Always spell the product name agentOS, never AgentOS; do not alter type identifiers such as AgentOSActorConfig. agentOS owns the runtime, kernel, VFS, language execution, registry packages, agentOS client APIs, docs, and publish machinery. agentOS Exec is the JavaScript, TypeScript, and Python execution surface of agentOS. - Keep agentOS product versions pinned at 0.0.1 in committed files. Release workflows apply real versions transiently with scripts/publish; never commit release-version rewrites. - agentOS-owned npm packages must use the @rivet-dev/agentos-* namespace. Registry software packages…
4.9k43d agoReviewMountCreate a free account to mount
Generate agentOS marketing/launch graphics (launch & social heroes, code-snippet cards) from the committed generators in docs-internal/graphics. Use when asked to make, update, or render an agentOS launch image, social image, "agentOS Apps" graphic, or technical code-snippet image.
4.9k43d agoReviewMountCreate a free account to mount
The Rust sidecar implements the kernel: virtual filesystem, process table, socket table, pipe/PTY management, and permission system. Guest code sees a self-contained OS and must never interact with the host directly. The kernel orchestrates three execution environments: ALL guest code MUST execute inside the kernel with ZERO host escapes. No runtime may spawn unsandboxed host processes, touch real host filesystems, open real network sockets, or call real Node.js builtins. Every syscall goes through the kernel. This is the single most…
4.9k43d agoReviewMountCreate a free account to mount
Rules for the docs in this repo. These pages are not rendered here — they are published on rivet.dev by the rivet-website repo, which symlinks this directory in. Everything below exists so a page written here renders correctly there. The website links docs/content into its content collection, so only real pages belong under content/. Anything else (scripts, fixtures, notes) goes elsewhere in the repo or it will be published as a docs page. Every page needs title and description. Both…
4.9k43d agoReviewMountCreate a free account to mount
- Client packages must stay same-version with the sidecar: assert the single protocol version integer, and do not add wire back-compat, runtime negotiation, or converters. - Generated client layers return raw generated protocol types. The embedded AgentOs facade is publicly exported from @rivet-dev/agentos-core. - Generic agentos clients must stay application-agnostic and forward only the sandbox protocol. - agentos packages must never depend on agent-os packages; dependency direction is strictly agent-os to agentos and must be CI-enforced after the split. -…
4.9k43d agoReviewMountCreate a free account to mount
Rules for the Agents docs in this repo. These pages are not rendered here. They are published on rivet.dev by the website repo. .github/workflows/docs-sync.yml copies this directory and examples/ into the website's vendor/agents/ on every merge to main. Everything below exists so a page written here renders correctly there. Sandbox Agent's own docs (sandboxagent.dev) live in sandbox-agent/docs/ and follow different rules. Nothing in this file applies to them. The website links content/ into its content collection, so only real pages…
1 project uses a version of this
1.6k10mo agoReviewMountCreate a free account to mount
- Use https://rivet.dev/llms.txt as the canonical documentation index for future RivetKit work. - App-defined RivetKit actors are a required Dynamic Apps capability. Preserve and verify actor deployment, state, actions, events,…
Deploy a Docker image to a Rivet Cloud cluster through the Rivet MCP server, or roll a cluster back to an earlier build. Use when asked to deploy, ship, release, or roll back an app on a Rivet cluster and a shell with Docker is available.
4918d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.