I made a Raspberry with Qwen my local car AI
Details
- External ID
- 49435675
- Source
- HN
- Company
- —
- Product
- I made a Raspberry with Qwen my local car AI
- Website domain
- github.com
- Launched
- Aug. 25, 2026
- Cohort
- —
- Upvotes
- 146
- Upvotes percentile
- 0.9543010752688172
- Tags
- —
- Fetched at
- Sept. 10, 2026, 5:32 a.m.
- Updated at
- Sept. 10, 2026, 5:32 a.m.
Description
Found that you can actually run a 35B Qwen model on a Pi with very impressive intelligence and stability. Built connectors for car ODB to read all about car internals, and manufacturer's cloud service for stuff like changing AC or opening/ locking doors. Gave it info such as the full car manual. And then hooked it up with my other agents in our discussion room!So now it can answer car questions such as "when should I add oil and what kind of oil?" and help you fully offline, and when online talk with the agent family that includes all the most powerful models so they know how the car is, plan new features and develop itself with them.For example, if car breaks and can't move the car agent informs my agent family and they can already look for a suitable train ticket without me needing to check things or do something.
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- —
- Function
- Agent / copilot
- Audience
- B2C
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- local ai assistant for cars
- Manually corrected
- False
Could you build this?
Partial Interfacing with physical hardware like car OBD-II buses, reverse-engineering proprietary vehicle manufacturer APIs, and optimizing large LLM inference on resource-constrained Raspberry Pi hardware requires specialized embedded systems and automotive knowledge.
What it would actually take: A working system requires an embedded Linux environment on a Raspberry Pi 5 connecting to an OBD-II adapter via CAN bus or ELM327 UART/Bluetooth. The hard parts are handling CAN bus protocol variations, reverse-engineering proprietary OEM telematics cloud APIs (with auth tokens and encryption), and running quantized 35B models (e.g., via llama.cpp or vLLM with aggressive offloading/RAM swap). Building it demands automotive CAN/OBD engineering expertise and low-level hardware performance tuning.
Discussion
20 comments analyzed.
Competitors mentioned: Ornith, Google search, Gemma (smaller models), Qwen (smaller variants)
Concerns raised: Response speed could be faster, Q3 model accuracy issues and hallucinations with BF16 precision, Limited to 2 cars (Mercedes) - narrow device coverage, Difficulty understanding Q3 accuracy claims vs. real-world performance
Feature requests: Add more car manufacturer cloud integrations for expanded device coverage, Proactive agent actions based on user schedule and preferences, Clear status indicators for use cases (proven/testing/planned), Automatic climate control activation before entering car based on preferences
Competitors
Other products that read as similar to this one — 77 launches clear the similarity bar, closest 8 shown.
Attention rank: #5 of 78 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 300 days after the earliest competitor.
- Sageling · hn · 2026-09-04 · 7 upvotes · similarity 0.46
- I built a system to drive my RC car from anywhere in the world · hn · 2026-01-19 · 6 upvotes · similarity 0.43
- Building a full agentic harness around a 4B model is hard · hn · 2026-08-19 · 5 upvotes · similarity 0.42
- Qwen 3.5 running on a $300 Android phone · hn · 2026-03-03 · 6 upvotes · similarity 0.41
- PHNTM One · ph · 2026-09-29 · 2 upvotes · similarity 0.41
- I used AI to recreate a $4000 piece of audio hardware as a plugin · hn · 2026-01-03 · 160 upvotes · similarity 0.39
- Mozilla.ai introduces Clawbolt, an AI Assistant for the trades · hn · 2026-03-03 · 12 upvotes · similarity 0.38
- Bike4Mind · hn · 2026-07-07 · 5 upvotes · similarity 0.37
Other launches for this product
- No other launches for this product.