Nicheloom visits: 58,094 all-time · 7,637 in the last 7 days

The opportunity tracker for new startups.

Today: 1,953 launches · Niche of the day: specialized calculation tools · See what launched today →

Building a full agentic harness around a 4B model is hard

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

Around 3 months ago, we were thinking why none of the iPhone apps running an LLM are built as a full harness (as in inference + agentic loop + context management + tools + MCP servers and etc.). It became more interesting when we noticed even the new Siri is not fully on device (and not available in EU for that matter).Having built a few agentic products around a custom harness in the past, we thought this shouldn't be that hard. well, we underestimated how "dumb" a 4B model can be, especially when it comes to tool calling. :DWe tried 8 different models and we settled on Qwen 3.5 4B and we used every trick we knew to make this model behave. well, it works!It's not gonna win in any intelligence or speed benchmark, but it can do actual useful work and it really is an on device, private, full agentic harness. That said, you can still connect your OpenRouter or OpenAI API keys if that's what you prefer.Please go check it out :) You need an iPhone 15 pro or above.

HN · launched Aug 19, 2026 · 5 upvotes (top 87%) · 0 views

Niche: ai agent runtime environments · 745 launches, 498 in the last 7 days ▲ +916% · Explore this niche →

Category and tags
  • Horizontal
  • Agent / copilot
  • Developer
  • AI-native
  • Hobby / open-source project

Visit website ↗ Source listing ↗

More like this: all 745 launches in ai agent runtime environments →

Could you build this?

No Running a local quantized 4B model on an iPhone while handling low-memory constraints, CoreML/Metal optimization, MCP tool-calling protocols, and background agent loops requires specialized iOS machine learning systems expertise.

What it would actually take: A real build requires an iOS app written in Swift/C++ leveraging Apple's MLX Swift or llama.cpp/executorch via Metal, fine-tuning or prompt-engineering a 4B model (like SmolLM2 or Phi/Qwen) to reliably emit structured MCP-compliant tool calls within tight 2-3GB memory ceilings, and deep integrations with EventKit, Contacts, and Shortcuts. The hardest parts are preventing iOS OS memory kills (jetsam) during multi-turn generation and context compression while running local inference.

Discussion

No comments on this launch.

Competitors

Other products that read as similar to this one : 238 launches clear the similarity bar, closest 8 shown.

Attention rank: #219 of 239 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 293 days after the earliest competitor.

Related data

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.