listen 127.0.0.1:6007 --workspace-config workspaces.json

Open http://127.0.0.1:6007. The workspace combines conversations with a live HTML Canvas and read-only file/diff viewers. Click file links in replies to open them, and use Insert into chat to add selected code to an editable draft. Keep the server's stdin open: EOF initiates shutdown. The gear button starts an Agent conversation for customizing the interface through files in ~/.pycodex/frontend/.

See the workspace guide for session controls, storage and Feishu setup. The separately distributed VS Code extension uses the same workspace backend, including on Remote SSH hosts.

Python API

Use the standard model and tool setup from Python:

from pycodex.bootstrap import build_agent, build_model

agent = build_agent(build_model())
try:
    result = agent.ask("Summarize this repository in one sentence.")
    print(result.output_text)
finally:
    agent.shutdown()

For custom integrations, Agent accepts a model client, ToolRegistry and ContextConfig. await agent.run_turn([...]) runs an asynchronous turn; AgentRuntime adds input queues, commands and frontend subscriptions. See runtime contracts and examples.

Portable configuration

Portable mode transfers an encrypted bundle of your configuration, instructions and skills to another machine. Start a storage service in a separate terminal:

python3 -m pycodex.portable.server --root .tmp/pycodex_storage --host 127.0.0.1 --port 5577

Upload the default Codex home, or specify another directory:

pycodex --put @127.0.0.1:5577
pycodex --put /path/to/.codex/@127.0.0.1:5577

After verifying a download round trip, the command prints a reusable pycodex --call ... command. Run it on the target machine using a storage address reachable from that machine.

Development and reference

uv sync --dev
uv run pycodex
uv run --dev pytest

Release notes and implementation details live in docs/.

Markdown view modes

Markdown file views include a Show source / Show preview button. Switching modes preserves each mode's reading position without replaying a previous line target.

Responses reliability

Providers can opt into ordered failover with fallback_models = ["backup-one", "backup-two"] in their [model_providers.<name>] table. Each target uses the same endpoint, credentials, history and tools; request settings are rebuilt for that model, while the session's selected model stays unchanged. Transient errors exhaust stream_max_retries before advancing. Unavailable-model errors and first-data timeouts advance immediately. Existing retry notices name both models and include the underlying error.

Failed models cool down for 900 seconds within that client. Subsequent requests skip them, retry them after expiry, and restart the full chain when every target is cooling. fallback_cooldown_seconds = 0 disables cooldown; explicit model selection clears it. New sessions and subagents have independent cooldowns. An absent or empty list disables failover. Invalid input, context-length and terminal incomplete errors retain their existing handling. Backups must support the active tools and context size; compaction keeps the selected model's policy.

Responses HTTP 408/429 and server errors use the provider retry budget. Rate-limit messages containing try again in or retry after supply the retry delay. CLI and workspace retry notices include the underlying error details; workspace notices survive browser refresh and active-turn reattachment, and remain separate from the assistant reply. They are not persisted in rollouts.

Workspace input history

The workspace message box supports Up/Down input history. Up recalls earlier human inputs in the current conversation; Down returns to the unsent draft. Automatic wake-up messages are excluded, and arrows retain normal cursor movement inside multiline drafts.

Metadata

Release files for python-codex 0.5.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for python-codex 0.5.1
File Size Uploaded Provenance Actions
python_codex-0.5.1.tar.gz 239.4 kB With provenance Details for python_codex-0.5.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for python-codex 0.5.1
File Interpreter ABI Platform Actions
python_codex-0.5.1-py3-none-any.whl Python 3 none any Details for python_codex-0.5.1-py3-none-any.whl

Total release size: 510.1 kB

Release files / python_codex-0.5.1.tar.gz

Download URL python_codex-0.5.1.tar.gz
Size 239.4 kB
Tags Source
SHA-256 checksum
How to use checksums
d1be26b7a10fb32f36e344df9b043e6793262333c4a95b4f750489aba2567f16
BLAKE2b-256 checksum
How to use checksums
c9aab23e4ba3b57fe619c696df02a1309b82ad8e6192fa7f2d24c186c7129def
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 22, 2026.

Transparency log

Release files / python_codex-0.5.1-py3-none-any.whl

Download URL python_codex-0.5.1-py3-none-any.whl
Size 270.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
552a2c6c15b353958917d096d61bb4ee5c71a410e14c1f2f3428dc42519c8853
BLAKE2b-256 checksum
How to use checksums
bc6cd4bd3d7c2d1959a266b32c0aed503b4d0889545c87ae502eb8508fb4dbb0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 22, 2026.

Transparency log

Security for python-codex 0.5.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for python_codex-0.5.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 22, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.5.1 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page