agenticos
Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skill
What is agenticos?
Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.
Overview of agenticos
What it is
AgenticOS is an open-source (Apache-2.0), self-hosted platform for building, running and governing AI agents across a company. Teams configure an agent in the browser by writing its instructions, choosing a model and switching on tools, then connect it to company documents and apps and publish it to web chat, Slack, Mattermost, Telegram, a website widget or an API. Administrators control who can use each agent, what it may spend and which actions need a person's approval, and every run is recorded. Agents run on Pydantic AI and pydantic-ai-harness; the surrounding layer uses FastAPI, PostgreSQL with pgvector and Next.js. It is maintained by Vstorm and described as an alternative to ChatGPT Enterprise and Grok Bot.
Key features
- A shared live chat where colleagues and agents work in the same room, with
@to bring in any agent, tool or document. - Any agent can hand software work to Claude Code or Codex, running on the ChatGPT or Claude subscription you already pay for.
- A real browser inside the chat, which you can take over when a sign-in needs you.
- 4,700+ MCP servers, including Notion, GitHub and Jira, with per-agent choice of which tools may be called.
- Governance for every request: roles, budgets, approvals, guardrails and a recorded run.
- Agents publish dashboards and reports as pages with stable links and version history.
- AgenticOS is itself an MCP server, so Claude Code, Codex or Cursor can list and run agents within what you allowed.
Use cases
- Companies that want an internal AI agent layer they own, instead of per-seat assistants in a vendor's cloud.
- Teams with repeated work over documents and tools, such as reports, support answers, contract checks and data analysis.
- IT and security teams that need data sovereignty, company sign-in, budgets, approvals and an audit trail for AI agents.
- Engineers who want typed Python extension points and a console their non-technical colleagues can use.
Getting started
Start with Docker Compose and access to a model provider. On macOS or Linux, run: bash curl -fsSL https://raw.githubusercontent.com/vstorm-co/agenticos/main/scripts/quickstart.sh | bash On Windows, run the same command inside WSL2 with Docker Desktop's WSL2 integration switched on. The installer asks for a model provider and key, your login and an organization name, pulls the published images and starts a deployment with a working agent in it. A host with 4 vCPU and 8 GB of RAM runs it. Then open http://localhost:3000 and sign in with the login you chose during installation.
License and pricing
AgenticOS is released under the Apache-2.0 license and is open source and self-hosted. The README and metadata do not state any pricing, and no paid tiers are described.
Based on the project's public README and repository metadata.