Assemble Labs – Hardware Brain for LLMs/IDEs
Hi HN friends, we're Nima (nimabanai) and Craig (cbschind) from Assemble Labs (https://assemblelabs.co) building the hardware context layer for AI to help you write better firmware faster. We’ve built an MCP server that plugs into any AI tool you’re using (Cursor, Claude Code, Gemini, etc.) and brings complete hardware context (schematics, datasheets, etc.) to your existing environment (new app fatigue is real...) with accuracy and in real time. Our goal is to make writing and debugging firmware on custom hardware faster and easier. Try out the free beta release:…
In plain words
Assemble Labs provides an MCP server that connects to AI coding tools like Cursor and Claude to supply hardware context including schematics and datasheets directly within existing environments. Designed for firmware developers working with custom hardware, it aims to speed up writing and debugging by making hardware documentation accessible in real time without requiring a separate application. The tool is available as a free beta.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN friends, we're Nima (nimabanai) and Craig (cbschind) from Assemble Labs (https://assemblelabs.co) building the hardware context layer for AI to help you write better firmware faster. We’ve built an MCP server that plugs into any AI tool you’re using (Cursor, Claude Code, Gemini, etc.) and brings complete hardware context (schematics, datasheets, etc.) to your existing environment (new app fatigue is real...) with accuracy and in real time. Our goal is to make writing and debugging firmware on custom hardware faster and easier. Try out the free beta release: https://app.assemblelabs.co and email me ([email protected]) or Craig ([email protected]) for any bugs, issues, suggestions, or anything else. Feedback is the most important thing for us right now and we’re only announcing this on HN. So only the free beta tier is available at the moment with no MCP call cap, please ignore the cap text on the website. We've spent our careers building hardware and consistently faced the same limitations with any AI tool we tried: - Generic answers: they lack knowledge of our specific board designs and hallucinate when there’s a knowledge gap. - Limited context: Windows max out after just a few datasheets, app notes, or SDK docs. - Poor technical comprehension: OCR fails on tables/diagrams, causing inconsistent answers which is unacceptable for complex board bring-up. We need a persistent hardware knowledge base that any agent, editor, or CLI can query for fast, accurate, repeatable answers. Our MCP ingests your schematics (must be KiCad for now, we’re working on native Altium and Cadence), datasheets for primary BOM components, and any additional documents (app notes, user manuals, etc.), then provides an MCP key you can plug into any AI tool. To be upfront about our free beta limitations: - KiCad only for native schematic parsing. Other EDA tool support coming soon. No firmware repo integration yet. - FastMCP backend (https://github.com/jlowin/fastmcp) with manual upload to AWS S3. On-prem/air-gapped/local/your-cloud options coming. Zero training on uploaded docs, even in beta. - No SOC 2/ISO27001 yet. In progress. We're building in public and want the community’s feedback on features, roadmap, and concerns so we can iterate quickly. Our long-term goal is to enable electrical engineers to write low-level firmware, and for software engineers to debug hardware issues. We want to be useful at the hardware-software interface: generating firmware→deploying it on board→running tests→debugging results→regenerating firmware. What do you guys think? Feedback, suggestions, concerns, harsh criticisms, feature requests, everything is welcome! For the firmware application of our tool: - What chipsets do you want to see supported? What peripherals are giving you headaches in bring-up? - What other functions should the MCP expose in addition to the ones we’ve built in? - Do you see other applications of our “hardware brain” outside of firmware development that seem interesting? We're shipping early and building this with you out in the open. Help us make the tool you actually want.
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 · 17d 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, October 2025
the whole month →
- SA
I went down the rabbit hole on a side project and ended up building this: Strange Attractors(https://blog.shashanktomar.com/posts/strange-attractors). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to…
AI · Oct 2025 · blog.shashanktomar.com
- ASAutism Simulator▲779
Hey all, I built this. It’s not trying to capture every autistic experience (that’d be impossible). It’s based on my own lived experience as well as that of friends on the spectrum. I'm trying to give people a feel for what masking, decision fatigue, and burnout can look like day-to-day. That’s hard to explain in words, but easier to show through choices and stats. I'm not trying to "define autism". I’ve gotten good feedback here about resilience, meds, and difficulty tuning. I’ll keep tweaking it. If even a few people walk away thinking, "ah, maybe that’s why my coworker struggles in those…
Life & fun · Oct 2025 · autism-simulator.vercel.app
