The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Dayflow – A git log for your day
Hi HN! I've been building Dayflow, a macOS app that automatically tracks what you're actually working on (not just which apps you have open).<p>Here's what it does:<p>- It creates a semantic timeline of your day;<p>- It does it by understanding the content on your screen (with local or cloud VLMs);<p>- This allows you to see exactly where your time went without any manual logging.<p>Traditional time trackers tell you "3 hours in Chrome" which is not very helpful. Dayflow actually understands if you're reading documentation, debugging code, or scrolling HN. Instead of "Chrome: 3 hours", you get "Reviewed PR comments: 45min", "Read HN thread about Rust: 20min", "Debugged auth flow: 1.5hr".<p>I was an early Rewind user but rarely used the retrieval feature. I built Dayflow because I saw other interesting uses for screen data. I find that it helps me stay on track while working - I check it every few hours and make sure I’m spending my time the way I intended - if I’m not, I try to course correct.<p>Here’s what you need to know about privacy:<p>- Run 100% locally using qwen2.5-vl-3b (~4GB model)<p>- No cloud uploads, no account<p>- Full source available under MIT license (<a href="https://github.com/JerryZLiu/Dayflow" rel="nofollow">https://github.com/JerryZLiu/Dayflow</a>)<p>- Optional: BYO Gemini API key for better quality (stored in Keychain, with free-tier workaround to prevent training on your data)<p>The tech stack is pretty simple, SwiftUI with a local sqlite DB. Uses native macOS apis for efficient screen captures. Since most people who run LLMs locally already have their tool of choice (Ollama, LLMStudio, etc.), I decided to not embed an LLM into Dayflow.<p>By far the biggest challenge was adapting from SOTA vision models like Gemini 2.5 Pro to small, local models. My constraints were that it had to take up <4GB of ram and have vision capabilities. I had to do a lot of evals to figure out that Qwen2.5VL-3B was the best balance of size and quality, but there was still a sizable tradeoff in quality that I had to accept. I also got creative with sampling rates and prompt chunking to deal with the 100x smaller context window. Processing a 15 minute segment takes ~32 local LLM calls vs 2 Gemini calls!<p>Here’s what I’m working on next:<p>Distillation: Using Gemini's high-quality outputs as training data to teach a local model the patterns it needs, hopefully closing the quality gap.<p>Custom dashboards where you can track answers to any question like "How long did I spend on HN?" or "Hours until my first deep work session of the day<p>I'd love to hear your thoughts, especially if you've struggled with productivity tracking or have ideas for what you'd want from a tool like this.
Show HN: Dayflow – A git log for your day
Hi HN! I've been building Dayflow, a macOS app that automatically tracks what you're actually working on (not just which apps you have open).<p>Here's what it does:<p>- It creates a semantic timeline of your day;<p>- It does it by understanding the content on your screen (with local or cloud VLMs);<p>- This allows you to see exactly where your time went without any manual logging.<p>Traditional time trackers tell you "3 hours in Chrome" which is not very helpful. Dayflow actually understands if you're reading documentation, debugging code, or scrolling HN. Instead of "Chrome: 3 hours", you get "Reviewed PR comments: 45min", "Read HN thread about Rust: 20min", "Debugged auth flow: 1.5hr".<p>I was an early Rewind user but rarely used the retrieval feature. I built Dayflow because I saw other interesting uses for screen data. I find that it helps me stay on track while working - I check it every few hours and make sure I’m spending my time the way I intended - if I’m not, I try to course correct.<p>Here’s what you need to know about privacy:<p>- Run 100% locally using qwen2.5-vl-3b (~4GB model)<p>- No cloud uploads, no account<p>- Full source available under MIT license (<a href="https://github.com/JerryZLiu/Dayflow" rel="nofollow">https://github.com/JerryZLiu/Dayflow</a>)<p>- Optional: BYO Gemini API key for better quality (stored in Keychain, with free-tier workaround to prevent training on your data)<p>The tech stack is pretty simple, SwiftUI with a local sqlite DB. Uses native macOS apis for efficient screen captures. Since most people who run LLMs locally already have their tool of choice (Ollama, LLMStudio, etc.), I decided to not embed an LLM into Dayflow.<p>By far the biggest challenge was adapting from SOTA vision models like Gemini 2.5 Pro to small, local models. My constraints were that it had to take up <4GB of ram and have vision capabilities. I had to do a lot of evals to figure out that Qwen2.5VL-3B was the best balance of size and quality, but there was still a sizable tradeoff in quality that I had to accept. I also got creative with sampling rates and prompt chunking to deal with the 100x smaller context window. Processing a 15 minute segment takes ~32 local LLM calls vs 2 Gemini calls!<p>Here’s what I’m working on next:<p>Distillation: Using Gemini's high-quality outputs as training data to teach a local model the patterns it needs, hopefully closing the quality gap.<p>Custom dashboards where you can track answers to any question like "How long did I spend on HN?" or "Hours until my first deep work session of the day<p>I'd love to hear your thoughts, especially if you've struggled with productivity tracking or have ideas for what you'd want from a tool like this.
