Launch HN：Rivet（YC W23）——在S3上扩展并编排智能体
Launch HN: Rivet (YC W23) – Scale and Orchestrate Agents on S3
我们发现了什么
方向观察：Launch HN：Rivet（YC W23）——在S3上扩展并编排智能体。原文包含第三方或历史项目线索，暂不能归属于本产品，需核对完整来源。
- 来源：Hacker News（发现于 2026-11-06）
- 证据等级：D · 包含历史项目、第三方案例或未来计划；不能作为当前项目收入证据。
- 商业模式：待核验
- 主题：AI Agent
- 初筛评分：20.6/100 · 收录 1 次
证据，比故事更重要。
规则清洗与初筛，未经人工商业核验。原文语境、实际客户和付费情况仍需自行验证。
引用与数字披露
来源类型（原作者自述／第三方测算／媒体转引）需采集端标注，本版尚未落字段。
- 作者
- 未标注
- 抓取日期
- 来源类型
- 未标注
- 币种
- 未标注
- 口径
- 未标注
- 披露主体
- 未标注
- 披露日期
- 未标注
中文辅助译文（全文）
HN 大家好，我们是 Rivet 的 Nathan 和 Nicholas（ https://rivet.dev ）——Rivet 是一款采用 actor 模型、用于智能体工作负载的快速、高密度且可扩展的编排器。它不会为每个智能体运行一个重量级沙箱，而是为每个智能体提供一个以 S3 为后端的轻量级 actor。actor 可通过长生命周期进程支持耗时较长的智能体回合，并提供用于保存上下文的内存状态、用于多人交互的 WebSocket 服务器、以 S3 为后端的持久化 SQLite 存储，以及空闲时的休眠机制。它采用了与 Cloudflare Durable Objects 类似的模型，但开源且支持自托管。这里有一份视频演示：https://www.youtube.com/watch?v=3Ev6I7DOV9c
2023 年参加 YC 时，我们正在为 Diep 和 Krunker 等多人游戏构建基础设施。这需要大力优化高吞吐量匹配、实时玩家消息传递和突发扩容。在此过程中，我们花了很多时间处理 Postgres 无法跟上吞吐量的工作负载。最初，我们基于 Redis 拼凑 Lua 脚本，但这种方式维护和升级起来过于麻烦。这促使我们扩展游戏服务器编排器，以支持我们如今称为 Rivet Actors 的技术：大量配备内存状态和持久化存储的轻量级工作进程。通过使用 actor，我们得以服务数千万名月活跃用户。
随着智能体日益流行，我们逐渐清楚，在沙箱中运行智能体效率低下。沙箱成本高、大部分时间闲置，而且启动缓慢。开发者开始使用 actor，因为 actor 的内存效率远高于沙箱（actor 的基线占用为 72 KB，而最小沙箱为 512 MB），启动速度也快得多（actor 的 p99 为 4.9 ms，而沙箱为 1.7 s）。例如，Amp 正在使用 Rivet 编排多人智能体。他们最初尝试基于 Cloudflare Durable Objects 构建，但由于平台限制和支持服务不响应，未能上线。他们在一个周末内迁移到 Rivet Actors，并部署到本地环境。Rivet 灵活的架构使他们可以根据自己的用例调整 Rivet，而不受框架或 Cloudflare Durable Objects 的内存、存储和运行时限制约束。
在底层，Rivet 以 S3 为后端，同时保持 SSD 级速度。为什么选择 S3？此前，Rivet 运行在 FoundationDB 上。然而，我们惊讶地发现，公司在 Rivet Actors 中存储的数据量比在 Postgres 中存储的数据量多出数个数量级，例如大型会话记录、智能体产物和完整的 POSIX 文件系统。随着数据增长，他们不得不开始花钱购买 SSD；这些 SSD 大部分时间处于闲置状态，存放着旧的会话记录。这促使我们更加坚定地采用 S3 作为主要存储介质，同时不牺牲性能。这意味着，存储在 Rivet 上的数据成本比存储在 EBS gp3 上低 10×，同时仍保持 SSD 级速度。事情并非直接将数据写入 S3 那么简单。对微小数据块进行大量 PUT 操作既缓慢又昂贵。因此，我们使用 SSD 层来优化速度和成本：
当你向某个 actor 的 SQLite 数据库写入数据时，只有在 3 个可用区中有 2 个的 SSD 已持有该数据后，写入才会得到确认。随后，数据会在后台批量同步到 S3。这意味着，S3 永远不会处于写入路径上，从而降低延迟和成本。读取数据或唤醒 actor 时，如果数据已在 SSD 中缓存，Rivet 就从 SSD 读取；否则回退到 S3。SSD 缓存可以按你的需求进行调优，为 actor 提供可配置的分层存储。这一架构使 Rivet 能够提供 1.07 ms 的持久写入（3 AZ，p99）、1.36 ms 的读取（p99），以及 138 ms 的对象存储读取（p99）。
