Manage stateful actors
Maintain conversation history across agent sessions using persistent memory.
Build stateful backends and secure sandboxes for AI coding agents with these verified Agent Skills.
Official Agent Skills published by Rivet dev
Build stateful AI integrations using actors and isolated workspaces. Use these skills to implement real-time collaboration, durable scheduling, and secure multi-tenant data architecture.
Maintain conversation history across agent sessions using persistent memory.
Implement Yjs and CRDTs for multiplayer editing and cursor tracking.
Execute code in isolated Wasm environments with full filesystem access.
Official Agent Skills published by Rivet dev.
Equips AI agents with persistent, isolated workspaces featuring a full filesystem, process execution, and networking via a lightweight in-process OS.
Build production-grade AI agent backends featuring persistent conversation memory, serial message queuing, and real-time streaming responses.
Builds scalable, realtime chat room backends using room-scoped Rivet Actors and SQLite-backed message history.
Add Rivet dev Skills to agents that support the Agent Skills format, including Claude, Claude Code, Codex, and OpenCode. Install manually from source, or use MCP Market Hub to sync and share them with your team.
Add official skills once, keep them current across your agents, and share the same skill set with your team.
Prefer manual control? Download the skills from source, then follow the install guide for your agent.
rivet-dev/skillsReal workflows powered by Rivet dev skills.
Build a collaborative code editor
Enable multiple users to edit code simultaneously with real-time CRDT synchronization.
Orchestrate sandboxed coding agents
Run agents in secure E2B or Docker containers using a universal API.
Deploy air-gapped AI infrastructure
Install self-hosted orchestration in private VPCs with no outbound telemetry.
Verified, first-party skills from other brands you know.