Show HN: Dayflow – A git log for your day
Hi HN! I've been building Dayflow, a macOS app that automatically tracks what you're actually working on (not just which apps you have open).<p>Here's what it does:<p>- It creates a semantic timeline of your day;<p>- It does it by understanding the content on your screen (with local or cloud VLMs);<p>- This allows you to see exactly where your time went without any manual logging.<p>Traditional time trackers tell you "3 hours in Chrome" which is not very helpful. Dayflow actually understands if you're reading documentation, debugging code, or scrolling HN. Instead of "Chrome: 3 hours", you get "Reviewed PR comments: 45min", "Read HN thread about Rust: 20min", "Debugged auth flow: 1.5hr".<p>I was an early Rewind user but rarely used the retrieval feature. I built Dayflow because I saw other interesting uses for screen data. I find that it helps me stay on track while working - I check it every few hours and make sure I’m spending my time the way I intended - if I’m not, I try to course correct.<p>Here’s what you need to know about privacy:<p>- Run 100% locally using qwen2.5-vl-3b (~4GB model)<p>- No cloud uploads, no account<p>- Full source available under MIT license (<a href="https://github.com/JerryZLiu/Dayflow" rel="nofollow">https://github.com/JerryZLiu/Dayflow</a>)<p>- Optional: BYO Gemini API key for better quality (stored in Keychain, with free-tier workaround to prevent training on your data)<p>The tech stack is pretty simple, SwiftUI with a local sqlite DB. Uses native macOS apis for efficient screen captures. Since most people who run LLMs locally already have their tool of choice (Ollama, LLMStudio, etc.), I decided to not embed an LLM into Dayflow.<p>By far the biggest challenge was adapting from SOTA vision models like Gemini 2.5 Pro to small, local models. My constraints were that it had to take up <4GB of ram and have vision capabilities. I had to do a lot of evals to figure out that Qwen2.5VL-3B was the best balance of size and quality, but there was still a sizable tradeoff in quality that I had to accept. I also got creative with sampling rates and prompt chunking to deal with the 100x smaller context window. Processing a 15 minute segment takes ~32 local LLM calls vs 2 Gemini calls!<p>Here’s what I’m working on next:<p>Distillation: Using Gemini's high-quality outputs as training data to teach a local model the patterns it needs, hopefully closing the quality gap.<p>Custom dashboards where you can track answers to any question like "How long did I spend on HN?" or "Hours until my first deep work session of the day<p>I'd love to hear your thoughts, especially if you've struggled with productivity tracking or have ideas for what you'd want from a tool like this.
