Vstorm's AgenticOS Turns Company Chat Into a Self-Hosted Agent Workspace Vstorm has published AgenticOS, an Apache-2.0, self-hosted AI agent platform built on Pydantic AI that runs via Docker Compose on 4 vCPU and 8 GB RAM and connects 4,700+ MCP servers and 28 model providers, including Ollama and vLLM. The platform combines shared human-agent chat rooms, RAG, browser automation, generated interfaces and coding handoff to Claude Code or Codex, with governance features including per-agent budgets, approvals, a hash-chained audit log and an envelope-encrypted vault. AgenticOS won the 2026 AAIF Open Agentic AI Innovation Award but lacks native SAML, SCIM and MFA. Vstorm's AgenticOS Turns Company Chat Into a Self-Hosted Agent Workspace A self-hosted, Apache-2.0 alternative to ChatGPT Enterprise that puts shared agents, RAG, a real browser and 4,700+ MCP servers behind your own firewall. - AgenticOS is an Apache-2.0, self-hosted AI agent platform https://github.com/vstorm-co/agenticos?utm source=alphasignal built on Pydantic AI. - Ships shared chat, RAG, a real browser, visuals, apps and coding handoff to Claude Code or Codex. - Connects 4,700+ MCP servers https://vstorm-co.github.io/agenticos/mcp/?utm source=alphasignal and 28 model providers including Ollama and vLLM. - Governance built in: per-agent budgets, approvals, hash-chained audit log, envelope-encrypted vault. - Runs via Docker Compose on 4 vCPU / 8 GB RAM; quickstart installer https://vstorm-co.github.io/agenticos/?utm source=alphasignal provisions a working agent. - Won the 2026 AAIF Open Agentic AI Innovation Award https://aaif.io/blog/winners-of-the-first-aaif-annual-technical-excellence-awards?utm source=alphasignal ; no native SAML, SCIM or MFA yet. Vstorm has published AgenticOS https://github.com/vstorm-co/agenticos?utm source=alphasignal , an Apache-2.0 platform for building, sharing, and governing AI agents across a company. It places agents and employees in shared conversations while giving organizations control over deployment, model providers, prompts, tools, secrets, and audit data. Built on Pydantic AI https://ai.pydantic.dev/?utm source=alphasignal , the project divides work between engineers and subject experts. Engineers register capabilities in typed Python, while colleagues configure agents in a browser by writing instructions, selecting a model, attaching knowledge, and enabling approved tools. Behavioral changes can therefore move through the console when no code change is required. A complete stack, ready to host The repository packages an application stack that runs through Docker Compose on company-managed infrastructure. It supports 28 model providers, including access through an existing ChatGPT subscription and local models served by Ollama or vLLM. | Layer | Implementation | |---|---| | Agent runtime | Pydantic AI and pydantic-ai-harness | | API | FastAPI | | Data and retrieval | PostgreSQL with pgvector | | Web interface | Next.js | | Deployment | Docker Compose with published images | Tools that extend beyond chat AgenticOS combines conversational agents with browser automation, coding sessions, generated interfaces, document retrieval, and Model Context Protocol integrations: - Shared rooms: Humans and agents can reply in the same conversation. Each message carries an identity, allowing an agent to distinguish participants. - Browser automation: This story is for Pro members You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.