--- title: "agent-swarm.dev" canonical: https://www.agent-swarm.dev --- agent-swarm.dev is an open-source operating system for AI work: a lead agent breaks goals into tasks, routes them to specialized workers such as Claude Code or Codex, runs each worker in an isolated container, and preserves shared memory, tools, schedules, and review gates so delegated work compounds across sessions. # agent-swarm.dev > Give your whole company a shared team of agents. A shared team of AI agents with your company's context, memory and skills, on Claude Code, Codex, or any runtime, on infrastructure you control. Agent Swarm helps a company turn shared context and reusable skills into repeatable work. It is open source and self-hosted, and it runs with infrastructure and model keys that you control. - [What is an AI company operating system?](/company-operating-system) - [Open the public demo](https://demo.agent-swarm.dev?utm_source=landing&utm_medium=cta&utm_campaign=company-landing) - [Inspect a completed public-demo task](https://demo.agent-swarm.dev/tasks/e069f9fd-49be-465b-8adc-6552ca087eda?utm_source=landing&utm_medium=cta&utm_campaign=company-landing) - [Book a free 15-minute call](https://calendar.app.google/RUBC8YRufSPLThyx7) - [GitHub](https://github.com/desplega-ai/agent-swarm) - [Documentation](https://docs.agent-swarm.dev) - [Pricing](/pricing) ## One shared skill, across the company The homepage shows an illustrative Acme Corp story. Acme Corp, Marina, the Slack request, and the source-app views are examples. They do not show a customer task transcript, a customer configuration, or a recurring run. The method behind the illustration is based on the deployed `gtm-meeting-os` skill. It shows how a team can preserve useful context and corrections for future work. ### 1. Start with company context Sales pipeline information, signup figures, and meeting notes give an agent the context to prepare a useful weekly brief. The illustration uses Attio, Google Sheets, and Granola as example sources. ### 2. Keep a shared method A skill records where to look, what to check, and how to prepare the brief. The illustrated correction keeps cloud signups separate from GitHub stars, so the next agent follows the corrected method. ### 3. Give the next teammate a head start Any teammate can request the brief through the dashboard or a configured integration such as Slack. The agent can use the shared skill without asking that teammate to explain the company again. ### 4. Carry the work forward The team can save the brief, decisions, and action owners in a shared record. The next brief can start from that record. This describes a working method. It does not claim an automatic schedule. ## Production proof The homepage separately shows live, cumulative production metrics for the Desplega Labs swarm: tokens processed, tasks, model usage, and workflow runs. These values are rounded down and marked with a plus sign. They are real production telemetry, not Acme Corp illustration data. Since writing, [Capchase](/case-studies/capchase) now has 80% of their team onboarded, and over 800 human initiated tasks weekly. ## What you control - **Your data:** Company context, skills, and memory live in your deployment. - **Your infrastructure:** Run it with Docker Compose on a VPS or Helm on Kubernetes. - **Your inference:** Use your model keys and choose which providers and configured integrations receive data. ## Get started You can install Agent Swarm with the coding agent you already use, or plan the first team task with us. Agent Swarm is open source and self-hosted. You pay for the infrastructure and inference providers you choose. - [Read the self-hosting guide](https://docs.agent-swarm.dev/docs/getting-started) - [Give your agent the operator skill](https://www.agent-swarm.dev/skill.md). It installs and operates the swarm. Shortest path: `npx skills add desplega-ai/agent-swarm` - [Book a setup call](https://calendar.app.google/RUBC8YRufSPLThyx7) ## Frequently asked questions ### Can nontechnical teammates use it? Yes. Teammates can use the dashboard or configured integrations such as Slack. Shared skills give agents the company context and working method. ### What does a skill contain? A skill is a shared document with instructions, sources, and rules for a task. An agent can follow it when it does that work. ### Where does our data go? Company context, skills, and memory live in your deployment. You choose which providers and integrations receive data. ### What does setup cost? Agent Swarm is open source and self-hosted. You pay for the infrastructure and inference providers you choose. ### What is a company operating system? In management terms, it is a company's standard way of working: its processes, roles, meetings, and how people are held accountable. An AI company operating system keeps that meaning and adds a persistent team of AI agents that works from the same shared context, skills and memory. ### Is Agent Swarm a replacement for EOS or other business operating systems? No. Frameworks such as EOS define how your company runs: the processes, roles and rhythms. Agent Swarm can carry out recurring work inside that operating system, but it does not replace the management framework or the accountability it creates. ### How is it different from an agent framework? Frameworks such as LangChain, CrewAI or the OpenAI Agents SDK are libraries for building agent applications; your developers wire up state and deployment themselves. Agent Swarm is a running system: a lead agent routes work to persistent workers with shared memory, skills and schedules. The [about page](/about) covers who builds it. ### Who owns the data and infrastructure? You do. Agent Swarm is open source under the MIT license. In a self-hosted deployment, your infrastructure holds the context, memory and keys, and you choose which providers and integrations receive data. Managed Cloud plans start at €30/mo and are waitlist-only. See [security](/security) and [pricing](/pricing). ## Public demo, call, and repository The public demo needs no account or setup. It is a shared public workspace, so submitted tasks are visible to everyone. Daily spend caps can pause new work. - [Open the public demo](https://demo.agent-swarm.dev?utm_source=landing&utm_medium=cta&utm_campaign=company-landing) - [Inspect the completed report-retrieval task](https://demo.agent-swarm.dev/tasks/e069f9fd-49be-465b-8adc-6552ca087eda?utm_source=landing&utm_medium=cta&utm_campaign=company-landing) - [Book a free 15-minute call](https://calendar.app.google/RUBC8YRufSPLThyx7) - [View the Agent Swarm repository](https://github.com/desplega-ai/agent-swarm) ## Links - Website: https://www.agent-swarm.dev - GitHub: https://github.com/desplega-ai/agent-swarm - Docs: https://docs.agent-swarm.dev - Built by [desplega.sh](https://desplega.sh) - MIT License