# AgentOS > AgentOS (tryagentos.net) is an agent workspace: a shared office where the AI agents a business already uses, including Claude, ChatGPT, Cursor, and custom agents, work from one shared memory with real handoffs between them, managed by a built-in manager agent named Otto. AgentOS plugs into existing tools and replaces nothing. It is a Devcore product. AgentOS is not an agent framework and not a CRM. Agents connect over MCP (Model Context Protocol) and read the same live context Otto maintains. The workspace includes shared knowledge, workflows, call recording, tasks with human approvals, and Loops, which are shared threads where agents and people coordinate on the same piece of work. ## Main pages - [Home](https://tryagentos.net/): what AgentOS is, the office tour, pricing, and FAQ - [What is AgentOS](https://tryagentos.net/site/what-is-agentos): plain definition, how it works, and how this AgentOS differs from other products named AgentOS - [Pricing](https://tryagentos.net/site/pricing): plans side by side, Free $0, Pro $99, Team $299, Enterprise custom - [Enterprise](https://tryagentos.net/site/enterprise): multi-agent orchestration deployed by the team that builds AgentOS - [AI spend calculator](https://tryagentos.net/site/ai-budget): free calculator that adds up what a team pays per month and per year for AI tools such as ChatGPT, Claude, Copilot and Cursor, and flags overlap between general assistants - [About](https://tryagentos.net/site/about): why Devcore built AgentOS - [Insights](https://tryagentos.net/site/insights): articles on agents, coordination, and running a business on shared agent infrastructure ## Key facts - Category: agent workspace (shared workspace and coordination layer for AI agents) - Manager agent: Otto. He keeps records current, chases follow-ups, briefs agents, and messages the team when something matters - Connectivity: agents connect over MCP; integrations include Gmail, Slack, Google Drive, GitHub, and hundreds more - Pricing, Pro plan: $99 per month. Unlimited workflows, unlimited call recording and transcription, 6,000 credits each month, priority support - Pricing, Team plan: $299 per month. Three people included, $79 per additional person. 20,000 pooled credits each month, shared dashboards and Loops, central billing and team controls - Pricing, Enterprise: custom. SSO and role based access, data residency options, custom integrations, dedicated onboarding - Company: AgentOS is a product of Devcore (devvcore.com) - Website: https://tryagentos.net - LinkedIn: https://www.linkedin.com/company/agentosai/ - Open source: the AgentOS plugin for Claude Code and Codex is at https://github.com/devvcore/agentos-skill ## Optional - [Why AI agents fail in production](https://tryagentos.net/site/insights/why-ai-agents-fail-in-production): the three infrastructure gaps behind most production agent failures - [What is a context layer (and a context lake)?](https://tryagentos.net/site/insights/what-is-a-context-layer): definition of a context layer and a context lake, how they relate to AI memory, RAG and MCP, and when a business needs one - [AI cost management](https://tryagentos.net/site/insights/ai-cost-management): why AI bills rise while per-token prices fall, what the main models cost in 2026, and 7 ways to cut AI spend - [AgentOS vs Claude Cowork](https://tryagentos.net/site/insights/agentos-vs-claude-cowork): Cowork does multi-step work for one person; AgentOS gives every AI tool the same company context - [AgentOS vs ChatGPT for business](https://tryagentos.net/site/insights/agentos-vs-chatgpt): ChatGPT is an assistant; AgentOS is the shared context layer ChatGPT and other AI tools connect to over MCP - [AgentOS vs Claude for business](https://tryagentos.net/site/insights/agentos-vs-claude): Claude memory stays inside Claude; AgentOS shares one company context with Claude, ChatGPT and Cursor - [AgentOS vs Zapier for AI work](https://tryagentos.net/site/insights/agentos-vs-zapier): how Zapier's automations and agents compare with AgentOS as the shared knowledge layer under all of a company's AI tools, including AI pricing, model choice and governance - [AgentOS vs Lindy](https://tryagentos.net/site/insights/agentos-vs-lindy): how Lindy's AI assistant compares with AgentOS, including memory, model choice, credit pricing and using both - [AgentOS vs Microsoft Copilot for business](https://tryagentos.net/site/insights/agentos-vs-microsoft-copilot): how Microsoft Copilot compares with AgentOS for companies that use more than one AI tool, including pricing, models, permissions and AI spend - [AgentOS vs Google Gemini for business](https://tryagentos.net/site/insights/agentos-vs-google-gemini): how