Pinned Tweet
Want to build some cool stuff with Gradium AI's voice models? Join our hackathon / builder challenge!
We'll drop all the details and specifics in a few days, but reserve your spot now 👇
We'll drop all the details and specifics in a few days, but reserve your spot now 👇
Alright, we teamed up with @GradiumAI for a builder challenge / hackathon 🚀
The idea is that you build something real with Gradium. It's free and open to everyone, and you can win some cool prizes.
🥇 First prize is a Raspberry Pi + 1M Gradium credits + lifetime access to unner-ups get 500k Gradium credits each and lifetime access to @active_builders
The brief drops in a few days, but you should save your spot now 👇
3
1
8
396
Active Builders retweeted
Today I'm launching Runlight 🚀
It's a free and open source web analytics tool you host yourself.
I run a lot of websites.
Every analytics tool I ever used charged a monthly fee per site, capped the number of pageviews I could track, set cookies on my visitors, or kept my data rs.
I wanted something simple that lived on my own server and told me what I needed to know.
So I built it.
Runlight has been running on my own sites for a while now (gotta eat your own dog food, right?).
Here's what it does.
→ No cookies. Runlight counts every real visitor without setting a single cookie.
→ The numbers you actually check. Visitors, pageviews, bounce rate, and time on site, all on one screen.
→ Pages, sources, and places. See where people land, where they came from, and where in the world they are, down to the city.
→ Goals, funnels, and revenue. Track conversions, see which sources make you money, and follow each visitor's journey step by step.
→ AI agents. My favourite part. Ever wonder if ChatGPT is reading your site? Runlight shows you every AI assistant that visits, and whether it was a person asking about you or a bot crawling for training.
→ When people show up. A GitHub-style heatmap of your busiest days and hours.
→ Device, browser, OS, screen size, and language.
→ Short links. Connect a custom domain and create short links that show up right alongside the rest of your stats.
Best of all, Runlight runs inside the app you already have.
There's no separate service to babysit.
Install the package, mount it at /runlight, and add one script tag.
You can run it on SQLite, Postgres, MySQL, or ClickHouse (there are performance benchmarks in the docs if you're curious).
Also, it works with pretty much any stack. There are packages for JavaScript, PHP, Python, Ruby, Go, Java, .NET, Elixir, and Rust, and it drops right into Next.js, Nuxt, SvelteKit, Astro, Rails, Express, Cloudflare Workers, and plenty more.
On a CMS? There are official plugins for WordPress, Drupal, and Craft CMS.
I believe analytics should be free, fast, and owned by the person running the site. That's Runlight.
It's open source, so dig through the code, open an issue, or send a PR.
It's a free and open source web analytics tool you host yourself.
I run a lot of websites.
Every analytics tool I ever used charged a monthly fee per site, capped the number of pageviews I could track, set cookies on my visitors, or kept my data rs.
I wanted something simple that lived on my own server and told me what I needed to know.
So I built it.
Runlight has been running on my own sites for a while now (gotta eat your own dog food, right?).
Here's what it does.
→ No cookies. Runlight counts every real visitor without setting a single cookie.
→ The numbers you actually check. Visitors, pageviews, bounce rate, and time on site, all on one screen.
→ Pages, sources, and places. See where people land, where they came from, and where in the world they are, down to the city.
→ Goals, funnels, and revenue. Track conversions, see which sources make you money, and follow each visitor's journey step by step.
→ AI agents. My favourite part. Ever wonder if ChatGPT is reading your site? Runlight shows you every AI assistant that visits, and whether it was a person asking about you or a bot crawling for training.
→ When people show up. A GitHub-style heatmap of your busiest days and hours.
→ Device, browser, OS, screen size, and language.
→ Short links. Connect a custom domain and create short links that show up right alongside the rest of your stats.
Best of all, Runlight runs inside the app you already have.
There's no separate service to babysit.
Install the package, mount it at /runlight, and add one script tag.
You can run it on SQLite, Postgres, MySQL, or ClickHouse (there are performance benchmarks in the docs if you're curious).
Also, it works with pretty much any stack. There are packages for JavaScript, PHP, Python, Ruby, Go, Java, .NET, Elixir, and Rust, and it drops right into Next.js, Nuxt, SvelteKit, Astro, Rails, Express, Cloudflare Workers, and plenty more.
On a CMS? There are official plugins for WordPress, Drupal, and Craft CMS.
I believe analytics should be free, fast, and owned by the person running the site. That's Runlight.
It's open source, so dig through the code, open an issue, or send a PR.
