Automatos AI is an open-source platform for building AI workforces. Create specialised agents, equip them with tools and knowledge, schedule their work, and let them operate autonomously — reporting back through a unified command centre.
It is not a chatbot wrapper. It is an operating system for AI agents.
100+ marketplace agents · 1,000+ tool integrations · 300+ LLMs · 150+ skills · Bring-your-own-keys
A unified chat interface that routes your messages to the right agent automatically. Quick actions let you jump straight into coding, creating agents, managing knowledge, or building recipes.
100+ agents in the community marketplace — install what you need, when you need it. Code Reviewer, QA Engineer, Sentinel, Scribe, researcher and marketer roles, Shopify specialists, and more. Each agent has its own model configuration, capabilities, persona, and performance metrics. Install from the marketplace or build a custom agent in seconds.
Connect your agents to GitHub, Slack, Jira, Stripe, Shopify, Datadog, Notion, HubSpot, and a thousand more through the community marketplace. Browse, install, and assign integrations to specific agents from a single dashboard — no glue code, no per-tool SDKs.
Packaged bundles install a full operations team in a single step — agents, skills, playbooks, and dashboard widgets pre-wired together. Example: the Shopify package ships with 12 specialised agents, 32 Shopify skills, and a widget set for store ops, inventory, merchandising, SEO, campaigns, and customer support. Install it once, and your workspace goes from empty to a running e-commerce back office.
Skills are portable, versioned capability packs — a system prompt, a set of tools, and an output contract. Drop Sentinel onto a security agent, Scout onto a research agent, or write your own. One skill, any agent, instantly productive.
Route any agent to any model. OpenAI, Anthropic, Google, DeepSeek, GLM, Mistral, Qwen, Llama — through OpenRouter or direct provider keys. Mix cheap models for heartbeat work with frontier models for reasoning, and see the cost impact per request.
See your entire AI workforce at a glance. Live agent status, scheduled routines, task completion metrics, and agent reports — all in one place. Agents report their findings so you don't have to check on them.
Track every API call across every model. See cost per agent, cost per request, usage trends over time, and cost projections. Know exactly what your AI workforce costs before the bill arrives.
Upload documents, sync folders from Dropbox and cloud storage, and let the platform chunk, embed, and index everything automatically. Your agents get RAG-powered access to your entire knowledge base.
| Capability | What it does |
|---|---|
| Universal Router | Multi-tier routing (cache, rules, semantic, LLM) sends messages to the right agent every time |
| Recipes & Workflows | Multi-step automation with scheduling, triggers, and inter-agent coordination |
| Prompt Optimisation | A/B test and score prompts against live traffic, automatically improve agent performance |
| Workspace Execution | Sandboxed environments where agents run code, manage files, and interact with Git repos |
| Multi-Tenancy | Full workspace isolation — each team gets their own agents, data, and configuration |
| Plugin System | Extend agents with skills, plugins, and custom tools from the marketplace or your own repos |
git clone https://github.com/AutomatosAI/automatos-ai.git
cd automatos-ai
cp .env.example .env # Add your API keys
docker-compose up- Frontend: http://localhost:3000
- API Docs: http://localhost:8000/docs
| Layer | Technology |
|---|---|
| Frontend | Next.js 14, TypeScript, Tailwind CSS, shadcn/ui |
| Backend | Python, FastAPI, SQLAlchemy, Alembic |
| Database | PostgreSQL, Redis |
| AI | OpenRouter, OpenAI, Anthropic, DeepSeek (multi-provider) |
| Storage | AWS S3, S3 Vectors |
| Auth | Clerk |
| Infra | Docker, Railway |
Full platform documentation is available in /docs, auto-synced from DeepWiki — 100+ pages covering architecture, APIs, agents, workflows, and deployment.
We're building the operating system for the agentic future. Contributions welcome.
- Fork the repo
- Create a feature branch
- Submit a PR
Star on GitHub · Read the Docs · DeepWiki
Apache 2.0 · Built by the Automatos AI team