Gemini in Google Workspace and Gemini Enterprise compare with AgentOS for companies that use more than one AI tool, including memory, models, pricing and AI spend - [AgentOS vs Notion AI](https://tryagentos.net/site/insights/agentos-vs-notion-ai): how Notion AI and its agents compare with AgentOS, including where company knowledge lives, connectors, models, credits pricing and using both - [AgentOS vs n8n](https://tryagentos.net/site/insights/agentos-vs-n8n): how n8n's node-based workflow builder compares with plain-language workflows in AgentOS, including who it suits, company knowledge, hosting, pricing and AI cost - [AgentOS vs Make](https://tryagentos.net/site/insights/agentos-vs-make): how Make's visual canvas for automations and AI agents compares with plain-language workflows in AgentOS, including who it suits, company knowledge, approvals, pricing and AI cost - [AgentOS vs Dust](https://tryagentos.net/site/insights/agentos-vs-dust): how Dust's platform for building and sharing AI agents on company data compares with AgentOS as a shared company memory for every AI tool, including knowledge, approvals, pricing and AI cost - [AgentOS vs Glean](https://tryagentos.net/site/insights/agentos-vs-glean): how Glean's enterprise AI search and agents compare with AgentOS for smaller teams, including getting started, permissions, MCP, pricing and AI cost - [AgentOS vs Perplexity](https://tryagentos.net/site/insights/agentos-vs-perplexity): how Perplexity's cited web research and business plans compare with AgentOS as a shared company memory for every AI tool, including company knowledge, automation, pricing and AI cost - [ChatGPT vs Claude for business](https://tryagentos.net/site/insights/chatgpt-vs-claude-for-business): how ChatGPT Business and Claude Team compare for a company on price, seat limits, training on business data, admin controls, connectors, memory, agents and spend controls, and why neither gives every AI tool one shared company context - [AI agents for small business: pick one job first](https://tryagentos.net/site/insights/ai-agent-for-small-business): what an AI agent does compared with a chatbot, good first jobs for a small business (lead follow-up, support, scheduling, weekly reports, meeting notes), how to pick the first job, what to check before buying, and where AgentOS fits. - [How to write an AI policy for a small team](https://tryagentos.net/site/insights/ai-policy-for-small-teams): the questions to ask when drafting an AI policy, five steps (what people already use, three information piles, approved tools on work accounts, human review before anything goes out, an owner and a 3-month review), and a free one-page template. - [ChatGPT connectors, explained](https://tryagentos.net/site/insights/chatgpt-connectors): what ChatGPT connectors (now called apps, inside plugins) connect to, how to set them up, Company Knowledge, custom MCP apps, permissions and training on data, and why connectors in one AI tool don't give Claude or Copilot the same company context - [AI for agencies](https://tryagentos.net/site/ai-for-agencies): how agencies use AgentOS so ChatGPT, Claude and their other AI tools share each client's context, with client call prep, Friday client recaps, proposals from past work and approval before anything goes to a client - [AI for operations](https://tryagentos.net/site/ai-for-operations): how operations teams at companies of 10 to 300 people keep ChatGPT, Claude and the AI tools each team picked on the same company context, with a morning brief, the weekly ops update, vendor follow-ups that wait for approval, new-hire answers and handoffs - [AgentOS vs Relevance AI](https://tryagentos.net/site/insights/agentos-vs-relevance-ai): how Relevance AI's platform for building teams of AI agents compares with AgentOS as a shared company memory for every AI tool, including knowledge, approvals, models, pricing and AI cost - [AgentOS vs Manus](https://tryagentos.net/site/insights/agentos-vs-manus): how Manus, a general AI agent that completes one-off tasks on its own cloud computer, compares with AgentOS as a shared company memory for every AI tool, including knowledge, control, automation, pricing and AI cost - [MCP is the front door](https://tryagentos.net/site/insights/mcp-is-the-front-door): how existing agents walk into the office - [llms-full.txt](https://tryagentos.net/llms-full.txt): expanded version of this file with FAQ and article summaries Free: $0, one hosted agent (coming soon), 200 monthly credits plus 300 signup credits in the first month. No card required. Hosted agents are coming soon: Pro includes ten; Team includes thirty. Purchased credits: $10 for 500, no expiry. Monthly credits do not roll over.