35
8
120
6,691
Active Builders retweeted
AI can help you write code faster. But that doesn't mean your team is shipping faster.
According to Atlassian's 2026 State of DevEx Report, 87% of developers say AI helps them ship faster, but only 28% report noticeably less friction.
That gap says a lot.
Finding information, hing, and tech debt don't magically disappear when you add an AI coding assistant.
And 65% of developers spend time correcting AI-generated work that missed the original intent.
We're getting better at generating code. The bigger challenge is connecting that code to the right context, requirements, reviews, and workflows.
AI adoption isn't the same as AI impact.
The next step isn't just giving developers more tools. It's rethinking how the entire SDLC works with AI.
That's exactly what @Atlassian is digging into on November 9 with industry experts @kelseyhightower, @nathenharvey, @jkriggins, and @Andrew_boyagi.
What's the biggest bottleneck AI hasn't solved for you yet?
Join the panel discussion and register for Atlassian's State of DevEx 2026 webinar:
fandf.co/4BGpB72
—
Thanks to @Atlassian for sponsoring this post!
According to Atlassian's 2026 State of DevEx Report, 87% of developers say AI helps them ship faster, but only 28% report noticeably less friction.
That gap says a lot.
Finding information, hing, and tech debt don't magically disappear when you add an AI coding assistant.
And 65% of developers spend time correcting AI-generated work that missed the original intent.
We're getting better at generating code. The bigger challenge is connecting that code to the right context, requirements, reviews, and workflows.
AI adoption isn't the same as AI impact.
The next step isn't just giving developers more tools. It's rethinking how the entire SDLC works with AI.
That's exactly what @Atlassian is digging into on November 9 with industry experts @kelseyhightower, @nathenharvey, @jkriggins, and @Andrew_boyagi.
What's the biggest bottleneck AI hasn't solved for you yet?
Join the panel discussion and register for Atlassian's State of DevEx 2026 webinar:
fandf.co/4BGpB72
—
Thanks to @Atlassian for sponsoring this post!
8
3
24
4,382
Active Builders retweeted
An AI agent remembering a fact isn't enough. It also needs to understand when that fact changed.
Imagine an agent handling customer support. A customer updates their delivery preference three times. A basic memory system might retrieve all three versions without explaining which AI Agent Memory 26.8 introduces graph-aware retrieval to solve this problem.
↳ Typed links like supersedes, refines, supports, and contradicts make relationships between memories explicit.
↳ Automatic linking can identify relationships as new memories are extracted, without requiring developers to create every link manually.
↳ The num_hops setting controls how far retrieval follows those relationships, while max_linked_results limits the additional context returned.
Older memories aren't simply deleted. They can remain available as historical context, helping agents understand how information evolved.
This is useful for long-running agents where customer preferences, support cases, and business facts change over time.
The release also introduces image-aware memory and additional enterprise controls.
Want to see how it works? The article includes a runnable Python notebook:
fandf.co/4e7wkwY
—
Thanks to @OracleDevs for sponsoring this post.
Imagine an agent handling customer support. A customer updates their delivery preference three times. A basic memory system might retrieve all three versions without explaining which AI Agent Memory 26.8 introduces graph-aware retrieval to solve this problem.
↳ Typed links like supersedes, refines, supports, and contradicts make relationships between memories explicit.
↳ Automatic linking can identify relationships as new memories are extracted, without requiring developers to create every link manually.
↳ The num_hops setting controls how far retrieval follows those relationships, while max_linked_results limits the additional context returned.
Older memories aren't simply deleted. They can remain available as historical context, helping agents understand how information evolved.
This is useful for long-running agents where customer preferences, support cases, and business facts change over time.
The release also introduces image-aware memory and additional enterprise controls.
Want to see how it works? The article includes a runnable Python notebook:
fandf.co/4e7wkwY
—
Thanks to @OracleDevs for sponsoring this post.
17
2
21
3,585
Active Builders retweeted
Hey @grok, what should developers focus on to stay relevant over the next 5–10 years?
6
3
24
9,165
Active Builders retweeted
We're planning a giveaway, but wanted to ask the community first!
What would you like as a prize?
What would you like as a prize?
8
5
21
5,218
Active Builders retweeted
I just released 90 free, open source skills that teach AI assistants to take notes properly.
It's something that's been annoying me for a while.
You hand an assistant a lecture, a recipe, or a meeting, and you get back the same old tidy list of bullets every time.
These skills hes a single job the way an expert would do it.