Show HN: Dayflow – A git log for your day
Hi HN! I've been building Dayflow, a macOS app that automatically tracks what you're actually working on (not just which apps you have open).<p>Here's what it does:<p>- It creates a semantic timeline of your day;<p>- It does it by understanding the content on your screen (with local or cloud VLMs);<p>- This allows you to see exactly where your time went without any manual logging.<p>Traditional time trackers tell you "3 hours in Chrome" which is not very helpful. Dayflow actually understands if you're reading documentation, debugging code, or scrolling HN. Instead of "Chrome: 3 hours", you get "Reviewed PR comments: 45min", "Read HN thread about Rust: 20min", "Debugged auth flow: 1.5hr".<p>I was an early Rewind user but rarely used the retrieval feature. I built Dayflow because I saw other interesting uses for screen data. I find that it helps me stay on track while working - I check it every few hours and make sure I’m spending my time the way I intended - if I’m not, I try to course correct.<p>Here’s what you need to know about privacy:<p>- Run 100% locally using qwen2.5-vl-3b (~4GB model)<p>- No cloud uploads, no account<p>- Full source available under MIT license (<a href="https://github.com/JerryZLiu/Dayflow" rel="nofollow">https://github.com/JerryZLiu/Dayflow</a>)<p>- Optional: BYO Gemini API key for better quality (stored in Keychain, with free-tier workaround to prevent training on your data)<p>The tech stack is pretty simple, SwiftUI with a local sqlite DB. Uses native macOS apis for efficient screen captures. Since most people who run LLMs locally already have their tool of choice (Ollama, LLMStudio, etc.), I decided to not embed an LLM into Dayflow.<p>By far the biggest challenge was adapting from SOTA vision models like Gemini 2.5 Pro to small, local models. My constraints were that it had to take up <4GB of ram and have vision capabilities. I had to do a lot of evals to figure out that Qwen2.5VL-3B was the best balance of size and quality, but there was still a sizable tradeoff in quality that I had to accept. I also got creative with sampling rates and prompt chunking to deal with the 100x smaller context window. Processing a 15 minute segment takes ~32 local LLM calls vs 2 Gemini calls!<p>Here’s what I’m working on next:<p>Distillation: Using Gemini's high-quality outputs as training data to teach a local model the patterns it needs, hopefully closing the quality gap.<p>Custom dashboards where you can track answers to any question like "How long did I spend on HN?" or "Hours until my first deep work session of the day<p>I'd love to hear your thoughts, especially if you've struggled with productivity tracking or have ideas for what you'd want from a tool like this.
Show HN: Ggc – A Git CLI tool written in Go with interactive UI
A while ago I shared an early version of ggc, a Git helper I built in Go.
Since then the project has grown quite a bit, and I’d love to share the latest updates (v6.0).<p>Repo: <a href="https://github.com/bmf-san/ggc" rel="nofollow">https://github.com/bmf-san/ggc</a><p>Install:
- macOS/Linux: `brew install ggc`
- Go: `go install github.com/bmf-san/ggc/v6@latest`
- Homebrew: `brew install ggc`
- Or grab binaries: <a href="https://github.com/bmf-san/ggc/releases" rel="nofollow">https://github.com/bmf-san/ggc/releases</a><p>Features:
Dual modes: Traditional CLI commands (ggc add, etc.) and interactive mode (launch with just ggc)
Intuitive command structure: Simplified interface for common Git operations
Incremental search UI: Quickly find and execute commands with real-time filtering
Fast and lightweight: Implemented in Go with minimal dependencies
Shell completions: Included for Bash, Zsh, and Fish
Custom aliases: Chain multiple commands with user-defined aliases
Cross-platform: Works on macOS, Linux, and Windows<p>Technical details:
Built with Go standard library and minimal external packages
Supports 50+ Git operations (add, commit, branch, pull, etc.)<p>I'd appreciate any feedback or contributions!
Show HN: Ggc – A Git CLI tool written in Go with interactive UI
A while ago I shared an early version of ggc, a Git helper I built in Go.
Since then the project has grown quite a bit, and I’d love to share the latest updates (v6.0).<p>Repo: <a href="https://github.com/bmf-san/ggc" rel="nofollow">https://github.com/bmf-san/ggc</a><p>Install:
- macOS/Linux: `brew install ggc`
- Go: `go install github.com/bmf-san/ggc/v6@latest`
- Homebrew: `brew install ggc`
- Or grab binaries: <a href="https://github.com/bmf-san/ggc/releases" rel="nofollow">https://github.com/bmf-san/ggc/releases</a><p>Features:
Dual modes: Traditional CLI commands (ggc add, etc.) and interactive mode (launch with just ggc)
Intuitive command structure: Simplified interface for common Git operations
Incremental search UI: Quickly find and execute commands with real-time filtering
Fast and lightweight: Implemented in Go with minimal dependencies
Shell completions: Included for Bash, Zsh, and Fish
Custom aliases: Chain multiple commands with user-defined aliases
Cross-platform: Works on macOS, Linux, and Windows<p>Technical details:
Built with Go standard library and minimal external packages
Supports 50+ Git operations (add, commit, branch, pull, etc.)<p>I'd appreciate any feedback or contributions!
Show HN: Ggc – A Git CLI tool written in Go with interactive UI
A while ago I shared an early version of ggc, a Git helper I built in Go.
