Skip to main content

Alysis AI

AI for code, work, and everyday tasks.

Build software with Alysis Code, create documents with Alysis Work, and delegate ongoing tasks to Alysis Owls — all in one desktop app.

PyPI version CLI downloads per month CI License GitHub stars Discord members

Download for macOS & Windows · Documentation · Community

macOS on Apple silicon · Windows x64 · No Python or CLI setup required

Alysis desktop app — a fresh Work workspace with Code and Owls navigation

Three ways to get things done

Product What you can do
Alysis Code Build, debug, and review software. Work with your repositories, inspect changes, run commands in the built-in terminal, and roll back to a checkpoint.
Alysis Work Turn notes, files, and research into Word documents, spreadsheets, presentations, and PDFs. Preview the result, select what needs changing, and ask for a revision.
Alysis Owls Delegate ongoing tasks to personal assistants with persistent memory, routines, and a private local or cloud computer. Keep context as your work continues.

Owls ask for approval before actions that reach other people, make payments, publish, or delete.

Your tools, your choice

  • Choose your models. Use an Alysis account, bring your own API keys, or connect local models.
  • Search the web. Built-in web search works with any model, without a separate search API key.
  • Work across apps. Built-in computer use lets Alysis operate the apps you allow.
  • Stay in control. Choose permissions for each task, with shell commands sandboxed by default. How permissions work. Verification commands also default to strict sandboxing. Strict mode refuses execution when no backend is available. Shell sandbox

Get started

  1. Download and install the app.
  2. Connect your preferred model in Models & keys.
  3. Open a repository in Code, bring a file into Work, or set up an Owl.

Desktop guide · Your first task · Release notes

Also available in your terminal

The open-source Alysis engine and CLI live in this repository. The CLI supports macOS, Linux, and Windows.

Alysis Code CLI welcome screen followed by a short conversation

Install the CLI
# macOS, Linux and WSL
curl -LsSf https://raw.githubusercontent.com/AlysisAi/AlysisCode/main/scripts/install.sh | sh
# Windows PowerShell
irm https://raw.githubusercontent.com/AlysisAi/AlysisCode/main/scripts/install.ps1 | iex

The installers manage Python for you. Run alysis to get started and alysis update to upgrade.

Already using Python 3.11+? Install with uv tool install alysis-code or pipx install alysis-code.

CLI documentation · VS Code · JetBrains preview

Community and contributions

Join Discord, report a bug, or read the contributing guide. Report vulnerabilities privately through the security policy.

License

The engine and CLI in this repository are licensed under Apache-2.0. See LICENSE, NOTICE, and the editor sidebar's third-party notices.

Metadata

Release files for alysis-code 0.17.3

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

Source distribution (sdist)

Source distribution for alysis-code 0.17.3
File Size Uploaded Provenance Actions
alysis_code-0.17.3.tar.gz 43.5 MB With provenance Details for alysis_code-0.17.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for alysis-code 0.17.3
File Interpreter ABI Platform Actions
alysis_code-0.17.3-py3-none-any.whl Python 3 none any Details for alysis_code-0.17.3-py3-none-any.whl

Total release size: 87.7 MB

Release files / alysis_code-0.17.3.tar.gz

Download URL alysis_code-0.17.3.tar.gz
Size 43.5 MB
Tags Source
SHA-256 checksum
How to use checksums
c567b902b6cee999be66d1da8391aa57ad152f340d6de4dcdd34a0fd029a6429
BLAKE2b-256 checksum
How to use checksums
f797858435dcaaf65ddb76e842049b12a2c77ba650d4ae1bd6d1a691f3797bb5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Nov 18, 2026.

Transparency log

Release files / alysis_code-0.17.3-py3-none-any.whl

Download URL alysis_code-0.17.3-py3-none-any.whl
Size 44.2 MB
Tags Python 3
SHA-256 checksum
How to use checksums
a5958b49501f07cb44e8d3825cb0ff6e8269961535e25345180e17b7a0a607d8
BLAKE2b-256 checksum
How to use checksums
36f004d02e4d7ade6ac130ade8f376c6c6dbce86d0f5a3af1778cb6d12372312
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Nov 18, 2026.

Transparency log

Security for alysis-code 0.17.3

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 alysis_code-0.17.3.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 Nov 18, 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.

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