KerligAI
@kerlig.com
AI interface for macOS. Write emails, Slack replies, Jira tickets, proofread, chat with documents ...with 350+ supported models!
www.kerlig.com
www.kerlig.com
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!
September 22, 2025 at 5:00 AM
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!
New on the Blog! 🤓 The 10-Minute Market Research Method That Actually Works
August 19, 2025 at 6:51 PM
New on the Blog! 🤓 The 10-Minute Market Research Method That Actually Works
🚀 Kerlig v2.4.0 now integrates with Cerebras - the world's fastest AI inference platform!
⚡ Lightning-fast speeds
🆓 Generous free tier
🤖 Access to Llama 4 Scout, Qwen 3 Coder 480B, and more cutting-edge models
Making AI workflows more efficient than ever!
#AI #MachineLearning #Kerlig
⚡ Lightning-fast speeds
🆓 Generous free tier
🤖 Access to Llama 4 Scout, Qwen 3 Coder 480B, and more cutting-edge models
Making AI workflows more efficient than ever!
#AI #MachineLearning #Kerlig
August 5, 2025 at 3:11 PM
🚀 Kerlig v2.4.0 now integrates with Cerebras - the world's fastest AI inference platform!
⚡ Lightning-fast speeds
🆓 Generous free tier
🤖 Access to Llama 4 Scout, Qwen 3 Coder 480B, and more cutting-edge models
Making AI workflows more efficient than ever!
#AI #MachineLearning #Kerlig
⚡ Lightning-fast speeds
🆓 Generous free tier
🤖 Access to Llama 4 Scout, Qwen 3 Coder 480B, and more cutting-edge models
Making AI workflows more efficient than ever!
#AI #MachineLearning #Kerlig
Kerlig 2.2.0 release! ⚡️
→ Speed up your workflow even more by using keyboard shortcuts for Insert in... V, Copy to clipboard C and Regenerate R
→ When using OpenRouter, the app name (Kerlig) is now displayed on your OpenRouter dashboard
→ Update for Gemini 2.5 Pro model (from 03-25 to 05-06)
→ Speed up your workflow even more by using keyboard shortcuts for Insert in... V, Copy to clipboard C and Regenerate R
→ When using OpenRouter, the app name (Kerlig) is now displayed on your OpenRouter dashboard
→ Update for Gemini 2.5 Pro model (from 03-25 to 05-06)
May 19, 2025 at 4:04 PM
Kerlig 2.2.0 release! ⚡️
→ Speed up your workflow even more by using keyboard shortcuts for Insert in... V, Copy to clipboard C and Regenerate R
→ When using OpenRouter, the app name (Kerlig) is now displayed on your OpenRouter dashboard
→ Update for Gemini 2.5 Pro model (from 03-25 to 05-06)
→ Speed up your workflow even more by using keyboard shortcuts for Insert in... V, Copy to clipboard C and Regenerate R
→ When using OpenRouter, the app name (Kerlig) is now displayed on your OpenRouter dashboard
→ Update for Gemini 2.5 Pro model (from 03-25 to 05-06)
Mathematical expressions are now supported in Kerlig 2.1.0 ⚡️
May 14, 2025 at 10:13 AM
Mathematical expressions are now supported in Kerlig 2.1.0 ⚡️
Kerlig 2.0.1 ⚡️ is now released with a few updates based on feedback, following the major 2.0 release.
- Return focus to the app from which Kerlig was launched after closing the Kerlig window with the Escape key
- Remove Presets content length limit (was 10,000 characters)
- Return focus to the app from which Kerlig was launched after closing the Kerlig window with the Escape key
- Remove Presets content length limit (was 10,000 characters)
May 12, 2025 at 10:22 AM
Kerlig 2.0.1 ⚡️ is now released with a few updates based on feedback, following the major 2.0 release.
- Return focus to the app from which Kerlig was launched after closing the Kerlig window with the Escape key
- Remove Presets content length limit (was 10,000 characters)
- Return focus to the app from which Kerlig was launched after closing the Kerlig window with the Escape key
- Remove Presets content length limit (was 10,000 characters)
Kerlig 2.0 is here with Custom Actions ⚡️⚡️⚡️
May 7, 2025 at 8:29 AM
Kerlig 2.0 is here with Custom Actions ⚡️⚡️⚡️
The art and the science. The thinking and the doing✌️
April 12, 2025 at 5:12 PM
The art and the science. The thinking and the doing✌️
You can add custom models, such as Gemini 2.5, to Kerlig at any time. Use the name "gemini-2.5-pro-exp-03-25" when adding.
