Headless Everything for Personal AI
markusw
19 points
4 comments
April 18, 2026
Related Discussions
Found 5 related stories in 65.5ms across 4,930 title embeddings via pgvector HNSW
- Show HN: Phantom – Open-source AI agent on its own VM that rewrites its config mcheemaa · 18 pts · March 30, 2026 · 57% similar
- Show HN: I built an OS that is pure AI evanbarke · 18 pts · March 28, 2026 · 57% similar
- Closed Source AI = Neofeudalism 0x79de · 38 pts · March 31, 2026 · 55% similar
- An AI robot in my home kukanani · 17 pts · April 07, 2026 · 55% similar
- Things I've Done with AI shepherdjerred · 80 pts · March 09, 2026 · 55% similar
Discussion Highlights (3 comments)
stephenlf
Interesting ideas. I would love programmatic access to everything, though I think it’s a stretch to expect this within a year. Personal AI agents are still niche. I suspect the timeline will look something like this: 1. 1-2 years, Google and Microsoft expand the capabilities of their OS-integrated apps, including support for integrating with external apps. Microsoft rolls out “Cortana Communications Protocol” (CCP), a closed-source alternative to MCP that integrates with Copilot. People hate it. 2. 3-5 years, people become more accustomed to personal AI agents. 3. 7 years, Apple rolls out “Apple Intelligence Link Protocol” (AILP) Apple’s take on CCP and MCP. It becomes the de facto standard. 4. 10 years, AILP, CCP, and MCP converge into a single standard. 80% of backend web frameworks support this standard out of the box. All phones support it. Millenials everywhere are constantly confounded and befuddled by these AI personal assistants. ——— It’s funny you mention the Salesforce CLI. I develop a Salesforce-based app for work. My agents and I likely run the `sf` command several hundred times a day.
xnx
First line: "It’s pretty clear that apps and services are all going to have to go headless: that is, they will have to provide access and tools for personal AI agents without any of the visual UI that us humans use today." Nope. Not clear at all. Agents are good and getting even better about controlling GUIs like the browser and desktop apps. Time and time again we've seen "dumb pipes" win. It ends up being much easier to build a smarter agent than rewrite every piece of software. In the real world, this is why self-driving cars are a better option that replacing every road, street, highway, and avenue with rail.
AndrewDucker
On Windows the accessibility APIs give you this. And as these same APIs are used for screen readers, automated testing, and AI access, supporting them is definitely worthwhile.