# plutonium.io > plutonium.io Reactor runs AI agents for a business. A loop is one agent with one job: you set what it may read, do and spend, and Reactor holds every run to that. Reactor search is text and semantic search over your documents and records. Every page of this site has a markdown twin. Add `.md` to a page's address (`/docs/guide/tools` is `/docs/guide/tools.md`, and the home page is `/index.md`), or send `Accept: text/markdown` to the page's own address. [/llms-full.txt](/llms-full.txt) is the whole documentation in one file. To work in an account, and not only read about it: - From a terminal, install `rxr` with `curl -fsSL https://plutonium.io/install.sh | sh`, then read `rxr guide`: [The Command Line](/docs/guide/command-line.md). - From an AI tool that speaks MCP, connect to `https://mcp.plutonium.io/mcp`: [Connect an AI tool](/docs/guide/connect-an-ai-tool.md). The server's prompts `new_loop` and `change_loop` give the steps in order. - To let a loop read a file or run a command on the person's own machine (a host tool, `rxr.host.yml`, `rxr serve`): [Tools on Your Own Machine](/docs/guide/your-machine.md). - To start a run from an event on the person's machine (a changed file, an interval, cron, a git hook): [Triggers and Schedules](/docs/guide/triggers-and-schedules.md), "From your machine". ## Site - [Home](/index.md): What Reactor is, what a loop does, and how you start - [Pricing](/pricing.md): What a run, a search and the Pro plan cost ## Documentation - [Documentation](/docs.md): How Reactor works, and how to build on it ## Reactor loop - [Getting Started](/docs/guide/getting-started.md): From signing in to your first run - [What Loops Are For](/docs/guide/what-loops-are-for.md): The jobs a business hands a loop — answering, qualifying, booking, triage, refunds, expenses, intake, digests and more — with a person in the conversation or with nobody at all - [Core Concepts](/docs/guide/concepts.md): The nouns Reactor is built from - [Building a Loop](/docs/guide/building-a-loop.md): Write a loop with LoopAssistant or by hand, save it as a draft, try it in My conversations, and publish it - [Testing a Loop](/docs/guide/testing-a-loop.md): Try a draft in My conversations, and declare test cases that must pass before a version can publish - [Agents](/docs/guide/agents.md): The workers a loop runs — their instructions, tools, model and role — and how to add your own - [Tools](/docs/guide/tools.md): The built-in tools a run can call, and how to give your loops your own HTTP endpoints — installed once, used by many loops - [Permissions and trust](/docs/guide/permissions-and-trust.md): What a run may do, who decides, what each built-in tool needs, the Rule of Two, and what a trusted source changes - [Connections](/docs/guide/connections.md): The services plutonium.io reaches as you — connect one with an API key or a sign-in, see how each stands, pause or remove it - [Asking the User](/docs/guide/asking-the-user.md): How a loop asks its user a question, collects details on a form that no model reads, checks an email address, and asks before it acts - [Collections and Outputs](/docs/guide/collections-and-outputs.md): Where a loop keeps what it learns — collections of records — and where it sends a result when a run ends - [Pages](/docs/guide/pages.md): Markdown pages that show your collections — written, previewed and published like a loop - [Letting a Loop Search](/docs/guide/search-indexes.md): Name a search index in a loop, what searching lets the loop's agents do, and how the loop's visitors search - [Triggers and Schedules](/docs/guide/triggers-and-schedules.md): Start runs without a person — on a schedule, from a signed webhook, from a new record, from a page button, or from your server - [Identity and Keys](/docs/guide/identity-and-keys.md): How a loop knows who its user is, which sites may load it, and the API keys your server uses - [Embedding the Chat](/docs/guide/embedding-the-chat.md): Put a published loop's chat on your own web page with one iframe, for anonymous visitors or for users your site signs in - [Connect an AI tool](/docs/guide/connect-an-ai-tool.md): Use plutonium.io from an AI tool such as Claude Desktop — a remote MCP server you connect by signing in, and disconnect in Settings - [The Command Line](/docs/guide/command-line.md): rxr, the Reactor command line — write a loop in a file, try the draft, test it, publish it and run it from a terminal, as a person or as an AI agent - [Tools on Your Own Machine](/docs/guide/your-machine.md): Host tools — let a loop read a file or run a command on your own machine, through rxr, and only what a file on that machine allows - [Operating Loops](/docs/guide/operating-loops.md): Watch runs live, stop one, take over a conversation, answer the decisions a loop waits on, and read each loop's numbers - [Money, Limits and Members](/docs/guide/money-limits-members.md): The prepaid wallet and the four budgets every run is held to, the limits on who may start runs, and the people in your account ## Reactor search - [Search Indexes](/docs/search/overview.md): Search indexes over your website, your files or a collection, searched by you, your loops, your visitors and your servers - [Writing a Search](/docs/search/writing-a-search.md): The four ways a search matches — words, an exact phrase, words with a typo, a pattern — words or meaning, the reranking model, and what each searcher may send ## API Reference - [API Overview](/docs/api/overview.md): The run API your server or page calls, how it authenticates, and what its limits answer - [Identity](/docs/api/identity.md): The doors that give one of your users a token for a loop, and your own OpenID issuer - [Runs](/docs/api/runs.md): Start a run of a published loop, read it, talk to it and follow it - [Search API](/docs/api/search.md): Search your indexes from your server with a search key, or search what a loop's published version searches - [Collections](/docs/api/collections.md): Read the records of a collection from your own server, under an API key - [Webhooks](/docs/api/webhooks.md): Start a run with a signed request, and receive what a loop sends when a run ends ## Optional - [Privacy Policy](/privacy.md) - [Terms](/terms.md)