Comments URL: https://news.ycombinator.com/item?id=49161336

Points: 2

# Comments: 0

The first two games are here: Poker - https://apps.apple.com/us/app/airplane-mode-poker/id67912479... https://play.google.com/store/apps/details?id=de.testco.airp... Liar's Dice https://play.google.com/store/apps/details?id=de.testco.airp... [iOS still in review]

BLE was the choice to have it work cross-platform and support multiple players. There is no Internet access and there is no analytics or app tracking.

It costs $2.99 as a one time unlock to host and $0 to join a game.

Thoughts on other games?

Comments URL: https://news.ycombinator.com/item?id=49161326

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49161319

Points: 1

# Comments: 0

You will be surprised how many sites allow all robots, but then block crawlers

Comments URL: https://news.ycombinator.com/item?id=49161193

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49160992

Points: 1

# Comments: 2

The idea to build Mirall was born at the Mallorca Film Festival. Companies and individuals in the movie industry often have the challenge to transfer large data files during the post production phase of a movie while large production studios often offer their own file transfer solutions. Smaller companies or individuals are often relying on consumer grade third party services, usually this is not allowed because of the potential of data leaks. Somehow it has become a complex problem to transfer large files over the internet. I overheard conversations where this was discussed and thought to myself that I might be able to solve that problem. Having used the Keet app and with some basic understanding of what the Pear framework is able to offer from a capability perspective, I thought I might give it a try.

Over the past four months I've been busy building this app with a high focus on ease of use and security. Now it is out there. The app is open source and free to download and use. I hope it solves a problem for many of you out there. Please give it a try and let me know if it works for you or where to improve.

Oliver

Comments URL: https://news.ycombinator.com/item?id=49160851

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49160681

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49160674

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49160540

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49160455

Points: 1

# Comments: 0

I’m Dallin, building Keystroke with my co-founder Blake. Keystroke is a recent pivot from Buster, our original YC W24 company.

Keystroke lets you build agents and durable workflows as TypeScript in your own repo, then deploy them to a web application where your team can use them. Our repo (ELv2 licensed) is here: https://github.com/keystrokehq/keystroke.

At Buster, we spent a lot of time building internal agents and automations. We used visual platforms like n8n and Zapier, as well as code-first tools like Trigger.dev, Mastra, and several of Vercel’s open frameworks. We genuinely liked many of them, but kept encountering two different problems:

1. Visual platforms gave us integrations, credentials, hosting, and an app the rest of the team could use, but became difficult to test, review, and debug as our systems grew.

2. Code-first tools gave us the flexibility of ordinary TypeScript and worked well with coding agents, but left us building the UI, runtime, permissions, credentials, and operational tooling ourselves.

So, we started building the thing we wish existed: a code-first framework that made it easy to build complex agents and AI systems, with a web app for teams to collaborate on top. We liked it so much that we decided to pivot away from Buster and focus on building Keystroke full time.

With Keystroke, I was able to rebuild our W24 idea (an AI data analyst) in ~5 minutes. I pointed Cursor at our old Buster repo and it was able to:

- spin up a local Keystroke project

- rebuild the OG Buster agent w/ memory, its own file system, etc

- connect our Postgres DB, PostHog, Metabase, and Slack

- build skills for using each of the data sources

- explore our DB and add schema docs to the file system

- build a workflow to keep schema docs synced

- name the agent "Delbert"

- then pushed him up to the Keystroke app

Since then, “Delbert” has been answering ad-hoc questions for me in Slack on a regular basis. He builds me metabase dashboards when I need them. He sets his own triggers, reviews key metrics periodically, and pings me in Slack if anything looks off.

In Keystroke, workflows are ordinary async TypeScript: a `for` loop is an actual `for` loop, inputs use Zod schemas, and everything you build can be tested with Vitest. Our managed runtime makes workflows durable across errors, sleeps, approval steps, and process restarts.

Agents wrap Vercel’s AI SDK and can use workflows, actions, other agents, MCP servers, and integrations as tools. They also include memory, a persistent filesystem, web search, triggers, and optional VM sandboxes.

Deployed agents and workflows instantly appear in the web app with a chat UI, workflow visualizations, input forms, sharing, credential management, integrations, and logs.

The entire platform was built from the ground up with coding agents in mind. Your coding agent can use the CLI to scaffold a local directory with a Keystroke project and an AGENTS.md. Then, it can build whatever agent or AI system you want, search our docs, run tests, and push what you build up to the Keystroke platform.

We plan to make money from our cloud offering, which has a free plan and usage-based pricing.

Our docs are here: https://keystroke.ai/docs.

You can watch a quick demo of Keystroke here: https://supercut.ai/share/keystroke/zeor1pD0bNlSTOuLUWmRBT?v....

You can try on cloud for free at: https://keystroke.ai/.

We’d especially appreciate feedback from people who have maintained agents and AI systems in visual tools or code-first frameworks. Where does this approach seem useful, and where are we rebuilding something that already works well elsewhere?

Comments URL: https://news.ycombinator.com/item?id=49160376

Points: 1

# Comments: 0

I got here after talking to multiple accountants and hearing them struggle to use Claude, Codex, Hermes and OpenClaw. The difficulties they had were classic:

1. QBO and Xero MCPs are brittle and allow limited access 2. They were only able to figure out how to run these locally 3. LLMs not being good at math 4. Configuring client memory

Coding agents disguised as one that does accounting felt like a simple yet powerful idea as a solution:

1. We connect to QBO and Xero using API instead of MCP and make it easy for multiple accounts connection 2. We deploy all client files along with `pi --rpc` in a sandbox so all can work on the cloud 3. A coding agent can simply write code for deterministic computations and run tests to catch inaccuracies 4. Each chat made progressively gets stored in the persistent sandbox meaning that agent can search through older conversations to look into its memory

I had to rebuild some of the architecture here several times as it required building a durable, persistent cloud coding agent essentially. Each client is configured almost as a repo/filesystem of its own that lives there forever, including the agent chats made by the users.

Stack is

- django for backend - modal for sandboxes - streaming uses two paths (1) for livestreaming (2) for durable background ones. Both use Cloudflare durable objects - frontend in vite - agent is a fork of pi - no MCP usage at all. For OCR, memory search, IRS docs search and further things, there is an embedded cli called `tlmc` that agent is encouraged to use in its system prompt

HN is not the right place to launch an accounting product however I thought the way this is built might be relevant to cloud agents and how to architect them.

Please let me know any feedback, requests and most of all any brutal feedback!

Comments URL: https://news.ycombinator.com/item?id=49160189

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49159964

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=49159763

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=49159705

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49159657

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=49159655

Points: 2

# Comments: 0

I built LaunchDaddy, a platform for discovering and launching new products.

I’m currently working on another product and want to stay focused on one direction, so I’m looking for someone who wants to acquire LaunchDaddy and continue building it.

The project includes: - LaunchDaddy brand and domain - Existing codebase - Product launch platform - All existing assets - All Social Media Accounts

I believe there is still room to build something interesting here for someone who wants to focus on the product launch space.

If you’re interested, feel free to reach out:

X/Twitter: https://x.com/heyalizaid

Thanks! Ali

Comments URL: https://news.ycombinator.com/item?id=49159640

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49159540

Points: 4

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49159490

Points: 1

# Comments: 0