我们投入了大量时间，确保 Rivet 可以在你需要的任何地方运行。自托管只需部署一个 Rust 二进制文件，唯一依赖项是 S3；Rivet Cloud 让你可以在 AWS 或 GCP 的任意区域部署专用集群；BYOC 则允许我们将 Rivet 部署到你的 VPC，而无需你自行运维。Rivet 在本地开发环境和生产环境中的运行方式也完全相同，因为 Rivet 是一款轻量级二进制程序，可以部署在任何能够使用 TypeScript 或 Rust 编写 Rivet Actors 的环境中。开箱即支持智能体（Pi Durable）、工作流、实时功能、多人交互、运行 AI 生成的代码、Durable Streams，以及与 Vercel 的 Eve 和 Turso 等工具的集成。
查看我们提供的全部指南，或让你的智能体查阅这些指南：https://rivet.dev/docs/#guides 现在就通过阅读快速入门指南（ https://rivet.dev/docs/ ）试用，或者让你的智能体执行：“运行 npx skills add rivet-dev/skills，然后构建一个多人聊天智能体并在本地运行。”我们很想了解你使用 Rivet 的体验并听取反馈！我们正大力投入，将 Rivet 打造为一种易于自托管、灵活且高效的智能体工作负载运行方式。GitHub: https://github.com/rivet-dev/rivet 架构：https://rivet.dev/docs/architecture/ 基准测试：https://rivet.dev/docs/benchmarking/ 自托管：https://rivet.dev/docs/deploy/self-host/
译文由上游机器翻译生成，可能有误；判断请以英文原文为准。
英文原文（来源本站未改写）
Hey HN, this is Nathan and Nicholas from Rivet ( https://rivet.dev ) – a fast, high-density, and scalable orchestrator for agentic workloads using the actor model.Rather than running a heavyweight sandbox per agent, each agent gets a lightweight actor backed by S3.Actors provide a long-lived process for long agent turns, in-memory state for context, a WebSocket server for multiplayer, durable SQLite storage backed by S3, and hibernation when idle.It's a similar model to Cloudflare Durable Objects, but it’s open source and self-hostable.Here’s a video walkthrough: https://www.youtube.com/watch?
v=3Ev6I7DOV9c When we went through YC in 2023, we were building infrastructure for multiplayer games like Diep and Krunker.This involved heavily optimizing high-throughput matchmaking, real-time player messages, and blitz scaling.Through that process, we spent a lot of time on workloads where Postgres couldn't keep up with our throughput.We started out by hacking together Lua scripts on top of Redis, but this became too cumbersome to maintain and upgrade.This led us to extend our game server orchestrator to support what we call Rivet Actors today: many lightweight workers with in-memory state and durable storage.By using actors, we were able to serve tens of millions of monthly active users.