There's one for Cornell notes that actually puts questions in the cue column, which I find most assistants get wrong. The meeting notes one won't turn "we should probably look into that" into a decision no one made. The recipe one keeps the "until the edges go golden" bits instead of flattening everything into "bake 20 min."
And there are some for niche stuff too, like birding logs, music practice, and D&D session notes.
And none of them makes anything up. If your source didn't say it, it gets marked [?] for you to fill in.
Here's why I made them.
A year ago I wrote on my blog that the habit of writing things down matters more than the software.
Then I wrote every day, hit a few hundred more notes, and ended up building my own notes app because hey I'd been wrong.
I build with AI all day, and the faster I go, the more I need to write. It just felt backwards that the AI was writing the worst notes.
90 skills in 4 collections:
- note-taking methods
- notes for your hobbies
- everyday notes
- writing
They work with Claude, Codex, Cursor, Copilot, Gemini CLI, and more.
npx skills add scratchpad-sh/skills
Of course they work with any notes app, or none at all, since everything comes out as plain Markdown.
It's something that's been annoying me for a while.
You hand an assistant a lecture, a recipe, or a meeting, and you get back the same old tidy list of bullets every time.
These skills hes a single job the way an expert would do it.
There's one for Cornell notes that actually puts questions in the cue column, which I find most assistants get wrong. The meeting notes one won't turn "we should probably look into that" into a decision no one made. The recipe one keeps the "until the edges go golden" bits instead of flattening everything into "bake 20 min."
And there are some for niche stuff too, like birding logs, music practice, and D&D session notes.
And none of them makes anything up. If your source didn't say it, it gets marked [?] for you to fill in.
Here's why I made them.
A year ago I wrote on my blog that the habit of writing things down matters more than the software.
Then I wrote every day, hit a few hundred more notes, and ended up building my own notes app because hey I'd been wrong.
I build with AI all day, and the faster I go, the more I need to write. It just felt backwards that the AI was writing the worst notes.
90 skills in 4 collections:
- note-taking methods
- notes for your hobbies
- everyday notes
- writing
They work with Claude, Codex, Cursor, Copilot, Gemini CLI, and more.
npx skills add scratchpad-sh/skills
Of course they work with any notes app, or none at all, since everything comes out as plain Markdown.
18
5
26
1,760
Active Builders retweeted
Quickly and easily create a CSS grid layout for your website!
7
3
33
7,432
Active Builders retweeted
I built parley for the @active_builders x @GradiumAI hackathon.
Here's the idea. You hold a key, talk to Claude Code, and let go. Your words show up in the prompt already cleaned up, and the prompt gets sent.
The "um"s, the "wait, no, Friday" and misheard names are all fixed . Say "the auth file" and it reaches Claude as @ src/auth.ts. Say just "stop", "undo that" or "clear the chat", and parley presses the keys for you.
It talks back too. When Claude finishes its turn with a question, parley chimes and opens the mic by itself, so you just answer. Say "answer me out loud" and Claude's reply gets read to you.
Gradium AI does all of the speech. Its speech-to-text streams your words into a little pill at the bottom of the screen while you're still talking. Its text-to-speech reads the answers. You can speak French, German, Spanish or Portuguese, and Claude still gets English. Parley remembers any word you correct so it's spelled right next time.
It's one Rust binary: a background process with a mic, Claude Code hooks, and a GTK pill on Linux. It runs on Linux (Hyprland), macOS and Windows.
It was a really fun build, and Gradium's speech-to-text is fast enough that talking to Claude feels natural. The repo is at github.com/radiumcoders/p…
Here's the idea. You hold a key, talk to Claude Code, and let go. Your words show up in the prompt already cleaned up, and the prompt gets sent.
The "um"s, the "wait, no, Friday" and misheard names are all fixed . Say "the auth file" and it reaches Claude as @ src/auth.ts. Say just "stop", "undo that" or "clear the chat", and parley presses the keys for you.
It talks back too. When Claude finishes its turn with a question, parley chimes and opens the mic by itself, so you just answer. Say "answer me out loud" and Claude's reply gets read to you.
Gradium AI does all of the speech. Its speech-to-text streams your words into a little pill at the bottom of the screen while you're still talking. Its text-to-speech reads the answers. You can speak French, German, Spanish or Portuguese, and Claude still gets English. Parley remembers any word you correct so it's spelled right next time.
It's one Rust binary: a background process with a mic, Claude Code hooks, and a GTK pill on Linux. It runs on Linux (Hyprland), macOS and Windows.
It was a really fun build, and Gradium's speech-to-text is fast enough that talking to Claude feels natural. The repo is at github.com/radiumcoders/p…
Alright, we teamed up with @GradiumAI for a builder challenge / hackathon 🚀
The idea is that you build something real with Gradium. It's free and open to everyone, and you can win some cool prizes.
