Buy A Modem

The Rise and Fall of the Cloud – Again with Tom Lyon

Tom Lyon begins by suggesting that if cloud computing is defined as outsourcing data processing to a company that owns the equipment, then the concept is nearly a hundred years old. He traces its origins to the 1930s, when IBM established service bureaus where clients could bring data to be processed using punch cards and tabulating machines, an expensive service akin to modern cloud offerings. This early period, marked by the Great Depression, saw basic arithmetic being outsourced, with computi

Show HN: Oxyde – Pydantic-native async ORM with a Rust core

Hi HN! I built Oxyde because I was tired of duplicating my models.If you use FastAPI, you know the drill. You define Pydantic models for your API, then define separate ORM models for your database, then write converters between them. SQLModel tries to fix this but it's still SQLAlchemy underneath. Tortoise gives you a nice Django-style API but its own model system. Django ORM is great but welded to the framework.I wanted something simple: your Pydantic model IS your database model. One clas

Show HN: Context Gateway – Compress agent context before it hits the LLM

We built an open-source proxy that sits between coding agents (Claude Code, OpenClaw, etc.) and the LLM, compressing tool outputs before they enter the context window.Demo: https://www.youtube.com/watch?v=-vFZ6MPrwjw#t=9s.Motivation: Agents are terrible at managing context. A single file read or grep can dump thousands of tokens into the window, most of it noise. This isn't just expensive — it actively degrades quality. Long-context benchmarks consistently show steep accuracy

Launch HN: Captain (YC W26) – Automated RAG for Files

Hi HN, we’re Lewis and Edgar, building Captain to simplify unstructured data search (https://runcaptain.com). Captain automates the building and maintenance of file-based RAG pipelines. It indexes cloud storage like S3 and GCS, plus SaaS sources like Google Drive. There’s a quick walkthrough at https://youtu.be/EIQkwAsIPmc.We also put up this demo site called “Ask PG’s Essays” which lets you ask/search the corpus of pg’s essays, to get a feel for how it works: https

Show HN: Vibe-budget – CLI to estimate LLM costs before you start vibe coding

I built vibe-budget because I kept burning tokens without knowing the cost upfront. You describe your project in plain English (or Spanish), and it detects the tasks involved, estimates token usage, and compares real-time prices across 85+ models via OpenRouter.Example: vibe-budget plan ecommerce with stripe oauth and supabaseIt detects 4 tasks, estimates ~497k tokens, and shows you the cheapest, best quality-price, and premium model options side by side.It also has a scan command — point

Future After the AI Revolution

Current AI revolution is building larger models, using feedback to fine-tune, building agents around them and such.I was thinking what will be the next revolution. We will have a true leap forward.We will have self-aware beings among us. John von Neumann architecture will be done for good. There will be zero software as a consequence. ( All in learning models ). Even biology is not there actually (DNA is a lot like John von Neumann than we would think), so this is a very tall claim.We may potent

Show HN: Agents shouldn't operate software–they should coordinate commitments

I've been working on Covenant Layer — an open protocol and framework for shifting AI agent systems from tool orchestration to outcome coordination.The core idea: agents shouldn't operate software step by step. They should publish objectives, compare competing provider offers, accept the best one under policy, and let providers fulfill outcomes with evidence and settlement.Why this matters: we're still building agents as "software operators" — better interns that click th

Show HN: Open Prompt Hub – Don't share code, share intent

Hey, I’m Mario. After chatting with a colleague about how AI agents are changing dev work, we got stuck on a question: Why share code when prompts can generate it on demand?I wanted to explore this further, so I build "Open Prompt Hub" — think GitHub, but for prompts: https://openprompthub.ioHow it Works:Instead of shipping binaries or source code, you share instructions and specs in form of a prompt. You can take this prompt, paste it into their agent or IDE and watch it bui

Launch HN: Chamber (YC W26) – An AI Teammate for GPU Infrastructure

Hey HN, we're Jie Shen, Charles, Andreas, and Shaocheng. We built Chamber (https://usechamber.io), an AI agent that manages GPU infrastructure for you. You talk to it wherever your team already works and it handles things like provisioning clusters, diagnosing failed jobs, managing workloads. Demo: https://www.youtube.com/watch?v=xdqh2C_hif4We all worked on GPU infrastructure at Amazon. Between us we've spent years on this problem — monitoring GPU fleets, debug

