The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Cpdown – Copy any webpage/YouTube subtitle as clean Markdown(LLM-ready)
TL;DR: I built a Chrome extension that copies webpage content or YouTube subtitles as clean, clutter-free Markdown with one click (or a shortcut). It even shows the token count, making it super handy for LLM prompts!<p>Hi, HN!<p>I often copy information from the web into my notes (Obsidian) or to feed context to LLMs for summaries/translations. So I built cpdown, a browser extension for this.<p>cpdown lets you convert any webpage/youtube subtitle into clean Markdown and copy it to your clipboard with a single click (or a keyboard shortcut).<p>Here are the key features:<p>* Intelligent Content Extraction: Uses Mozilla's Readability or Defuddle (by the Obsidian devs!) to strip away ads, sidebars, and other noise, focusing only on the main article content.
* Clean Markdown Conversion: The extracted HTML is then neatly converted to Markdown using the Turndown library.
* Token Count for LLMs: It calculates and displays the token count of the copied text using tiktoken. This is super handy for knowing if you're within limits before pasting into LLMs like ChatGPT or Claude.
* YouTube Transcript Copying: On YouTube video pages, it can copy the full transcript in Markdown format, automatically adding the video title as an H1 header.
* Customizable Options: You can choose your preferred content extractor (Readability/Defuddle), opt to wrap copied content in a code block, and more.<p>cpdown is completely free and open-source, built with WXT, React, and TypeScript.<p>You can grab it from the Chrome Web Store or check out the source code on GitHub. I'd love to hear your feedback, feature requests, or any suggestions!<p>* Chrome Web Store: <a href="https://chromewebstore.google.com/detail/cpdown/knnaflplggjdedobhbidojmmnocfbopf" rel="nofollow">https://chromewebstore.google.com/detail/cpdown/knnaflplggjd...</a>
* GitHub: <a href="https://github.com/ysm-dev/cpdown">https://github.com/ysm-dev/cpdown</a><p>Thanks for checking it out!
Show HN: String Flux – Simplify everyday string transformations for developers
I built <a href="https://stringflux.io/" rel="nofollow">https://stringflux.io/</a> to make everyday string transformations a little less painful. It’s similar to CyberChef in the sense that it supports multiple string operations, but with a cleaner, more focused UI and smart suggestions based on your input.<p>You can also chain transformations — for example: decode base64 string which was base64 encoded from minified json → then json format (pretty-print) it — all in one flow. This is helpful when dealing with complex or nested strings, like encoded API responses or log data, where you need to apply multiple steps to make the content readable.<p>The idea came from the frustration of jumping between different tools just to handle common string tasks.<p>There’s a short GIF demo in the GitHub README: <a href="https://github.com/stringflux/stringflux">https://github.com/stringflux/stringflux</a><p>Would love to hear your thoughts and feedback!
Show HN: Container Use for Agents
Show HN: Container Use for Agents
Show HN: Lambduck, a Functional Programming Brainfuck
What if Brainfuck was less like C and more like Scheme?<p>The interpreter implemetation is pretty bad. It's not very fast, it's not very good, and it's probably not very correct. But maybe there's some vaguely interesting programs you could write with it!<p>For example, the Y combinator:<p><pre><code> λf. (λx. f (x x)) (λx. f (x x))
</code></pre>
is written as:<p><pre><code> \` \`1 `0 0 \`1 `0 0</code></pre>
Show HN: Lambduck, a Functional Programming Brainfuck
What if Brainfuck was less like C and more like Scheme?<p>The interpreter implemetation is pretty bad. It's not very fast, it's not very good, and it's probably not very correct. But maybe there's some vaguely interesting programs you could write with it!<p>For example, the Y combinator:<p><pre><code> λf. (λx. f (x x)) (λx. f (x x))
</code></pre>
is written as:<p><pre><code> \` \`1 `0 0 \`1 `0 0</code></pre>
Show HN: Lambduck, a Functional Programming Brainfuck
What if Brainfuck was less like C and more like Scheme?<p>The interpreter implemetation is pretty bad. It's not very fast, it's not very good, and it's probably not very correct. But maybe there's some vaguely interesting programs you could write with it!<p>For example, the Y combinator:<p><pre><code> λf. (λx. f (x x)) (λx. f (x x))
</code></pre>
is written as:<p><pre><code> \` \`1 `0 0 \`1 `0 0</code></pre>
Show HN: AI game animation sprite generator
I tried to build AI game animation generator last year ( <a href="https://news.ycombinator.com/item?id=40395221">https://news.ycombinator.com/item?id=40395221</a>), a lot of people were interested, but it failed, mainly because the technology was not good enough.<p>1 year passed, there were a lot of developments in video/image generation. I tried it again, I think it works super well now. Actually beyond my expectation.<p>You can generate all kinds of game character animation sprites with only 1 image.<p>1, upload your image of your character
2, choose the action you want
3, generate!<p>Support basic actions like Run, Jump, Punch and complicated ones like: Shoryuken, Spinning kick, etc.<p>High quality sprite sheet will be directly generated to use in Unity and any game engine.<p>If you are an indie game developer, you don't need to high an artist or animator to develop you game.<p>For studios, it's 10x cost saving and 10x efficiency as no more creating animations for 100 NPCs 100 times.<p>Please check it out, looking forward to your feedback!
