Dev Systems

Show HN: Claw Cash – Money agents can trust, and verify. Stablecoins in. BTC out

Hey HN, I built Claw Cash, a CLI that gives autonomous agents a Bitcoin wallet. Humans pay in stablecoins (USDC/USDT on Polygon, Arbitrum, Ethereum), the agent auto-converts to Bitcoin and holds it as treasury. When the agent needs to pay for compute or other services, it swaps back on the fly.The core thesis is that an LLM can cryptographically verify Bitcoin. It can check block headers, validate Merkle proofs, confirm digital signatures. It cannot independently verify that Circle has doll

Instance segmentation model that extracts 3D geometry from 2D floor plans

Hey HN,I am an ML Engineer and a full-stack software engineer. For the past few weekends, I have been working on a pipeline to solve a PropTech problem: turning messy, highly occluded 2D floor plans into clean, structured data for 3D extrusion. Originally demoed for a firm hiring for the role.The Problem: If you try to use standard object detection (bounding boxes) or basic OCR (tested Qwen, DeepSeek) on architectural plans, it fails instantly. Walls intersect, doors swings and dimension lines h

Show HN: Hardware and software safety standard for AI and Robots (15 patents)

I'm a solo inventor in rural Pennsylvania. Over 13 days in February 2026, I filed 15 provisional patent applications (134 claims) with the USPTO covering a full-stack safety and governance architecture for AI systems.The patents break into three domains:Hardware enforcement (4 PPAs, 33 claims): A dedicated safety processor on its own power rail controls whether AI compute receives electricity. AI boots only after safety completes self-test. During operation, the safety processor monitors AI

Show HN: Raypher–eBPF-based runtime security and hardware identity for AI agents

Hey HN,I’m the founder of Raypher . We are building a kernel-level execution guard and cryptographic identity layer specifically designed for autonomous AI agents(opencalw). curent AI agents(open claw) are big security risks our Mission is to make a security feture that will enable developers to make agents and ship them faster without worrying about security risks The Problem: Right now, the agentic ecosystem (OpenClaw, LangChain, MCPs) is giving LLMs "hands" with almost zero runtime

Seeking a Front End Engineer Role

Location: India Remote: Yes!, but can do on-site/hybrid in Pune Role: Frontend/Software/Founding engineer full-time Willing to relocate: Yes, but want visa sponsorship. Technologies: Languages & Frameworks: TypeScript, JavaScript, React, Next.js, Node.js Databases & State: MongoDB, SQL (PostgreSQL/MySQL), Redux Toolkit, React Context API UI & Frontend: Material-UI (MUI), Tailwind CSS, SCSS, HTML5/CSS3, Responsive UI/UX

Show HN: A Vaadin Algebra and Calculus Solver Built with AI Assistance

Hi HN,I’d like to share a side project that has gradually become my main creative outlet: The Algebrator, a web-based algebra and calculus solver I built using Java, Spring Boot, Vaadin 24, and a symbolic math engine under the hood.It started as a personal attempt to revisit the math I loved in middle/high school, but it evolved into a multi-year design experiment in AI-augmented software engineering. I built and iterated on this app using a paired-programming workflow with LLMs (ChatGPT +

Ask HN: In the Age of AI, How Do I Grow as a Software Engineer?

I'm 3.5 years into my career. I was able to enjoy the first 10 months of it ignorant of the storm LLMs / agentic development would bring.The never ending promise of my job being automated away is soul crushing, especially considering I made a career change & got a 2nd BS degree in computer science to get into the software space.I'm really at a loss given how bleak things are made out to seem and its really crushed my motivation. I don't have a lot of senior engineers arou

The Reason Robotics DevOps Is Failing to Scale

In the robotics industry, the transition from manual "bespoke" workflows to standardized Continuous Integration and Continuous Deployment (CI/CD) is a critical requirement for scaling operations. Robotics CI/CD involves automating the build, testing, and distribution of software specifically for heterogeneous hardware, such as NVIDIA Jetson or other edge devices.Robotics CI/CD: Key Requirements:Hardware <-> Software Alignment: Unlike traditional cloud CI/CD, r

RCCLX: Innovating GPU communications on AMD platforms

We are open-sourcing the initial version of RCCLX – an enhanced version of RCCLthat we developed and tested on Meta’s internal workloads. RCCLX is fully integrated with Torchcomms and aims to empower researchers and developers to accelerate innovation, regardless of their chosen backend.Communication patterns for AI models are constantly evolving, as are hardware capabilities. We want to iterate on collectives, transports, and novel features quickly on AMD platforms. Earlier, we developed and op

Microservices Platforms - part 5: Observability platform

This is the fifth article in a series based on my QCon San Francisco 2025 talk Microservices Platforms: When Team Topologies Meets Microservices Patterns.The articles in the series are: Microservices Platforms - part 1: Overview Microservices Platforms - part 2: Service foundation platform Microservices Platforms - part 3: Security platform Microservices Platforms - part 4: Infrastructure services platform Microservices Platforms - part 5: Observability platformThis article describes the Ob

SHADOWING | C1 English (IT) | Monitoring distributed systems

In this shadowing session, follow along with two software engineers, Zoe and Gianna, as they discuss the topic "Monitoring ...

