AI interface for macOS. Write emails, Slack replies, Jira tickets, proofread, chat with documents ...with 350 supported models!

Joined February 2024
79 Photos and videos
Pinned Tweet
22 Jul 2025
🚀 Kerlig 2.3.0 is here! Now you can capture content directly from browser tabs (even behind login walls!), plus read structured data from Apple Mail, Notes, Notion & Slack. ✨ Also new: • Latest AI models • Auto-close option • Custom actions out of beta • Longer model names
3
1
15
3,625
In Kerlig 2.6.0 you can save attachments (websites, YouTube transcripts, app content) to disk as Markdown. Enjoy! ツ
1
5
798
Big milestone! Kerlig is now available on @Setapp 💪
6
1,241
New update 2.5.3! Kerlig now properly extracts ▶️YouTube video transcripts after their recent update. Refreshed the model lineup: GPT-5.4, Claude Sonnet 4.6, Claude Opus 4.6, Gemini 3.1 Pro (Preview), and Gemini 3.1 Flash-Lite (Preview)
1
4
301
Kerlig retweeted
New release is here! Updated with the latest AI models: 🤖 Anthropic: Opus 4.5, Sonnet 4.5, Haiku 4.5 🧠 OpenAI: GPT-5.2, GPT-5.1 ✨ Google: Gemini 3 Pro, Gemini 3 Flash ⚡ Groq: LLaMA 3.3 70b Versatile Enjoy!
2
1
5
1,748
New release is here! Updated with the latest AI models: 🤖 Anthropic: Opus 4.5, Sonnet 4.5, Haiku 4.5 🧠 OpenAI: GPT-5.2, GPT-5.1 ✨ Google: Gemini 3 Pro, Gemini 3 Flash ⚡ Groq: LLaMA 3.3 70b Versatile Enjoy!
2
1
5
1,748
24 Dec 2025
customer support 👏
24 Dec 2025
how many hours of customer support it has saved me it's just unbelievable! direct integration with Apple Mail is :chief-kiss:
2
344
17 Nov 2025
Ready for Black Friday deals?
17 Nov 2025
The two best AI apps on apps.deals -- @KerligAI and @Bolt__AI Have you added AI to your daily workflow?
2
2
452
Kerlig retweeted
22 Sep 2025
Just ran some benchmarks on Apple Foundation Model and thought I'd share the results: Setup: ✦ MacBook Pro M1 Max, 32GB RAM ✦ Using @KerligAI app Performance: ✦ Time to First Token (TTFT) with 3,088 input tokens cold start: 7.32 seconds ✦ Tokens per Second (TPS): 33 tokens/sec Quick thoughts: The cold start time is pretty reasonable for on-device inference, and 33 TPS is solid. It doesn't feel slow at all. I'd say "acceptable", though I can't call it fast. Anyone else testing Apple's Foundation Model?
1
1
11
1,798
22 Sep 2025
Exciting update! 🍏 Kerlig 2.5.0 now supports Apple Foundation Model (on-device) on macOS 26! Use your favorite Kerlig actions with the same model used by Apple Intelligence!
4
6
2,685
12 Sep 2025
Reached 2nd place on Uneed! Thank you 💪
12 Sep 2025
Here's yesterday's podium, congratulations 🙌🏻 🥇 nano banana - 58 points 🥈 Kerlig (@KerligAI) - 51 points 🥉 Context Engineer MCP (@alessiocarra_) - 40 points
1
393
11 Sep 2025
Support Kerlig on Uneed today!
11 Sep 2025
LAUNCH 🚀 Kerlig is now live on Uneed! Likely the best AI quick chat you can get on macOS I appreciate your support (ᵔᴥᵔ)
1
356
2 Sep 2025
Summarize, explain, translate, behind the scenes:
2 Sep 2025
How Kerlig summarizes websites? I share the secret sauce: 1. First, it reads HTML source directly from the browser using AppleScript, so whatever page/app you see, Kerlig can see it too. This can only be done by a desktop app. When you see Claude or ChatGPT "Reading/Searching web," they do it anonymously from their servers. This means they can be easily blocked, and most importantly, they can't see what you see as a logged-in user, like social media, paid articles, web apps, etc. 2. Next, it strips out ads, popovers, overlays, footers, and other distractions. The goal is to provide LLMs only with what's important – otherwise, it's easy to make the model distracted and confused, which will result in mediocre output. 3. Finally, it converts cleaned-up HTML code to Markdown format. LLMs love Markdown – it's their native format, easiest to understand. It's basically plain text with formatting (also supports tables, images, links, etc.). At this point asking LLMs to summarize, explain, translate is a piece of cake. That’s the “secret sauce”: Kerlig makes web content digestible so you get sharp, accurate summaries without the fluff.
322
29 Aug 2025
terminal buddy 🤌
29 Aug 2025
Best buddies 🤝 @KerligAI, who knew you can increase your server throughput 5x by changing the TCP congestion algo from `cubic` to `bbr`
335
11 Aug 2025
Analyze Trustpilot user reviews and find ideas for new SaaS products! ⭐️
11 Aug 2025
User reviews are a goldmine for new SaaS ideas! See how I »chat with 500 user reviews« on Trustpilot with kerlig.com ↘️ Prompt: Analyze YNAB reviews, pay attention to missing features and complaints and create a list of features that an YNAB alternative should have to fill in the blanks and pain points.
284