As agents grew in popularity, it became clear that running agents in sandboxes is inefficient.Sandboxes are expensive, mostly idle, and slow to start.Developers started using actors because they are far more memory efficient (72 KB baseline for actors vs 512 MB for a minimal sandbox) and fast to start (4.9 ms p99 for actors vs 1.7 s p99 for sandboxes).For example, Amp is using Rivet to orchestrate multiplayer agents.They originally tried to build on Cloudflare Durable Objects, but couldn’t launch because of the platform’s limitations and unresponsive support.They migrated to Rivet Actors in a weekend and deploy on-prem.
Rivet’s flexible architecture lets them adapt it to their own use cases without being constrained by a framework or the memory, storage, and runtime limits of Cloudflare Durable Objects.Under the hood, Rivet is backed by S3 while maintaining SSD speeds.Why S3?Previously, Rivet ran on FoundationDB.However, we were surprised to find that companies are storing orders of magnitude more data on Rivet Actors than in Postgres, such as large session transcripts, agent artifacts, and full POSIX filesystems.As their data grew, they had to start paying for SSDs that sat mostly idle with old transcripts.This led us to double down on S3 as our primary storage medium without sacrificing performance.
This choice means that data stored on Rivet is 10× cheaper than on EBS gp3 while maintaining SSD speeds.It’s not as simple as writing data straight to S3.Lots of PUTs for tiny blobs of data are slow and expensive.Instead, we use an SSD tier to optimize speed and cost: When you write data to an actor’s SQLite database, the write is acknowledged once SSDs in 2 of 3 availability zones have it.Then, the data is batched to S3 in the background.This means that S3 is never on the write path, which lowers latency and cost.When reading data or waking an actor, Rivet reads from SSDs if already cached and falls back to S3 if not.
SSD caches can be tuned to meet your needs, giving you configurable tiered storage for your actors.This architecture lets Rivet provide 1.07 ms durable writes (3 AZ, p99), 1.36 ms reads (p99), and 138 ms reads from object storage (p99).We’ve spent a lot of time making sure that Rivet can run wherever you need it.Self-hosting requires deploying a single Rust binary with S3 as the only dependency, Rivet Cloud lets you deploy dedicated clusters on AWS or GCP in any region, and BYOC lets us deploy Rivet to your VPC without having to operate it yourself.
Rivet also runs identically in local dev as in production, since Rivet is a lightweight binary that runs anywhere Rivet Actors can be written in TypeScript or Rust.Out of the box, they support agents (Pi Durable), workflows, real-time, multiplayer, running AI-generated code, Durable Streams, and integrations with tools like Vercel’s Eve and Turso.See all of our available guides, or point your agent at them: https://rivet.dev/docs/#guides Try it out now, by reading our quickstart guides ( https://rivet.dev/docs/ ) or ask your agent: “Run npx skills add rivet-dev/skills, then build a multiplayer chat agent and run it locally.” We’d love to get feedback on your experience with Rivet!
We’re deeply invested in making Rivet an easy-to-self-host, flexible, and efficient way to run agentic workloads.GitHub: https://github.com/rivet-dev/rivet Architecture: https://rivet.dev/docs/architecture/ Benchmarks: https://rivet.dev/docs/benchmarking/ Self-hosting: https://rivet.dev/docs/deploy/self-host/
这条还缺什么证据？
下面每条都由本条已有字段推出（等级、理由、商业模式、来源次数、是否演示）， 本站不生成推测性结论；通用验证方法放在方法论页。
- 可核验的收入或付费证据查官网定价页与付费口径；第三方数据源（如 GetLatka）只作旁证，需标注来源与时点。
- 商业模式未定确认按席位／按用量／授权还是开源托管版收费；开源项目另查 LICENSE 与是否存在付费版。
- 只有单一来源找一手站点或其他渠道是否重复出现同一产品；社区热帖数量不等于商业进展。
通用验证清单（谁有这个问题／谁愿意付费／一个人能交付哪一小步）见我们的筛选方法。