Khirby
The self-hosted CRM that respects your data
What it does
Khirby is an open-source, self-hosted CRM for B2B teams who want full control over their data. Contacts, pipeline, work boards, email, and a plugin SDK — all in one Docker deploy. No SaaS fees, no vendor lock-in, your server.
Khirby is a self-hosted CRM with Ask Khirby inside the app—shaped around how you sell and work. Website forms become leads, mail sits on the deal, and the data stays on a server you run.
Ask Khirby works inside the CRM—on contacts, deals and boards—so the tool bends to how you sell, not the other way around. Ask Khirby is the assistant built into Khirby. Open it from the sidebar or the command palette: update contacts and deals, read mail, turn on Marketplace tools, or add a simple Self Build tool—on your own key. Compose drafts mail; MCP is the door for an external agent. Neither is an autopilot. Ask is part of the product, not a bolt-on chat. It uses the same key as AI Compose. A person still sends mail; Ask does not delete records. Compose drafts replies, the first mail to a lead, and newsletter bodies on any OpenAI-compatible endpoint—including a model on your own…from khirby.com
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com