菜单
Build an AI agent backend with persistent memory: one Rivet Actor per conversation, queued message handling, and streaming LLM responses as realtime events.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build a realtime chat room backend with Rivet Actors: one actor per room, SQLite-backed message history, and WebSocket broadcast to every connected client.
Build a collaborative text editor backend with Yjs CRDTs and Rivet Actors: per-document actors relay sync and awareness updates and persist snapshots.
Durable cron jobs with Rivet Actors: schedule.after and schedule.at timers survive restarts and crashes, plus re-arming recurring jobs and idempotent handlers.
Live cursors and multiplayer presence with Rivet Actors: per-connection cursor state, realtime updates over events or raw WebSockets, and throttling.
Pragmatic patterns for building multiplayer games: matchmaking, tick loops, realtime state, interest management, and validation.
Multi-tenant data isolation with one Rivet Actor per tenant: the actor key is the tenant id, so each tenant gets its own isolated dataset and migrations.
| name | ai-agent |
| description | Build an AI agent backend with persistent memory: one Rivet Actor per conversation, queued message handling, and streaming LLM responses as realtime events. |
IMPORTANT: Before doing anything, you MUST read BASE_SKILL.md in this skill's directory. It contains essential guidance on debugging, error handling, state management, deployment, and project setup. Those rules and patterns apply to all RivetKit work. Everything below assumes you have already read and understood it.
If you need a reference implementation, read the raw working example code in these templates:
Patterns for building AI agent backends with RivetKit, where each conversation is one Rivet Actor that owns its memory, its message queue, and its streaming output.
Start with one of the working examples on GitHub and adapt it. The sections below describe the flagship ai-agent example unless a variant is called out explicitly.
| Variant | Starter Code | Use When |
|---|---|---|
| Queue-driven AI SDK agent | GitHub | You want a streaming chat agent where each conversation keeps its own persistent memory and processes one message at a time. |
| Sandbox coding agent | GitHub | The agent should run a coding agent (Codex by default) inside an isolated sandbox via Docker, Daytona, or E2B. |
| Durable streams agent (experimental) | GitHub | You want replayable, restart-safe prompt and response delivery through durable streams instead of actor state and events. |
Use one actor per conversation, keyed by a conversation or agent id (see Actor Keys). The agent actor's persistent state is the conversation memory: in the ai-agent example, messages and status live in JSON actor state and survive sleep and restarts with no external database. Every model call rebuilds the prompt from c.state.messages plus a system prompt, so memory and inference input are the same data.
| Variant | Where Memory Lives | Persisted State Fields |
|---|---|---|
ai-agent | JSON actor state | messages, status |
sandbox-coding-agent | JSON actor state plus the sandbox ACP session | messages, status, sessionId |
experimental-durable-streams-ai-agent | Durable streams; the actor stores only its conversation id and a read cursor | conversationId, promptStreamOffset |
In the ai-agent example, the client pushes user input onto the agent's message queue with agent.connection.send("message", { text, sender }). This is a queue push, not an action call. The actor's run hook (see Lifecycle) consumes the queue serially with for await (const queued of c.queue.iter()).
Serial queue consumption is the per-conversation concurrency guarantee: at most one in-flight model call per actor, with no extra locking. The status field (thinking while a model call is in flight) is UI signal only; the run loop is the actual lock. The loop also checks c.aborted inside the token stream so shutdown exits gracefully.
| Variant | Message Ingress | Serialization Guarantee |
|---|---|---|
ai-agent | message queue pushed via connection.send | run hook pops one queued message at a time with c.queue.iter(). |
sandbox-coding-agent | sendMessage action, no queue | Each call awaits the sandbox round trip before broadcasting the result. |
experimental-durable-streams-ai-agent | Durable prompt stream long-polled from onWake | promptStreamOffset is persisted per chunk, so restarts resume without reprocessing prompts. |
The ai-agent actor broadcasts a response event for every model text delta. The payload carries messageId, the per-token delta, the cumulative content, and a done flag (plus error on failure), so clients can either append deltas or idempotently replace the message by messageId using content. The example frontend replaces by messageId, which tolerates dropped events. The terminal broadcast has an empty delta, the full content, and done: true.
Because the assistant message object lives in c.state.messages and is mutated in place during streaming, partial content persists if the actor restarts mid-stream. The example broadcasts once per AI SDK delta with no throttling; batching or throttling deltas is a recommended extension for high-traffic deployments, not something the example implements.
Variant differences: sandbox-coding-agent sends a single response broadcast with done: true after the sandbox finishes (no incremental streaming), and experimental-durable-streams-ai-agent appends per-token chunks to a durable response stream, then broadcasts responseComplete or responseError.
| Topic | Summary |
|---|---|
| Topology | agentManager["primary"] singleton directory plus one agent[agentId] actor per conversation. |
| Ingress | Client pushes AgentQueueMessage payloads onto the agent's message queue with connection.send. |
| Streaming | One response broadcast per model delta, terminal broadcast with done: true. |
| Memory | Full transcript and status in JSON actor state; no external database. |
The manager creates AgentInfo records and warms each agent through actor-to-actor communication: createAgent calls c.client<typeof registry>(), then client.agent.getOrCreate([info.id]) and awaits getStatus() so the conversation actor exists before the client connects. The sandbox variant extends this topology with a codingSandbox actor that shares the agent's key (codingSandbox.getOrCreate([c.key[0]])), so the agent-to-sandbox mapping is implicit in the key space.
Actors
Key: agentManager["primary"]
Responsibility: Directory actor. Creates AgentInfo records, lists agents, and warms each agent actor via c.client().
Actions
createAgentlistAgentsQueues
State
agentsKey: agent[agentId]
Responsibility: One actor per conversation. Holds the full message history and status, consumes queued user messages in its run loop, calls the model via the AI SDK, and broadcasts streaming deltas.
Actions
getHistorygetStatusQueues
messageEvents
messageAddedstatusresponseState
messagesstatusLifecycle
sequenceDiagram
participant C as Client
participant AM as agentManager
participant A as agent
participant LLM as Model API
C->>AM: createAgent(name)
AM->>A: getOrCreate([info.id]) + getStatus()
AM-->>C: AgentInfo
C->>A: connection.send("message", {text, sender})
Note over A: run loop pops queue via c.queue.iter()
A-->>C: messageAdded (user message)
A-->>C: messageAdded (assistant placeholder)
A-->>C: status (thinking)
A->>LLM: streamText(system prompt + history)
loop each text delta
LLM-->>A: delta
A-->>C: response {messageId, delta, content, done: false}
end
A-->>C: response {delta: "", content, done: true}
A-->>C: status (idle)
The examples ship without auth so they stay minimal. Apply this baseline before exposing an agent backend.
OPENAI_API_KEY (or ANTHROPIC_API_KEY) is read by the AI SDK inside the actor process. The key never reaches the browser; clients only talk to the actor over RivetKit. The sandbox variant forwards keys into the sandbox env, never to the client.onBeforeConnect or createConnState checks with scoped tokens as a recommended extension. See Authentication.text. Enforce payload size limits, schema validation, and per-connection rate limits as a recommended extension.sender field verbatim. Bind sender identity to the authenticated connection instead.