Show HN: Prothon – docs-first Python project generator for AI development

Prothon is a Python project generator that scaffolds a uv-based project with eight quality tools (ruff, ty, pytest, hypothesis, mutmut, bandit, vulture, complexipy) and a documentation-driven workflow for AI coding agents.The problem it solves: AI assistants lose context between sessions and drift from your decisions as context windows fill up. Prothon addresses this with three ideas:1. A three-level doc hierarchy (SPEC, DESIGN, PATTERNS) where each level scopes a single concern and higher alway

Show HN: Maestro App Factory – FOSS Agentic Engineering Orchestrator

Hi HN,For the last few months I’ve been working on Maestro App Factory, a free and open source tool for using AI agents to build software. It’s not a generic orchestrator: it implements agents with distinct roles and functionality, organizes them into a team, manages their work, and enforces highly opinionated tooling, workflows, and constraints in software.The core ideas are simple:- LLMs act like human engineers. LLMs are trained on human artifacts and exhibit human-like behaviors (inclu

Show HN: MuonTickets Git-native ticketing for AI agents and parallel development

I built MuonTickets, a Git-native, file-based ticketing system designed for AI agents and high-parallel development workflows.Instead of using external issue trackers, tickets live directly inside the repository as Markdown files (/tickets/T-000123.md). State changes are commits. Validation runs in pre-commit and CI.The idea is simple:One ticket = one fileStrict lifecycle: ready → claimed → needs_review → doneDependency-aware task pickingWIP limits enforcedmt pick lets agents self-sele

I'm Building OpenClaw Skills for Nonprofit RBM Logic Models

For years, I have worked in results-based management, supporting nonprofit and development programs through manual activities design and implementation.After that, I began using a dedicated GPT tool to support this work and improve consistency in early-stage analysis and drafting, for example https://Inkd.in/dbmBAXMBI have now created and am actively piloting the next step with OpenClaw autonomous sub-agents, including this focused skill for nonprofit RBM logic model development:

Show HN: Docdex – A local tool to reduce LLM tokens and make agents smarter

Hi HN,I use LLMs every day for software development, and wanted to have a better experience by reducing the token usage and providing digested information about the codebase to the agent.So I built Docdex. The idea was simple: a local, persistent layer that preprocesses and structures your project so the model can spend its context window on the actual problem, not on rediscovering what already exists.It started as a document indexer in Rust, built on Tantivy for proper ranked full-text search.T

Ask HN: How do you employ LLMs for UI development?

I have found a workflow that makes Claude a fantastic companion for most of the work involved in fullstack web development. The exception I find to be the most significant limitatipn to productive potential however, is interface development and UX. Curious to hear if anyone has relevant experience, or found any good approaches to this?

Show HN: A macOS toolbar app that resolves issues in your GitHub repos

InsomniDev is a MacOS toolbar app that can save you time and money. It wakes up your machine on a set schedule, finds issues in a target GitHub repo that you've labeled as eligible, and attempts to solve them using agentic CLIs. Then it opens a PR. You wake up to draft solutions ready for review. It leverages the existing command line tools on your machine to do this, so it’s extremely lightweight. Everything runs right on your machine.As of now it supports Claude Code and Gemini. Enable th

Show HN: Microterm runs Linux VM in any browser tab via WASM, RISCV64 emulation

Microterm is a fully compliant Linux virtual machine that runs in any browser tab. It is designed for real development and operations workflows, not demo-only terminal output. You can use it on desktop, tablets, and phones, including iOS home-screen PWA installs.Under the hood, Microterm combines Restty (libghostty + WebGPU) web terminal rendering and a TinyEMU-backed Alpine Linux guest on RISC-V64. The VM image is chunk-loaded in the browser and booted locally.I successfully used it to run Code

Show HN: Fostrom, an IoT Cloud Platform built for developers

Hey HN! Arjun and Sid here.Fostrom is an IoT Cloud Platform designed for developers to make it really easy to get started and scale fleets. We have Device SDKs (in Python, JS, Elixir, more coming soon), Typed Schemas, Per-Device Mailboxes, Programmable Actions, 4 Global Regions for lower-latency connections, and much more.We've built Fostrom to solve a real need we faced in our previous startup, building a fully automated indoor vertical farm. We spent more time figuring out IoT infrastruct