openyfai-aria 1.0.0

Building AGI in public: A local-first cognitive agent with memory, world model, and Telegram integration.

ARIA (Bringing AGI to the Public)

We are building AGI in public, phase by phase, and you can watch it get smarter in real-time.

ARIA is a local-first cognitive agent with a visible brain: persistent memory, a live knowledge graph, governed tool use, continuous Telegram integration, and hackable Markdown skills.

It is built for people who want more than chat. Run it in the background, inspect how it reasons via the Local Web Dashboard, and connect it to Telegram for a 24/7 unprompted proactive AI companion.

In one sentence: install once, run aria setup, pair it on Telegram, and chat.

Quick start

# 1. Clone and Install
git clone https://github.com/openyfai/aria.git && cd aria
pip install -e ".[full,dev]"

# Alternative: install released package from PyPI (no clone required)
# pip install "openyfai-aria[full]"

# 2. Setup your keys and get your Telegram Pairing Code
aria web

# (Optional) 3. Run the background daemon to keep ARIA alive 24/7
aria start

Open http://127.0.0.1:8000 (or the Next.js frontend), complete the on-screen setup (Anthropic/Telegram keys), paste the generated PAIR- code into your Telegram bot, and try chatting!

Analyze this repo and build a knowledge graph of the architecture.

Building the static UI once (cd aria-ui && npm install && npm run build) is required before aria web can serve the app from aria-ui/out. See docs/quickstart.md for the full step-by-step.

Why ARIA

• Local-first memory and state backed by SQLite.
• A visible graph of what the agent believes.
• Provider and model choice from the setup wizard or aria setup.
• Operator controls for approvals, usage, Telegram pairing, and remote access.
• Markdown skills that let contributors extend behavior without editing Python.

More ways to run

Path	When to use
Web UI (aria web)	Default: finish setup in the browser.
Terminal agent (aria after setup)	Keyboard-first use.
CLI setup only (aria setup)	You prefer not to use the web wizard once.
Docker	Deploy to a server or share on a LAN; needs .env and a web API key. See docs/quickstart.md.

Requirements

• Python >=3.12
• Node 20 to build aria-ui/
• Docker optional

Safe defaults

• Tool approvals are on.
• Terminal execution is off.
• Direct code writes are off.
• Background actions are off.
• Remote web binds require ARIA_WEB_API_KEY.
• Telegram is deny-by-default until paired from Operator.

Read SECURITY.md before exposing ARIA beyond localhost.

Power user / troubleshooting

If chat or setup fails after you have saved provider keys, see docs/quickstart.md for aria doctor, aria doctor --ping, and related commands. You do not need these for a first successful run.

Provider support

Gemini, OpenAI, Anthropic, OpenRouter, DeepSeek, Mistral, Groq, Ollama, and local OpenAI-compatible endpoints. Settings come from the wizard, aria setup, data/ runtime files, or environment variables.

Skills

Add a Markdown file under skills/, restart ARIA, and the agent can use that workflow. Start with skills/repo_researcher.md or skills/README.md.

Repository guide

• Core loop: aria/core/cognitive_loop.py
• Providers: aria/llm/
• Web backend: scripts/web_server.py
• CLI: scripts/cli.py
• Telegram: scripts/telegram_bot.py
• Web UI: aria-ui/src/
• Skills: skills/

Development

python -m pytest tests
ruff check .
cd aria-ui && npm install && npm run lint && npm run build

Project docs

• docs/quickstart.md — install paths, Docker, troubleshooting
• CONTRIBUTING.md
• SECURITY.md
• CODE_OF_CONDUCT.md
• docs/planning/ROADMAP.md — phased roadmap
• docs/planning/launch-checklist.md — pre-public-release checklist
• docs/planning/launch-issue-backlog.md — seeded “good first issue” ideas
• CHANGELOG.md

License

Apache-2.0. See LICENSE.