# Introduction > Ryph runs coding agents on your own infrastructure, and makes them safe enough to hand real work. Ryph is an open-source platform for running coding agents on infrastructure you control. You give an agent a task from a GitHub, GitLab or Radicle thread, a chat, a schedule or an alert. It works in a sandbox with a checkout of your code, and hands back a pull request, an issue, a page or an answer, wherever you asked. ![A task in Ryph's web app. The list of tasks is on the left. In the middle is Ada's run: it reproduced a bug in the playground, ran commands and wrote tests, with every step in the transcript. On the right are the run's actions: a reply on the pull request, the patch it opened, and the checks, all eight passed.](https://ryph.ai/docs/run-page.jpg) *A run in Ryph's web app. Every step the agent takes is in the transcript, and what it did outside the sandbox, from review replies to patches and checks, is on the right.* ## Put an agent on call Point your alerts at Ryph, and every alert opens a thread in your incident channel with an agent already in it. Within a minute it has read the alert, queried your dashboards, gone through recent commits and your runbooks, and posted what it found. Whoever is on call mentions it to steer it. Once it finds the cause, it can write the fix, run your checks and open a pull request for your team to review. When the alert resolves, it wraps up in the same thread. - [Set up incident response](https://ryph.ai/docs/incident-response.md): Run Ryph with Docker Compose and put an agent on call. An alert fires, the agent investigates in Discord, Slack, Telegram or Zulip with your team, and proposes a fix as a pull request. [Chat & Responses](https://ryph.ai/docs/chat.md) explains how agents work in chat, and how an alert brings one in. ## Give your team an agent they can trust Put an agent in your company chat, and anyone in the channel can hand it work. Engineers ask how something works. Someone from support pastes a screenshot of a broken button, and the agent reproduces it in a browser, fixes it, and opens a pull request with before and after screenshots. Someone from finance asks how signups changed since the pricing update, and gets a page with a chart. That's safe to hand a whole company because the agent holds no keys. An agent that reads a hostile issue, web page or chat message can be talked into anything, so Ryph assumes it might be. Git, model providers and tools are reached through Ryph's gateways, which check every request. The agent's work leaves the sandbox as a patch, Ryph opens the pull request, and an engineer reviews every change before it ships. - [Give your team a secure agent](https://ryph.ai/docs/team-agent.md): Put an agent in your company chat that answers questions about your code, fixes what people report and builds reports from your data. It can't push to main, so every change waits for your team's review. [Secure forge interactions](https://ryph.ai/docs/secure-forge-interactions.md) explains how agents ship pull requests and file issues without a git key. ## Features Both run on the same pieces as everything else in Ryph. Agents can be confined to the hosts on your allowlist, run your checks against the commit they'll ship, and start from a machine with your toolchain and a warm build. You can watch them click through your app in their browser, or open their dev server yourself. Ryph runs as one binary on your laptop, Docker Compose on a server, or Kubernetes for a team, and your code stays with you. - [Secure forge interactions](https://ryph.ai/docs/secure-forge-interactions.md): Agents clone, ship pull requests, file issues and review code without ever holding a git key. Every request goes through Ryph’s forge, which checks it against what the agent may do. - [Egress confinement](https://ryph.ai/docs/egress-confinement.md): Runs and environment builds reach the internet only through Ryph’s egress proxy, and only the hosts on your allowlist. - [Tool proxy](https://ryph.ai/docs/tool-proxy.md): Agents use Linear, Sentry, Grafana and other MCP servers through Ryph, which keeps the keys and checks every call against the tools the agent was given. - [Model proxy](https://ryph.ai/docs/model-proxy.md): Agents call Anthropic, OpenAI and any OpenAI-compatible model through Ryph, which keeps the keys, holds each run to its models and counts what it costs. - [Checks](https://ryph.ai/docs/checks.md): Agents run your checks until they pass. Passes carry forward, so the pull request opens green. - [Environments](https://ryph.ai/docs/environments.md): Each repo gets a machine with its tools, dependencies and a warm build, so runs start working right away. - [Browser use](https://ryph.ai/docs/browser.md): Agents click through your app in a real browser while you watch live, and post their screenshots to pull requests, issues and chat. - [Artifacts](https://ryph.ai/docs/artifacts.md): Reports, comparisons and overviews come back as pages with charts and diagrams, updated as you ask for more. - [Previews](https://ryph.ai/docs/previews.md): Agents run your app’s dev server in their sandbox, and you click through it in your own browser while they work. Only people who can see the run get in. - [Chat & Responses](https://ryph.ai/docs/chat.md): Mention an agent in Slack, Zulip or Telegram, or let an alert bring one into your incident channel. - [Semantic memory](https://ryph.ai/docs/semantic-memory.md): Agents keep what they learn about your code and your team. Ryph checks each lesson on its way in, and later runs start with what fits their task. - [Automations](https://ryph.ai/docs/automations.md): Start runs on a schedule, or when Sentry, Grafana or any other service sends a request. The instructions stay fixed, and what came in rides along as context. ## Get started [Get started](https://ryph.ai/docs/getting-started.md) points you to a guide, or to the ways to run Ryph for your team. [Core concepts](https://ryph.ai/docs/overview.md) explains agents, tasks, runs and patches.