Gemini 2.5 Pro excels in advanced reasoning, complex problem-solving, coding, and web app development. ✨
Here is a quick demo:
Gemini 2.5 Pro excels in advanced reasoning, complex problem-solving, coding, and web app development. ✨
Here is a quick demo:
April 4, 2025 at 12:14 PM
You can add custom models, such as Gemini 2.5, to Kerlig at any time. Use the name "gemini-2.5-pro-exp-03-25" when adding.
Gemini 2.5 Pro excels in advanced reasoning, complex problem-solving, coding, and web app development. ✨
Here is a quick demo:
Gemini 2.5 Pro excels in advanced reasoning, complex problem-solving, coding, and web app development. ✨
Here is a quick demo:
WIP → Custom Actions! ✨ Need your feedback – what would you like to add/remove here?
March 25, 2025 at 9:30 PM
WIP → Custom Actions! ✨ Need your feedback – what would you like to add/remove here?
New on the Blog → Guide to Perplexity Deep Research with examples 🧠
Includes SaaS market research, travel planning, quantum computing...
Includes SaaS market research, travel planning, quantum computing...
March 24, 2025 at 10:02 PM
New on the Blog → Guide to Perplexity Deep Research with examples 🧠
Includes SaaS market research, travel planning, quantum computing...
Includes SaaS market research, travel planning, quantum computing...
🚀 Thrilled to announce Perplexity is now a first-class integration in Kerlig 1.8.0!
✨ Web search with citations
💡 Transparent reasoning
⌨️ CLI support for Team License owners
Plus new keyboard shortcuts for model & preset selection, better streaming, and support for macOS 10.15+
✨ Web search with citations
💡 Transparent reasoning
⌨️ CLI support for Team License owners
Plus new keyboard shortcuts for model & preset selection, better streaming, and support for macOS 10.15+
March 18, 2025 at 1:27 PM
🚀 Thrilled to announce Perplexity is now a first-class integration in Kerlig 1.8.0!
✨ Web search with citations
💡 Transparent reasoning
⌨️ CLI support for Team License owners
Plus new keyboard shortcuts for model & preset selection, better streaming, and support for macOS 10.15+
✨ Web search with citations
💡 Transparent reasoning
⌨️ CLI support for Team License owners
Plus new keyboard shortcuts for model & preset selection, better streaming, and support for macOS 10.15+
Excited to announce Kerlig 1.7.0 with revamped AI integrations and model management!
March 10, 2025 at 4:30 PM
Excited to announce Kerlig 1.7.0 with revamped AI integrations and model management!
New on the Blog → Prompt Library for DeepSeek models ✨
Includes blog writing, proofreading, marketing, and more.
Includes blog writing, proofreading, marketing, and more.
March 1, 2025 at 4:00 AM
New on the Blog → Prompt Library for DeepSeek models ✨
Includes blog writing, proofreading, marketing, and more.
Includes blog writing, proofreading, marketing, and more.
The initial model load time is a few seconds, and then it generates text at a decent speed, this took approximately 2 seconds. GPU memory is, as expected, maxing out when generating.
February 15, 2025 at 11:06 AM
The initial model load time is a few seconds, and then it generates text at a decent speed, this took approximately 2 seconds. GPU memory is, as expected, maxing out when generating.
Taking local model "Mistral Small 24b" via Ollama for a spin!
Overall, it has decent speed and accuracy! 👏
Sometimes it adds additional text even though the "fix spelling" action has an explicit prompt saying not to add anything.
Tested on M1 Max (32GB).
Overall, it has decent speed and accuracy! 👏
Sometimes it adds additional text even though the "fix spelling" action has an explicit prompt saying not to add anything.
Tested on M1 Max (32GB).
February 15, 2025 at 11:06 AM
Taking local model "Mistral Small 24b" via Ollama for a spin!
Overall, it has decent speed and accuracy! 👏
Sometimes it adds additional text even though the "fix spelling" action has an explicit prompt saying not to add anything.
Tested on M1 Max (32GB).
Overall, it has decent speed and accuracy! 👏
Sometimes it adds additional text even though the "fix spelling" action has an explicit prompt saying not to add anything.
Tested on M1 Max (32GB).
If you want to fix spelling & grammar with local models, I found the best results using Gemma 9b and Llama 3.2 11b models. Smaller models can get confused easily, while models with more than 14b are starting to be quite slow, so 9b and 11b are kind of a sweet spot.
February 14, 2025 at 4:09 PM
If you want to fix spelling & grammar with local models, I found the best results using Gemma 9b and Llama 3.2 11b models. Smaller models can get confused easily, while models with more than 14b are starting to be quite slow, so 9b and 11b are kind of a sweet spot.
Kerlig 1.6.2 🚀 adds support for sending images to Ollama vision models, which allows on-device document analysis, extracting text, understanding charts/diagrams, and creating descriptions for visual content.
