@xiaomovps: I deployed PI Durable directly to CloudFlare, achieving one-click deployment, and fully utilizing free resources Becaus…

X AI KOLs Timeline Tools
cloudflare durable-objects agents one-click-deployment open-source serverless

Summary

作者将 PI Durable 项目直接部署到 Cloudflare，利用 Workers、Durable Objects、SQLite 存储等免费资源实现一键部署与开源的个人 Agent 方案，支持自定义 API 端点与任务唤醒。

I deployed PI Durable directly to CloudFlare, achieving one-click deployment, and fully utilizing free resources🔥 Because Cloudflare natively supports PI Durable, and it even has its own project PI harness I wondered if I could use Cloudflare's free resources to build a PI Durable project, enabling free one-click deployment And I actually pulled it off—the solution I used: 1. Workers: Run the Agent backend, handle API requests, and call AI models 2. Durable Objects: Maintain Agent instances, persist sessions and task states 3. SQLite Storage: Built-in database for Durable Objects, saving chat history, model configs, and task data—no need to create a separate D1 4. Static Assets: Host frontend HTML, CSS, JavaScript, and UI resources 5. Workers Builds: Connect to GitHub for automatic code building and deployment 6. Variables & Secrets: Securely store environment keys like ACCESS_TOKEN 7. Durable Object Alarms: Schedule wake-ups for the Agent to execute delayed tasks and reminders On top of that, I set it up to allow custom API endpoint configs—common ones like OpenAI and Anthropic protocols are all supported The only thing to watch out for: If you're using a paid tier for the corresponding service, keep an eye on your billing—don't expose it publicly, or you risk getting hit with usage fees. But if you're on the free tier, there's no such risk
Original Article
View Cached Full Text

Cached at: 10/11/26, 09:17 PM

I deployed PI Durable directly to CloudFlare, achieving one-click deployment, and fully utilizing free resources🔥

Because Cloudflare natively supports PI Durable, and it even has its own project PI harness

I wondered if I could use Cloudflare’s free resources to build a PI Durable project, enabling free one-click deployment

And I actually pulled it off—the solution I used:

  1. Workers: Run the Agent backend, handle API requests, and call AI models

  2. Durable Objects: Maintain Agent instances, persist sessions and task states

  3. SQLite Storage: Built-in database for Durable Objects, saving chat history, model configs, and task data—no need to create a separate D1

  4. Static Assets: Host frontend HTML, CSS, JavaScript, and UI resources

  5. Workers Builds: Connect to GitHub for automatic code building and deployment

  6. Variables & Secrets: Securely store environment keys like ACCESS_TOKEN

  7. Durable Object Alarms: Schedule wake-ups for the Agent to execute delayed tasks and reminders

On top of that, I set it up to allow custom API endpoint configs—common ones like OpenAI and Anthropic protocols are all supported

The only thing to watch out for: If you’re using a paid tier for the corresponding service, keep an eye on your billing—don’t expose it publicly, or you risk getting hit with usage fees. But if you’re on the free tier, there’s no such risk

Project address:

都是同一队列里面 然后分批唤醒

差不多 而且用的都是免费资源 一键部署

完全没有问题 绝对够一个人用

Similar Articles

@jiangkoumo_: Pi officially published a tutorial on building a multi-user Agent on Cloudflare Durable Objects. A single Durable Object corresponds to one session, with state stored in the built-in SQLite. Multiple users can share the same link to join the same session and chat collaboratively…

X AI KOLs Timeline

Pi officially published a tutorial on building a multi-user Agent on Cloudflare Durable Objects: a single Durable Object maps to one session, state is stored in built-in SQLite, and it supports multiple users sharing a link to chat collaboratively, as well as scheduled wake-up tasks. The tutorial also demonstrates an isolated design for session retrieval, idempotent request handling, and a mechanism for sharing a single alarm across multiple tasks.

@yibie: https://x.com/yibie/status/2108478625653862637

X AI KOLs Timeline

Armin Ronacher details how Pi Durable enables agent processes to resume from the point of interruption after a crash: persistence is achieved through an "effect sandwich" (intent, execution, result storage) rather than event sourcing, combined with a versioned document store to manage agent application state, supporting deployment to platforms such as Vercel, Cloudflare DO, and E2B.

@realchendahuang: I feel that everyone is still using less than 1% of Cloudflare's capabilities. It now has way too many features. Object storage: use R2. Backend API: use Workers. AI gateway: use AI Gateway. Heavy computation: use Containers. Cache: use KV. Database...

X AI KOLs Timeline

This tweet introduces various development features provided by Cloudflare, including object storage R2, backend API Workers, AI gateway AI Gateway, containers, cache KV, database D1, and PostgreSQL connection HyperDrive, emphasizing their low cost, rich features, and generous free tier.