Show HN: AI game animation sprite generator
I tried to build AI game animation generator last year ( <a href="https://news.ycombinator.com/item?id=40395221">https://news.ycombinator.com/item?id=40395221</a>), a lot of people were interested, but it failed, mainly because the technology was not good enough.<p>1 year passed, there were a lot of developments in video/image generation. I tried it again, I think it works super well now. Actually beyond my expectation.<p>You can generate all kinds of game character animation sprites with only 1 image.<p>1, upload your image of your character
2, choose the action you want
3, generate!<p>Support basic actions like Run, Jump, Punch and complicated ones like: Shoryuken, Spinning kick, etc.<p>High quality sprite sheet will be directly generated to use in Unity and any game engine.<p>If you are an indie game developer, you don't need to high an artist or animator to develop you game.<p>For studios, it's 10x cost saving and 10x efficiency as no more creating animations for 100 NPCs 100 times.<p>Please check it out, looking forward to your feedback!
Show HN: AI game animation sprite generator
I tried to build AI game animation generator last year ( <a href="https://news.ycombinator.com/item?id=40395221">https://news.ycombinator.com/item?id=40395221</a>), a lot of people were interested, but it failed, mainly because the technology was not good enough.<p>1 year passed, there were a lot of developments in video/image generation. I tried it again, I think it works super well now. Actually beyond my expectation.<p>You can generate all kinds of game character animation sprites with only 1 image.<p>1, upload your image of your character
2, choose the action you want
3, generate!<p>Support basic actions like Run, Jump, Punch and complicated ones like: Shoryuken, Spinning kick, etc.<p>High quality sprite sheet will be directly generated to use in Unity and any game engine.<p>If you are an indie game developer, you don't need to high an artist or animator to develop you game.<p>For studios, it's 10x cost saving and 10x efficiency as no more creating animations for 100 NPCs 100 times.<p>Please check it out, looking forward to your feedback!
Show HN: AI game animation sprite generator
I tried to build AI game animation generator last year ( <a href="https://news.ycombinator.com/item?id=40395221">https://news.ycombinator.com/item?id=40395221</a>), a lot of people were interested, but it failed, mainly because the technology was not good enough.<p>1 year passed, there were a lot of developments in video/image generation. I tried it again, I think it works super well now. Actually beyond my expectation.<p>You can generate all kinds of game character animation sprites with only 1 image.<p>1, upload your image of your character
2, choose the action you want
3, generate!<p>Support basic actions like Run, Jump, Punch and complicated ones like: Shoryuken, Spinning kick, etc.<p>High quality sprite sheet will be directly generated to use in Unity and any game engine.<p>If you are an indie game developer, you don't need to high an artist or animator to develop you game.<p>For studios, it's 10x cost saving and 10x efficiency as no more creating animations for 100 NPCs 100 times.<p>Please check it out, looking forward to your feedback!
Show HN: iOS Screen Time from a REST API
We're Oliver and Royce and we're the founders of Clearspace. We build tools to help people reduce their screen time (here’s us two years ago: <a href="https://news.ycombinator.com/item?id=35888644">https://news.ycombinator.com/item?id=35888644</a>)<p>We get all kinds of requests from users for ways they'd like to use their screen time data.<p>- “Auto-donate $x to charity every time I exceed a limit or try to bypass it”<p>- “My 75 Hard group has a screen time requirement, can we set up group visibility?”<p>- “Let my personal agent know if it’s a good time to tackle things on my todo list”<p>- “Auto-report large deviations in my screen time to my therapist “<p>We aren't able to build for all of them, so we're releasing this API.<p>This is the first time iOS Screen Time is accessible on the web. Apple doesn’t expose it, but since we measure it ourselves, we can - via UI or API. We're launching this API so developers can build all these tools and more. Our goal is to enable more solutions to what we believe is the biggest problem in the world - the misalignment of human attention and intention in the digital world.<p>Here's a quick demo of setting up and using the API: <a href="https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdxo-eTu/view?usp=sharing" rel="nofollow">https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdx...</a>
Show HN: iOS Screen Time from a REST API
We're Oliver and Royce and we're the founders of Clearspace. We build tools to help people reduce their screen time (here’s us two years ago: <a href="https://news.ycombinator.com/item?id=35888644">https://news.ycombinator.com/item?id=35888644</a>)<p>We get all kinds of requests from users for ways they'd like to use their screen time data.<p>- “Auto-donate $x to charity every time I exceed a limit or try to bypass it”<p>- “My 75 Hard group has a screen time requirement, can we set up group visibility?”<p>- “Let my personal agent know if it’s a good time to tackle things on my todo list”<p>- “Auto-report large deviations in my screen time to my therapist “<p>We aren't able to build for all of them, so we're releasing this API.<p>This is the first time iOS Screen Time is accessible on the web. Apple doesn’t expose it, but since we measure it ourselves, we can - via UI or API. We're launching this API so developers can build all these tools and more. Our goal is to enable more solutions to what we believe is the biggest problem in the world - the misalignment of human attention and intention in the digital world.<p>Here's a quick demo of setting up and using the API: <a href="https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdxo-eTu/view?usp=sharing" rel="nofollow">https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdx...</a>
Show HN: iOS Screen Time from a REST API
We're Oliver and Royce and we're the founders of Clearspace. We build tools to help people reduce their screen time (here’s us two years ago: <a href="https://news.ycombinator.com/item?id=35888644">https://news.ycombinator.com/item?id=35888644</a>)<p>We get all kinds of requests from users for ways they'd like to use their screen time data.<p>- “Auto-donate $x to charity every time I exceed a limit or try to bypass it”<p>- “My 75 Hard group has a screen time requirement, can we set up group visibility?”<p>- “Let my personal agent know if it’s a good time to tackle things on my todo list”<p>- “Auto-report large deviations in my screen time to my therapist “<p>We aren't able to build for all of them, so we're releasing this API.<p>This is the first time iOS Screen Time is accessible on the web. Apple doesn’t expose it, but since we measure it ourselves, we can - via UI or API. We're launching this API so developers can build all these tools and more. Our goal is to enable more solutions to what we believe is the biggest problem in the world - the misalignment of human attention and intention in the digital world.<p>Here's a quick demo of setting up and using the API: <a href="https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdxo-eTu/view?usp=sharing" rel="nofollow">https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdx...</a>
Show HN: iOS Screen Time from a REST API
We're Oliver and Royce and we're the founders of Clearspace. We build tools to help people reduce their screen time (here’s us two years ago: <a href="https://news.ycombinator.com/item?id=35888644">https://news.ycombinator.com/item?id=35888644</a>)<p>We get all kinds of requests from users for ways they'd like to use their screen time data.<p>- “Auto-donate $x to charity every time I exceed a limit or try to bypass it”<p>- “My 75 Hard group has a screen time requirement, can we set up group visibility?”<p>- “Let my personal agent know if it’s a good time to tackle things on my todo list”<p>- “Auto-report large deviations in my screen time to my therapist “<p>We aren't able to build for all of them, so we're releasing this API.<p>This is the first time iOS Screen Time is accessible on the web. Apple doesn’t expose it, but since we measure it ourselves, we can - via UI or API. We're launching this API so developers can build all these tools and more. Our goal is to enable more solutions to what we believe is the biggest problem in the world - the misalignment of human attention and intention in the digital world.<p>Here's a quick demo of setting up and using the API: <a href="https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdxo-eTu/view?usp=sharing" rel="nofollow">https://drive.google.com/file/d/1QahETj3xaaIsn0JiNbuqvTaSLdx...</a>
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code.<p>ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer.<p>the pain:<p>your agent screams out an endpoint that never existed
it makes confident assumptions and you spend hours debugging false leads<p>the fix:<p>ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going.<p>some features:<p>- zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live
- cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks.
- markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up
- file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB<p>the quickstart<p>pip install ask-human-mcp
ask-human-mcp --help<p>add to .cursor/mcp.json and restart:
{
"mcpServers": {
"ask-human": { "command": "ask-human-mcp" }
}
}<p>now any call like:<p>answer = await ask_human(
"which auth endpoint do we use?",
"building login form in auth.js"
)<p>creates:<p>### Q8c4f1e2a
ts: 2025-01-15 14:30
q: which auth endpoint do we use?
ctx: building login form in auth.js
answer: PENDING<p>just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues.<p>link:<p>github -> <a href="https://github.com/Masony817/ask-human-mcp">https://github.com/Masony817/ask-human-mcp</a><p>feedback:<p>I'm Mason a 19yo solo-founder at Kallro. Happy to hear any bugs, feature requests, or weird edge cases you uncover - drop a comment or open an issue!
buy me a coffee -> coff.ee/masonyarbrough
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code.<p>ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer.<p>the pain:<p>your agent screams out an endpoint that never existed
it makes confident assumptions and you spend hours debugging false leads<p>the fix:<p>ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going.<p>some features:<p>- zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live
- cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks.
- markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up
- file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB<p>the quickstart<p>pip install ask-human-mcp
ask-human-mcp --help<p>add to .cursor/mcp.json and restart:
{
"mcpServers": {
"ask-human": { "command": "ask-human-mcp" }
}
}<p>now any call like:<p>answer = await ask_human(
"which auth endpoint do we use?",
"building login form in auth.js"
)<p>creates:<p>### Q8c4f1e2a
ts: 2025-01-15 14:30
q: which auth endpoint do we use?
ctx: building login form in auth.js
answer: PENDING<p>just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues.<p>link:<p>github -> <a href="https://github.com/Masony817/ask-human-mcp">https://github.com/Masony817/ask-human-mcp</a><p>feedback:<p>I'm Mason a 19yo solo-founder at Kallro. Happy to hear any bugs, feature requests, or weird edge cases you uncover - drop a comment or open an issue!
buy me a coffee -> coff.ee/masonyarbrough
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code.<p>ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer.<p>the pain:<p>your agent screams out an endpoint that never existed
it makes confident assumptions and you spend hours debugging false leads<p>the fix:<p>ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going.<p>some features:<p>- zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live
- cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks.
- markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up
- file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB<p>the quickstart<p>pip install ask-human-mcp
ask-human-mcp --help<p>add to .cursor/mcp.json and restart:
{
"mcpServers": {
"ask-human": { "command": "ask-human-mcp" }
}
}<p>now any call like:<p>answer = await ask_human(
"which auth endpoint do we use?",
"building login form in auth.js"
)<p>creates:<p>### Q8c4f1e2a
ts: 2025-01-15 14:30
q: which auth endpoint do we use?
ctx: building login form in auth.js
answer: PENDING<p>just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues.<p>link:<p>github -> <a href="https://github.com/Masony817/ask-human-mcp">https://github.com/Masony817/ask-human-mcp</a><p>feedback:<p>I'm Mason a 19yo solo-founder at Kallro. Happy to hear any bugs, feature requests, or weird edge cases you uncover - drop a comment or open an issue!
buy me a coffee -> coff.ee/masonyarbrough
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code.<p>ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer.<p>the pain:<p>your agent screams out an endpoint that never existed
it makes confident assumptions and you spend hours debugging false leads<p>the fix:<p>ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going.<p>some features:<p>- zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live
- cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks.
- markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up
- file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB<p>the quickstart<p>pip install ask-human-mcp
ask-human-mcp --help<p>add to .cursor/mcp.json and restart:
{
"mcpServers": {
"ask-human": { "command": "ask-human-mcp" }
}
}<p>now any call like:<p>answer = await ask_human(
"which auth endpoint do we use?",
"building login form in auth.js"
)<p>creates:<p>### Q8c4f1e2a
ts: 2025-01-15 14:30
q: which auth endpoint do we use?
ctx: building login form in auth.js
answer: PENDING<p>just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues.<p>link:<p>github -> <a href="https://github.com/Masony817/ask-human-mcp">https://github.com/Masony817/ask-human-mcp</a><p>feedback:<p>I'm Mason a 19yo solo-founder at Kallro. Happy to hear any bugs, feature requests, or weird edge cases you uncover - drop a comment or open an issue!
buy me a coffee -> coff.ee/masonyarbrough
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code.<p>ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer.<p>the pain:<p>your agent screams out an endpoint that never existed
it makes confident assumptions and you spend hours debugging false leads<p>the fix:<p>ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going.<p>some features:<p>- zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live
- cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks.
- markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up
- file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB<p>the quickstart<p>pip install ask-human-mcp
ask-human-mcp --help<p>add to .cursor/mcp.json and restart:
{
"mcpServers": {
"ask-human": { "command": "ask-human-mcp" }
}
}<p>now any call like:<p>answer = await ask_human(
"which auth endpoint do we use?",
"building login form in auth.js"
)<p>creates:<p>### Q8c4f1e2a
ts: 2025-01-15 14:30
q: which auth endpoint do we use?
ctx: building login form in auth.js
answer: PENDING<p>just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues.<p>link:<p>github -> <a href="https://github.com/Masony817/ask-human-mcp">https://github.com/Masony817/ask-human-mcp</a><p>feedback:<p>I'm Mason a 19yo solo-founder at Kallro. Happy to hear any bugs, feature requests, or weird edge cases you uncover - drop a comment or open an issue!
buy me a coffee -> coff.ee/masonyarbrough