February 10, 2025 at 8:45 PM
Kerlig 1.6.2 🚀 adds support for sending images to Ollama vision models, which allows on-device document analysis, extracting text, understanding charts/diagrams, and creating descriptions for visual content.
🚀 New on the Blog → Running Gemini 2.0 Models on macOS with 2M token context, 90% cost savings vs competitors, and mind-blowing performance.
Learn how to run these powerhouse models right on your Mac with @Kerlig.com in our latest guide 🧵
Learn how to run these powerhouse models right on your Mac with @Kerlig.com in our latest guide 🧵
February 8, 2025 at 9:55 PM
🚀 New on the Blog → Running Gemini 2.0 Models on macOS with 2M token context, 90% cost savings vs competitors, and mind-blowing performance.
Learn how to run these powerhouse models right on your Mac with @Kerlig.com in our latest guide 🧵
Learn how to run these powerhouse models right on your Mac with @Kerlig.com in our latest guide 🧵
🚀 Kerlig 1.6.1 release! Check out the latest update featuring new Google Gemini models:
1️⃣ Gemini 2.0 Pro
2️⃣ Gemini 2.0 Flash
3️⃣ Gemini 2.0 Flash-Lite
4️⃣ Gemini 2.0 Flash Thinking
Plus, Kerlig menu bar icon now alerts you when update is available & bug fixes!
1️⃣ Gemini 2.0 Pro
2️⃣ Gemini 2.0 Flash
3️⃣ Gemini 2.0 Flash-Lite
4️⃣ Gemini 2.0 Flash Thinking
Plus, Kerlig menu bar icon now alerts you when update is available & bug fixes!
February 8, 2025 at 4:16 PM
🚀 Kerlig 1.6.1 release! Check out the latest update featuring new Google Gemini models:
1️⃣ Gemini 2.0 Pro
2️⃣ Gemini 2.0 Flash
3️⃣ Gemini 2.0 Flash-Lite
4️⃣ Gemini 2.0 Flash Thinking
Plus, Kerlig menu bar icon now alerts you when update is available & bug fixes!
1️⃣ Gemini 2.0 Pro
2️⃣ Gemini 2.0 Flash
3️⃣ Gemini 2.0 Flash-Lite
4️⃣ Gemini 2.0 Flash Thinking
Plus, Kerlig menu bar icon now alerts you when update is available & bug fixes!
🚀 New release: Kerlig™ 1.6.0!
Added support for remote team deployments with CLI commands for license & API key management. New default models added to Ollama: DeepSeek R1, Llama 3.1, Qwen 2.5, Phi-4. Plus, fixed Anthropic prompt caching issue.
Enjoy!
Added support for remote team deployments with CLI commands for license & API key management. New default models added to Ollama: DeepSeek R1, Llama 3.1, Qwen 2.5, Phi-4. Plus, fixed Anthropic prompt caching issue.
Enjoy!
February 6, 2025 at 12:43 PM
🚀 New release: Kerlig™ 1.6.0!
Added support for remote team deployments with CLI commands for license & API key management. New default models added to Ollama: DeepSeek R1, Llama 3.1, Qwen 2.5, Phi-4. Plus, fixed Anthropic prompt caching issue.
Enjoy!
Added support for remote team deployments with CLI commands for license & API key management. New default models added to Ollama: DeepSeek R1, Llama 3.1, Qwen 2.5, Phi-4. Plus, fixed Anthropic prompt caching issue.
Enjoy!
You can run full DeepSeek R1 *671B* in Kerlig via @openrouter.bsky.social, plus its 4 other versions 👇
January 29, 2025 at 3:13 PM
You can run full DeepSeek R1 *671B* in Kerlig via @openrouter.bsky.social, plus its 4 other versions 👇
🧑🐋 In Kerlig 1.5.4, we've added the DeepSeek R1 70b model to Groq!
PS DeepSeek models are also available through OpenRouter and Ollama for running locally.
Cheers!
PS DeepSeek models are also available through OpenRouter and Ollama for running locally.
Cheers!
January 28, 2025 at 10:17 PM
🧑🐋 In Kerlig 1.5.4, we've added the DeepSeek R1 70b model to Groq!
PS DeepSeek models are also available through OpenRouter and Ollama for running locally.
Cheers!
PS DeepSeek models are also available through OpenRouter and Ollama for running locally.
Cheers!
New post on the Blog! 🚨
Run DeepSeek R1 locally on macOS
Run DeepSeek R1 locally on macOS
January 27, 2025 at 11:23 AM
New post on the Blog! 🚨
Run DeepSeek R1 locally on macOS
Run DeepSeek R1 locally on macOS