🥇 First prize is a Raspberry Pi + 1M Gradium credits + lifetime access to unner-ups get 500k Gradium credits each and lifetime access to @active_builders
The brief drops in a few days, but you should save your spot now 👇
12
4
16
567
Active Builders retweeted
I built heckled.dev for the @active_builders x @GradiumAI hackathon.
Here's the idea. You paste a landing page URL, pick a heckler, and get roasted out loud for about 60-90 seconds.
Then you get a fix list you can paste straight into your AI to (hopefully) improve your landing page.
A headless Chrome screenshots your page and maps the headline, buttons, pricing, and proof. Claude reads all that and writes an eight-part stand-up set, with each bit pointing at the elements it mentions.
Gradium AI does the voice and each heckler (Jaded VC, Growth Bro, Creative Director, and Documentarian) is a voice I built with Gradium Voice Design, with its own pronunciation dictionary. It does French roasts too.
Gradium also returns word-level timestamps, and those run the whole player. The captions follow the voice, and the camera pans to a spotlight on whatever's being roasted at that moment.
It's one Next.js process with a SQLite queue. About a minute from URL to heckle.
It was a fun little project, and I got to try Gradium AI's tools, which was pretty awesome. The repo is at github.com/phillips-jon/h…
Here's the idea. You paste a landing page URL, pick a heckler, and get roasted out loud for about 60-90 seconds.
Then you get a fix list you can paste straight into your AI to (hopefully) improve your landing page.
A headless Chrome screenshots your page and maps the headline, buttons, pricing, and proof. Claude reads all that and writes an eight-part stand-up set, with each bit pointing at the elements it mentions.
Gradium AI does the voice and each heckler (Jaded VC, Growth Bro, Creative Director, and Documentarian) is a voice I built with Gradium Voice Design, with its own pronunciation dictionary. It does French roasts too.
Gradium also returns word-level timestamps, and those run the whole player. The captions follow the voice, and the camera pans to a spotlight on whatever's being roasted at that moment.
It's one Next.js process with a SQLite queue. About a minute from URL to heckle.
It was a fun little project, and I got to try Gradium AI's tools, which was pretty awesome. The repo is at github.com/phillips-jon/h…
Alright, we teamed up with @GradiumAI for a builder challenge / hackathon 🚀
The idea is that you build something real with Gradium. It's free and open to everyone, and you can win some cool prizes.
🥇 First prize is a Raspberry Pi + 1M Gradium credits + lifetime access to unner-ups get 500k Gradium credits each and lifetime access to @active_builders
The brief drops in a few days, but you should save your spot now 👇
4
1
12
493
Active Builders retweeted
typeui.sh is an amazing design layer for AI coding agents!
1. Design skills
2. UI prompts
3. Works with Claude, Codex & Cursor
Check it out!
1. Design skills
2. UI prompts
3. Works with Claude, Codex & Cursor
Check it out!
9
7
56
7,982
Today is the last day to signup for the Gradium AI hackathon! We're announcing all the details to people on the list later today 🚀
Last day to signup for the @GradiumAI x @active_builders hackathon! We'll be dropping the details later today 🚀
2
0
4
259
Active Builders retweeted
Co-organizing a builder challenge with @joncphillips: Active Builders x Gradium AI.
Free, open to everyone, teams welcome.
1st place wins a Raspberry Pi, 1M Gradium credits and Active Builders lifetime membership.
Sign up → activebuilders.dev/hackathon/grad…
Free, open to everyone, teams welcome.
1st place wins a Raspberry Pi, 1M Gradium credits and Active Builders lifetime membership.
Sign up → activebuilders.dev/hackathon/grad…
6
4
30
4,016
Active Builders retweeted
Alright, we teamed up with @GradiumAI for a builder challenge / hackathon 🚀
The idea is that you build something real with Gradium. It's free and open to everyone, and you can win some cool prizes.
🥇 First prize is a Raspberry Pi + 1M Gradium credits + lifetime access to unner-ups get 500k Gradium credits each and lifetime access to @active_builders
The brief drops in a few days, but you should save your spot now 👇
The idea is that you build something real with Gradium. It's free and open to everyone, and you can win some cool prizes.
🥇 First prize is a Raspberry Pi + 1M Gradium credits + lifetime access to unner-ups get 500k Gradium credits each and lifetime access to @active_builders
The brief drops in a few days, but you should save your spot now 👇
4
6
18
6,431