Since then the project has grown quite a bit, and I’d love to share the latest updates (v6.0).<p>Repo: <a href="https://github.com/bmf-san/ggc" rel="nofollow">https://github.com/bmf-san/ggc</a><p>Install:
- macOS/Linux: `brew install ggc`
- Go: `go install github.com/bmf-san/ggc/v6@latest`
- Homebrew: `brew install ggc`
- Or grab binaries: <a href="https://github.com/bmf-san/ggc/releases" rel="nofollow">https://github.com/bmf-san/ggc/releases</a><p>Features:
Dual modes: Traditional CLI commands (ggc add, etc.) and interactive mode (launch with just ggc)
Intuitive command structure: Simplified interface for common Git operations
Incremental search UI: Quickly find and execute commands with real-time filtering
Fast and lightweight: Implemented in Go with minimal dependencies
Shell completions: Included for Bash, Zsh, and Fish
Custom aliases: Chain multiple commands with user-defined aliases
Cross-platform: Works on macOS, Linux, and Windows<p>Technical details:
Built with Go standard library and minimal external packages
Supports 50+ Git operations (add, commit, branch, pull, etc.)<p>I'd appreciate any feedback or contributions!
Show HN: FlyCode – Recover Stripe payments by automatically using backup cards
We built FlyCode after seeing subscription businesses lose ~35% of recurring revenue each year to failed payments — even when customers had other valid cards on file.<p>*The problem:* When a customer's primary card fails, Stripe retries a few times then cancels the subscription. If that customer has a backup card, it isn’t tried. At least 20% of active customers have more than one card on file, which means a lot of preventable churn.<p>*Our solution:* FlyCode automatically identifies if a customer has other valid cards on file and retries them when a subscription payment fails. You can configure when these retries happen during the dunning period (beginning, middle, end) and define validity rules (e.g. “card was used in last 180 days”). It’s a Stripe app — no code changes needed.<p>We've seen 18%-20% higher recovery rates from our core retry engine, plus another 5–10% from using backup cards. Importantly, there was no increase in refunds or chargebacks — in fact, rates were lower than merchant averages. Big companies like Microsoft and Amazon already do this internally; we wanted to make the same capability accessible to smaller SaaS teams.<p>*Under the hood:* FlyCode monitors for failed invoices, checks for available backup methods via Stripe’s PaymentMethod API, and systematically retries in a way that avoids service disruption or manual workflows.<p>We’re Jake, Etai, and Tzachi — we previously built payment recovery systems at startups and enterprises, which is how we discovered this gap.<p>You can try it here: [<a href="https://www.flycode.com/stripe">https://www.flycode.com/stripe</a>]<p>We’d love feedback from anyone dealing with subscription payment failures. What’s been your experience with involuntary churn? Have you considered leveraging backup payment methods?
Show HN: FlyCode – Recover Stripe payments by automatically using backup cards
We built FlyCode after seeing subscription businesses lose ~35% of recurring revenue each year to failed payments — even when customers had other valid cards on file.<p>*The problem:* When a customer's primary card fails, Stripe retries a few times then cancels the subscription. If that customer has a backup card, it isn’t tried. At least 20% of active customers have more than one card on file, which means a lot of preventable churn.<p>*Our solution:* FlyCode automatically identifies if a customer has other valid cards on file and retries them when a subscription payment fails. You can configure when these retries happen during the dunning period (beginning, middle, end) and define validity rules (e.g. “card was used in last 180 days”). It’s a Stripe app — no code changes needed.<p>We've seen 18%-20% higher recovery rates from our core retry engine, plus another 5–10% from using backup cards. Importantly, there was no increase in refunds or chargebacks — in fact, rates were lower than merchant averages. Big companies like Microsoft and Amazon already do this internally; we wanted to make the same capability accessible to smaller SaaS teams.<p>*Under the hood:* FlyCode monitors for failed invoices, checks for available backup methods via Stripe’s PaymentMethod API, and systematically retries in a way that avoids service disruption or manual workflows.<p>We’re Jake, Etai, and Tzachi — we previously built payment recovery systems at startups and enterprises, which is how we discovered this gap.<p>You can try it here: [<a href="https://www.flycode.com/stripe">https://www.flycode.com/stripe</a>]<p>We’d love feedback from anyone dealing with subscription payment failures. What’s been your experience with involuntary churn? Have you considered leveraging backup payment methods?
Show HN: The Blots Programming Language
I've been working on this small, slightly weird expression-oriented programming language for a little while now and feel ready to share it with others. I use it pretty often now in my day-to-day and work life, as a scratchpad for doing a bit of quick math or picking some pieces of data out of a JSON payload.<p>Would really appreciate any feedback about the syntax, docs, features that are glaringly missing, etc. Before anybody mentions it: I know the performance is pretty lousy when dealing with a lot of data. If you can believe it, the runtime is about 100x faster than it used to be! Long term I'd like to switch to a proper bytecode interpreter, but so far performance has been Good Enough for my use cases.<p>Thanks for taking a look!
