Metadata-Version: 2.4
Name: arteliq
Version: 0.1.2
Summary: Self-improving multi-agent harness: goal -> project -> kanban -> workers -> verified result
Author: MisterReds
License-Expression: Apache-2.0
Project-URL: Homepage, https://misterreds.github.io/arteliq/
Project-URL: Repository, https://github.com/MisterReds/arteliq
Project-URL: Issues, https://github.com/MisterReds/arteliq/issues
Keywords: ai-agents,multi-agent,autonomous-agents,agent-harness,llm,claude-code,codex
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Environment :: Web Environment
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: anthropic>=1.0
Requires-Dist: httpx>=0.27
Requires-Dist: PyYAML>=6
Requires-Dist: tzdata; sys_platform == "win32"
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == "dev"
Provides-Extra: gates
Requires-Dist: ruff==0.17.2; extra == "gates"
Requires-Dist: mypy==2.4.0; extra == "gates"
Requires-Dist: types-PyYAML==6.0.12.20261103; extra == "gates"
Requires-Dist: coverage>=7.6; extra == "gates"
Requires-Dist: radon>=6; extra == "gates"
Requires-Dist: pylint>=3.3; extra == "gates"
Requires-Dist: mutmut>=3.8; extra == "gates"
Requires-Dist: pip-audit>=2.7; extra == "gates"
Dynamic: license-file

<p align="center"><img src="https://raw.githubusercontent.com/MisterReds/arteliq/master/docs/brand/arteliq-logo.svg" alt="Arteliq" height="72"></p>

**Arteliq** is a self-improving multi-agent harness: you give it a goal, it plans the project, hires a team of AI
workers, reviews every task, and keeps going until an independent audit confirms the goal is met.

**Arteliq** — многоагентный харнесс: цель → план → команда ИИ-воркеров → ревью каждой задачи → аудит результата.
Работает автономно, на любых провайдерах и подписках (Claude Code, Codex, API, локальные модели).

<p align="center"><img src="https://raw.githubusercontent.com/MisterReds/arteliq/master/docs/img/app-project-light.webp" alt="Arteliq dashboard: project page" width="760"></p>

```bash
pip install arteliq
arteliq run "Make a CLI tool that converts CSV to JSON, with tests and a README" --web
# dashboard: http://127.0.0.1:8765
arteliq app        # the dashboard in its own app window
```

- Autonomy first: the owner is asked only when a decision is genuinely theirs.
- Verified results: discriminating checks per task, a reviewer, and a completion audit.
- Any provider: Claude Code and Codex subscriptions, Anthropic and OpenAI-compatible APIs, local models.
- Desktop app window, phone access and a Telegram bot.
- Safety: an OS sandbox for agent commands, a command policy, protected project files.

Full documentation (in Russian): https://github.com/MisterReds/arteliq