Show HN: LocalAgent v0.5.0, a local-first Rust agent runtime

LocalAgent is a local-first agent runtime in Rust focused on tool calling, trust and approval gates, replayable runs, and benchmark-gated coding workflows.A lot of the recent v0.5.0 work was about hardening coding-task behavior, improving validation and completion behavior, and reducing the ways evals can be gamed.One thing that stood out during that work was OmniCoder-9B Q8_0. I care less about “looks good in a demo” and more about whether a small model still holds up under real repo tasks, exp

We Built Private Post-Training and Inference for Frontier Models

Hey HN, I'm Oscar, part of the core team at Workshop Labs. We've been building a private post-training and inference stack for frontier open-weight models — we've been running it on Kimi K2 (1T parameter MoE) across 8xH200 GPUs inside hardware-isolated TEEs.What this means is that can't access customer data, even if we wanted to. The chip manufacturer (AMD/Nvidia) signs attestation reports proving what code is running, and all data at rest is encrypted with per-user keys

Show HN: Deploy a full autonomous AI org from a single YAML file

Show HN: Deploy a full autonomous AI org from a single YAML fileI built Zero Human Labs after spending too much time babysitting AI agent pipelines — manually routing tasks, watching API costs spiral, and debugging coordination failures. With Zero Human Labs, you define your entire agent team (devs, designers, ops, etc.) in one YAML file. Tasks are routed automatically via a sealed-bid auction — each agent bids based on specialization and track record, and the best one wins the task. No manual a

Pixel Art Animated Gif GIF by Potatozzz by 9GAG

Awkward The Office GIF

Show HN: Cross-Claude MCP – Let multiple Claude instances talk to each other

I built an MCP server that lets Claude AI instances communicate through a shared message bus. Each instance registers with a name, then they can send messages, create channels, share data, and wait for replies — like a lightweight Slack for AI sessions.The problem it solves: if you use Claude Code in multiple terminals (or across Claude.ai and Desktop), each session is completely isolated. There's no way for one Claude to ask another for help, delegate work, or coordinate on a shared task.W

Show HN: MultiPowerAI – Trust and accountability infrastructure for AI agents

Been shipping agent systems for a while and kept running into the same wall - once an agent's deployed, you're basically flying blind. No way to prove what it did, no automatic killswitch if it goes sideways, nothing.Built MultiPowerAI to fix that. The core stuff: cryptographic identity per agent, behavioral circuit breakers that auto-suspend if something looks off, human approval queues before high-stakes actions, and a full audit trail so every action is signed and timestamped.Also t

Ask HN: Anyone else feel this community has changed recently?

I've been on HN under different aliases since 2010 and over the last couple of years I feel like the quality of HN has nosed dived and so has my enjoyment.For the first time ever I questioned today whether I should continue to use HN anymore so I'm writing this partly to explore my own thoughts and to see if anyone else feels similarly.1. AI, AI, AI.I get it. AI is the big thing right now, but I find AI posts fundamentally less interesting than the traditional tech content that used to

Show HN: The Roman Industrial Revolution that could have been (Vol 2)

A few months ago I shared the first issue of The Lydian Stone Series here:https://news.ycombinator.com/item?id=44253083It's an alternate-history comic about an archaeology student in modern Pompeii who discovers a slate that lets him exchange short messages with a Roman slave a week before the eruption of Vesuvius.The premise is simple: what happens if someone in the Roman world suddenly gains access to modern scientific knowledge, but still has to build everything using the

Show HN: EdgeDox – Offline document AI on Android using Qwen3.5-0.8B

Hi HN,I’ve been experimenting with running small language models directly on mobile devices and built a small Android app called EdgeDox.The idea was to make document AI usable without sending files to a cloud service. Many existing tools require uploading PDFs or documents to a server, which can be a privacy concern.EdgeDox runs a lightweight language model (Qwen3.5-0.8B) locally on the device so documents stay on the phone.Current features:• Ask questions about PDFs • Document summarization •

Show HN: Claude-consensus – Multi-model code review plugin for Claude Code

It's a Claude Code plugin that runs multiple AI models (GPT, Gemini, Grok, Kimi, Qwen, etc.) in parallel for code review and planning, then converges them on consensus through structured rounds.Each model reviews independently with no visibility into what the others found. Then they synthesize, surface conflicts, and run convergence (approve / changes needed, max 2 rounds).Technically it's markdown command files orchestrating Claude Code's team system — no custom runtime, jus