Show HN: The Blots Programming Language
I've been working on this small, slightly weird expression-oriented programming language for a little while now and feel ready to share it with others. I use it pretty often now in my day-to-day and work life, as a scratchpad for doing a bit of quick math or picking some pieces of data out of a JSON payload.<p>Would really appreciate any feedback about the syntax, docs, features that are glaringly missing, etc. Before anybody mentions it: I know the performance is pretty lousy when dealing with a lot of data. If you can believe it, the runtime is about 100x faster than it used to be! Long term I'd like to switch to a proper bytecode interpreter, but so far performance has been Good Enough for my use cases.<p>Thanks for taking a look!
Show HN: The Blots Programming Language
I've been working on this small, slightly weird expression-oriented programming language for a little while now and feel ready to share it with others. I use it pretty often now in my day-to-day and work life, as a scratchpad for doing a bit of quick math or picking some pieces of data out of a JSON payload.<p>Would really appreciate any feedback about the syntax, docs, features that are glaringly missing, etc. Before anybody mentions it: I know the performance is pretty lousy when dealing with a lot of data. If you can believe it, the runtime is about 100x faster than it used to be! Long term I'd like to switch to a proper bytecode interpreter, but so far performance has been Good Enough for my use cases.<p>Thanks for taking a look!
Show HN: Kekkai – a simple, fast file integrity monitoring tool in Go
I built a tool called *Kekkai* for file integrity monitoring in production environments.
It records file hashes during deployment and later verifies them to detect unauthorized modifications (e.g. from OS command injection or tampering).<p>Why it matters:<p>* Many web apps (PHP, Ruby, Python, etc.) on AWS EC2 need a lightweight way to confirm their code hasn’t been changed.
* Traditional approaches that rely on metadata often create false positives.
* Kekkai checks only file content, so it reliably detects real changes.
* I’ve deployed it to an EC2 PHP application in production, and it’s working smoothly so far.<p>Key points:<p>* *Content-only hashing* (ignores timestamps/metadata)
* *Symlink protection* (detects swaps/changes)
* *Secure S3 storage* (deploy servers write-only, app servers read-only)
* *Single Go binary* with minimal dependencies<p>Would love feedback from others running apps on EC2 or managing file integrity in production.
Show HN: Kekkai – a simple, fast file integrity monitoring tool in Go
I built a tool called *Kekkai* for file integrity monitoring in production environments.
It records file hashes during deployment and later verifies them to detect unauthorized modifications (e.g. from OS command injection or tampering).<p>Why it matters:<p>* Many web apps (PHP, Ruby, Python, etc.) on AWS EC2 need a lightweight way to confirm their code hasn’t been changed.
* Traditional approaches that rely on metadata often create false positives.
* Kekkai checks only file content, so it reliably detects real changes.
* I’ve deployed it to an EC2 PHP application in production, and it’s working smoothly so far.<p>Key points:<p>* *Content-only hashing* (ignores timestamps/metadata)
* *Symlink protection* (detects swaps/changes)
* *Secure S3 storage* (deploy servers write-only, app servers read-only)
* *Single Go binary* with minimal dependencies<p>Would love feedback from others running apps on EC2 or managing file integrity in production.
Show HN: Kekkai – a simple, fast file integrity monitoring tool in Go
I built a tool called *Kekkai* for file integrity monitoring in production environments.
It records file hashes during deployment and later verifies them to detect unauthorized modifications (e.g. from OS command injection or tampering).<p>Why it matters:<p>* Many web apps (PHP, Ruby, Python, etc.) on AWS EC2 need a lightweight way to confirm their code hasn’t been changed.
* Traditional approaches that rely on metadata often create false positives.
* Kekkai checks only file content, so it reliably detects real changes.
* I’ve deployed it to an EC2 PHP application in production, and it’s working smoothly so far.<p>Key points:<p>* *Content-only hashing* (ignores timestamps/metadata)
* *Symlink protection* (detects swaps/changes)
* *Secure S3 storage* (deploy servers write-only, app servers read-only)
* *Single Go binary* with minimal dependencies<p>Would love feedback from others running apps on EC2 or managing file integrity in production.
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput