Skip to main content

Aria Code icon

Aria Code

An open-source AI agent for coding, financial analysis and logistics operations.
Numbers you can check, client data kept apart, actions a person approves.

简体中文 · English

npm version PyPI version CI status Apache License 2.0

Real Aria Code session: Gemini 2.5 Pro writes fx.py and its tests, runs them after each step is approved, then /review checks the change

A real session on Gemini 2.5 Pro (Vertex AI): Aria writes fx.py and its tests, runs them once each step is approved, then /review checks the change and gives its verdict. Waiting is shortened; nothing else is changed. Still · Recorder · Renderer

What Aria Code does

Writes code and builds projects. Describe the task in plain words. Aria reads the project, writes and edits files, runs commands and tests, and shows every change before it lands — nothing is written or run until you say yes. /review reviews a change the way a careful colleague would: prioritised findings (P0–P3) with file and line, and a verdict; aria-code review --base main --fail-on P1 gates a pull request in CI. Use a local Ollama model, Gemini on Google Cloud (Vertex AI, with nothing more than a gcloud login), or another supported provider.

Analyses markets and finances. Quotes, technical indicators, backtests with an HTML report, risk and factor analysis, SEC filings, and US, Hong Kong, A-share and crypto data. Results name their data source, period and any gaps.

Real Aria Code session: technical indicators for AAPL and a one-year momentum backtest on SPY, with data source, period and completeness stated

Runs logistics operations. For third-party logistics: reorder points, safety stock, ABC/XYZ classes, dead stock, carrier scorecards and freight anomalies — and in Feishu, a daily digest per shipper with approval cards.

Real Aria Code session: a refusal to mix two shippers' data, reorder points for one shipper, and a carrier scorecard with a saving and two anomalies

Both recorded from real sessions — market data from yfinance; the logistics data is the sample 3PL in evals/fixtures, with no model call.

How it works

A general-purpose assistant aims for an answer that reads well. In code, markets and warehouses the result gets acted on — a rounding rule in a currency function, one purchase order left out of a reorder quantity. Three rules follow from that.

Numbers you can check. Reorder points, safety stock, carrier rankings and backtests come from stated formulas and named data, with the formula and every assumption in the result — as does stablecoin settlement reconciliation, from the Artheras skills Aria Code can install. When the data cannot support an answer — under 14 days of demand history, rows that name no shipper — it says so instead of estimating. The operations eval suite checks exactly these traps.

Client data kept apart. A third-party logistics provider holds many clients' stock side by side. A chat group bound to one shipper confines every analysis to that shipper, and the logistics tools themselves refuse another shipper's data or an unattributable file — the rule holds below the prompt, whatever the model asks for.

Actions a person approves. In the terminal, every file write and command waits for your yes, with the diff in front of you. In Feishu, /补货 turns the reorder list into a purchase-order draft card; nothing happens until an authorised approver presses approve, and what runs is exactly what was shown. The draft is a file for your own purchasing system — Aria Code places no orders.

A fresh install has no live business data: the logistics tools read your exports (CSV or JSON), market data comes from public sources, and the chat features need a Feishu app or the Aria relay.

Quick start

Install the standalone CLI on macOS or Linux without Python, Node.js, or npm:

curl -fsSL https://raw.githubusercontent.com/artheras/aria-code/main/scripts/install.sh | sh
~/.local/bin/aria

On Windows x64, run this in PowerShell:

irm https://raw.githubusercontent.com/artheras/aria-code/main/scripts/install.ps1 | iex
aria

The installer downloads the binary for your OS from the latest GitHub release, checks its SHA-256 digest, and installs it in your user account. Open a new terminal to start the interactive CLI with aria, aria code, or aria-code. Set ARIA_CODE_VERSION=v0.55.0 to pin a release.

Alternative package-manager installs: npm install -g @artheras/aria-code (requires npm) or python3 -m pip install --upgrade "aria-code<4" (requires Python 3.10+; the <4 skips an older 4.x numbering that PyPI still lists). For development from source, see CONTRIBUTING.md.

The pip base install supports coding and chat without the financial data stack. Add it with python3 -m pip install "aria-code[finance]<4"; full, all, and dev retain finance dependencies. Native/npm releases retain their bundled financial tools. See optional finance installation.

Updates

Aria checks for a newer stable version in the background at startup, at most once per day. Cached notices appear immediately; network checks never delay the prompt. It checks GitHub Releases, or scoped npm for npm installs. Pip updates pin the GitHub version and verify that version is available on PyPI, avoiding the older 4.x numbering still listed as PyPI's latest. Source checkouts receive Git update instructions.

aria update --check  # check without installing
aria update          # install the newest stable version for this install channel
aria update --to 0.110.0  # choose a specific stable release
aria update --rollback   # native macOS/Linux: restore the previous managed release offline

In an interactive session, use /update --check or /update, then restart Aria. Native updates verify SHA-256 and the downloaded binary's version before switching the command; a failed download or verification leaves the existing command in place. Startup checks only notify. To disable them, set check_for_update_on_startup to false in ~/.aria-code/config.json.

For GitHub notifications, open this repository, select Watch → Custom → Releases, and save. Notifications follow your GitHub notification settings. Published stable releases appear on the release page once the platform assets and package publishing have completed.

Native macOS/Linux updates retain interrupted transfers and can use the verified official npm platform artifact when GitHub downloads fail. For recovery and a model generation check (aria health --model --tools --json), see updates and model diagnostics.

To use a local model, install Ollama, pull a coding model, and start Aria in local-only mode:

ollama pull qwen2.5-coder:7b
aria-code --local

Or run a single task in an existing project:

aria-code -C ~/Projects/my-app -p "Inspect this project, fix the failing tests, run them, and summarize the diff."

Aria may request approval before editing files or running commands, according to the configured permission mode. Review changes and test results before committing them.

Google Cloud models can use Aria's local file and command tools: inference stays in the cloud while edits and tests run on your computer. Use --read-dir DIR for additional file-reading locations and --add-dir DIR for additional writable directories. Command-line directory grants last for this invocation only. See local projects and file access for permissions and Google authentication.

In a script or CI job, --json prints one JSON result and --format jsonl prints one JSON event per line as the turn runs (turn.started, tool.started, tool.completed, turn.completed). Only JSON goes to stdout, and a failed turn exits 1. With no one there to approve, pass --allow-tools edit_file,run_command for the tools the job may use.

aria-code -p "Fix the failing tests and run them" --format jsonl --allow-tools edit_file,run_command > events.jsonl

Models and accounts

Route What it needs
Local Ollama An installed and running Ollama model; no cloud account for local inference.
Direct cloud provider That provider's API credentials and network access.
Direct Google Cloud Vertex AI GOOGLE_CLOUD_PROJECT and either a gcloud auth login (Aria uses Vertex AI's OpenAI-compatible endpoint with that login's token) or Application Default Credentials with aria-code[google]. GOOGLE_CLOUD_LOCATION defaults to global. Any model your project can use works without an API key: /model google/gemini-3.8-flash, the Gemini 3 previews (served only from global), or Gemma and other Model Garden managed models by their id (/model google/<id>), which go through Vertex's OpenAI-compatible endpoint.
Arthera hosted service Install aria-code[google] and sign in through /login in the CLI. Arthera account sign-in does not grant Vertex AI credentials to your own machine.

Install extras only for features you use; see pyproject.toml for the current package options. Local inference can work offline, but live market data, remote integrations, sign-in, and cloud models cannot.

Explore the project

Topic Start here
Architecture and runtime Architecture
Opt-in Rust CLI prototype and migration stages Rust CLI migration
Tool permissions and data boundaries Safety notes
Warehouse agents and their read-only data contract Warehouse ERP agents
Strategy and backtesting workflows Strategy workspace
More examples Examples
Releases and changes Changelog

For the current command-line flags, run aria-code --help. For help inside the interactive CLI, run /help. These are preferable to a copied command inventory that can drift from the product.

Contributing and license

Contributions are welcome; see CONTRIBUTING.md. Aria Code is open source under the Apache License, Version 2.0.

Releases 4.2.0 through 4.4.5 were published under the Business Source License 1.1 and remain available under those terms; releases up to and including 4.1.2 were MIT. A license grant cannot be withdrawn from someone who already has it, so each version keeps the license it shipped with — see NOTICE.

Shared financial tools can also run independently through the Financial Service MCP integration, with a reusable Finance workflow in Aria Plugins. Legacy financial commands remain available.

Metadata

Release files for aria-code 0.167.0

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

Source distribution (sdist)

Source distribution for aria-code 0.167.0
File Size Uploaded Provenance Actions
aria_code-0.167.0.tar.gz 2.6 MB Without provenance Details for aria_code-0.167.0.tar.gz

Built distributions (wheels)

Table of built distributions (wheels) for aria-code 0.167.0
File Actions
aria_code-0.167.0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for aria_code-0.167.0-py3-none-win_amd64.whl
aria_code-0.167.0-py3-none-manylinux_2_17_x86_64.whl Python 3 none Linux glibc 2.17+ x86-64 Details for aria_code-0.167.0-py3-none-manylinux_2_17_x86_64.whl
aria_code-0.167.0-py3-none-manylinux_2_17_aarch64.whl Python 3 none Linux glibc 2.17+ ARM64 Details for aria_code-0.167.0-py3-none-manylinux_2_17_aarch64.whl
aria_code-0.167.0-py3-none-macosx_13_0_x86_64.whl Python 3 none macOS 13.0+ x86-64 Details for aria_code-0.167.0-py3-none-macosx_13_0_x86_64.whl
aria_code-0.167.0-py3-none-macosx_13_0_arm64.whl Python 3 none macOS 13.0+ ARM64 Details for aria_code-0.167.0-py3-none-macosx_13_0_arm64.whl
aria_code-0.167.0-py3-none-any.whl Python 3 none any Details for aria_code-0.167.0-py3-none-any.whl

Total release size: 87.1 MB

Release files / aria_code-0.167.0.tar.gz

Download URL aria_code-0.167.0.tar.gz
Size 2.6 MB
Tags Source
SHA-256 checksum
How to use checksums
afcb3023cd5cb414e619ede1c1b1eff0a745bf5e7be0335bf07d0b34d1e9fbef
BLAKE2b-256 checksum
How to use checksums
7ed6b847b15c9cbe88448017d7cf7b0c8451630db21ac8eeda296cd55cfd3114
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / aria_code-0.167.0-py3-none-win_amd64.whl

Download URL aria_code-0.167.0-py3-none-win_amd64.whl
Size 16.8 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
d327e5e5f69d4c5953bbb858ff3f721702d0fa8524b7a578cc4911ed91f2f302
BLAKE2b-256 checksum
How to use checksums
95a8b910d89fbc690461bfd9332443d98cfde723e5683dd320b380c5dadc4f12
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / aria_code-0.167.0-py3-none-manylinux_2_17_x86_64.whl

Download URL aria_code-0.167.0-py3-none-manylinux_2_17_x86_64.whl
Size 16.9 MB
Tags Linux glibc 2.17+ x86-64 Python 3
SHA-256 checksum
How to use checksums
12dc3c18345113c3752e6575343aa9106c1ccc8aae78058ca5cf61e21cb6fb32
BLAKE2b-256 checksum
How to use checksums
5f93fa9e38e6eda39afa5ca088ad7df9905652d59b24388e2f809e1d729f3deb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / aria_code-0.167.0-py3-none-manylinux_2_17_aarch64.whl

Download URL aria_code-0.167.0-py3-none-manylinux_2_17_aarch64.whl
Size 15.7 MB
Tags Linux glibc 2.17+ ARM64 Python 3
SHA-256 checksum
How to use checksums
8c70bb42c9412fb936618732c759a0eceff241328af63b642b8bbfa1d4be3140
BLAKE2b-256 checksum
How to use checksums
d4795f2a90bdbb7b8547c76560c9bbf06b61f37822b08b39d669e061b6c9b713
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / aria_code-0.167.0-py3-none-macosx_13_0_x86_64.whl

Download URL aria_code-0.167.0-py3-none-macosx_13_0_x86_64.whl
Size 16.9 MB
Tags Python 3 macOS 13.0+ x86-64
SHA-256 checksum
How to use checksums
fa9880a6132ad1bea16c35f4bc9e62ec6b5af0392ae2e54207b81ac1e3c3fb21
BLAKE2b-256 checksum
How to use checksums
a7a1f44a163dc0f068d4364535b37975dcacdef158b485d86e661cfd598550e7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / aria_code-0.167.0-py3-none-macosx_13_0_arm64.whl

Download URL aria_code-0.167.0-py3-none-macosx_13_0_arm64.whl
Size 15.9 MB
Tags Python 3 macOS 13.0+ ARM64
SHA-256 checksum
How to use checksums
43b636646975d07400329818542a7a2ec8d2d7c17bd2acebd67eedad652c3b89
BLAKE2b-256 checksum
How to use checksums
5b02f6dee874e00497e7239429036cfdad9dcd677ca5c85a6d7b699c31ae8b1a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / aria_code-0.167.0-py3-none-any.whl

Download URL aria_code-0.167.0-py3-none-any.whl
Size 2.2 MB
Tags Python 3
SHA-256 checksum
How to use checksums
7b6d6816ea066a5d36b5bcb76f1a9e44c140d7c644f7eb6295c02bda565c3528
BLAKE2b-256 checksum
How to use checksums
e2ad84498195c6e2ecf825128d0197cacfd9abb77e0e7d43ae635186780d69b3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for aria-code 0.167.0

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

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

0.167.0 This release

7 release files No 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