HN tasn 1d ago

Show HN: Diom – Back end primitives (queue, rate limit, etc.) in one Rust binary

Diom backend server provides cache, queues, rate-limiting, idempotency in single Rust binary. Open-source developer infrastructure tool.

HN hammer-mei 1d ago

Stopgap for Claude -p before Anthropic's June 15 billing split

Stopgap announcement for Claude pricing changes before June 15 billing split.

HN lcmeyer 1d ago

Learning Systems and Innate Behavior

Essay on learning systems and innate behavior in organisms. Off-topic.

HN matt_d 1d ago

Verifying EDA and compiler optimizations once and for all

ParaBit solver verifies correctness of EDA and compiler optimizations using parametric bitvector theory, presented at CAV 2026.

HN matt_d 1d ago

StepStone: LLM-Based GPU Kernel Driver Fuzzing via User-Space Libraries [pdf]

Research paper on using LLMs to fuzz GPU kernel drivers via user-space libraries. Novel ML application for security testing.

HN DhruvKumarJha 1d ago

Show HN: We wrote forensic intelligence reports on 20 open-source codebases

Forensic analysis reports on 20 open-source codebases examining architectural assumptions and design flaws.

HN cleardusk 1d ago

Show HN: Lance – image/video generation and understanding in one model

Lance is an open-source multimodal model with 3B active parameters for image/video generation and understanding, released by ByteDance with code and paper.

HN speckx 1d ago

You never learned to delegate. AI just made it obvious

Opinion article about AI changing delegation practices in organizations.

HN chhum 1d ago

AI-generated abandonware is hollowing out open source

Opinion piece about AI-generated low-quality packages degrading open source ecosystems.

HN andros 1d ago

Chat client for Meshtastic LoRa mesh networks in Emacs

Emacs chat client for Meshtastic LoRa mesh networks using direct USB serial connection.

HN linkdd 1d ago

Localgcp: LocalStack for GCP, emulating 14 Google Cloud services locally

LocalStack-equivalent open-source emulator for 14 GCP services including Vertex AI and BigQuery, works offline with standard client libraries.

HN pyrex41 1d ago

Formal Verification Gates for AI Coding Loops

Research on formal verification methods for ensuring reliability in AI coding agent loops.

HN mityash 1d ago

Benchmarking AI coding agents for distributed SQL: 350 runs, 17 models

Benchmark study evaluating 17 AI coding agents across 350 runs on distributed SQL tasks.

HN smooke 1d ago

Co-Scientist: A multi-agent AI partner to accelerate research

Co-Scientist: multi-agent AI system designed to partner with researchers and accelerate scientific discovery.

HN demonthos 1d ago

Betlang: A tiny (50kb) programming language detection model

Betlang is a 50KB machine learning model for CPU-based programming language detection supporting 30+ languages with ranked probability outputs.

HN dhakalster 1d ago

Microsoft Agent 365: Autonomous AI for enterprise governance by 2026

Microsoft announces Agent 365 for autonomous enterprise governance by 2026. Product announcement for AI agents in enterprise.

HN chrisjj 1d ago

ChatGPT and other AI bots made errors before Scottish election, study finds

Study finds ChatGPT and AI bots made factual errors during Scottish election. Research on LLM accuracy in political context.

HN snakajima 1d ago

Show HN: MulmoClaude – open-source platform where Claude composes tools and GUIs

MulmoClaude is an open-source AI-native application platform where Claude composes tools and GUIs as plugins in a single registry, with examples including accounting systems and obligation engines.

HN gmays 1d ago

Anthropic, Gates Foundation launch $200M partnership for AI in health, education

Anthropic and Gates Foundation commit $200M for AI in health and education. Partnership announcement for public goods.

HN bixxie09 1d ago

Show HN: I built an AI cloud architect that ships working infrastructure

LLM application that generates cloud infrastructure designs from descriptions/sketches, producing validated code, security grades, and cost estimates.

HN philipisik 1d ago

Show HN: Hocuspocus 4 – Yjs collab server

Hocuspocus v4 released under MIT license, a WebSocket backend for real-time collaboration built on Yjs CRDT library, running on Bun, Deno, Cloudflare Workers.

HN jonnyasmar 1d ago

Show HN: atrium – a resumable, tiling workspace manager for Claude Code, Codex

macOS workspace manager for Claude Code and other AI dev agents with resumable sessions, terminals, browsers, and task management.

HN shenli3514 1d ago

Testing distributed systems with AI agents

Framework for AI agents to design and run tests for distributed systems, generating test plans and findings reports with multi-model support.

HN hn_acker 1d ago

Kickstarting "The Reverse Centaur's Guide to Life After AI"

Book promotion for speculative fiction about life after AI. Kickstarter campaign for DRM-free distribution.

HN alshanty 1d ago

Show HN: Free AI headshots from one selfie, no signup

Free AI headshot generator creating studio-quality profile pictures from single selfie input.

HN willbilton 1d ago

TokenScale – AI API pricing in words you know (The Hobbit = $0.06)

Browser-based calculator comparing LLM API pricing across models using familiar content examples (novels, emails, contracts).

HN ryan4rtmx 1d ago

RTMX: Intent Layer for Agentic Engineering

RTMX is a CLI tool for requirements traceability that integrates with AI agents via MCP, allowing agents to build against defined specifications tracked in git.

HN rgombash 1d ago

OCL Nexus Local – Open-source local compute fabric for AI agents

OCL Nexus Local is an open-source compute fabric for local-first AI agent development, featuring isolated Ubuntu sandboxes, Model Context Protocol support, and Docker Compose deployment.

HN fbuilesv 1d ago

You can't whisper at an AI agent

Stripe developer relations overview with no technical content about AI agents.

HN prengaraj 1d ago

Token Saver for AI Tools

Educational tool explaining token economics for AI APIs, comparing tokenization and pricing across Claude, Gemini, and ChatGPT.

HN sbulaev 1d ago

Max-severity flaw in ChromaDB for AI apps allows server hijacking

Security vulnerability (CVE-2026-45829) in ChromaDB vector database allowing unauthenticated code execution on exposed servers.

HN kadhirvelm 1d ago

Good Code, Wrong Feature: The Handoff Problem

Essay on coordination bottlenecks in AI-driven engineering teams, discussing communication failures and documentation practices.

HN ScottAperion 1d ago

Aperion Shield: local guardrail that blocks destructive AI coding agent ops

Open-source MCP server providing safety guardrails for AI coding agents, blocking destructive operations across SQL, git, filesystem, cloud, and kubernetes.

HN mikelgan 1d ago

We've entered a golden age of idea thieves and liars

Opinion piece about misinformation and plagiarism. Not AI/tech-specific.

HN ballista2026 1d ago

LLM INQUISITOR: Evaluating how AI models handle long, realistic tasks

LLM INQUISITOR is a methodology and tool for evaluating AI systems in real-world workflows, measuring stability, reliability, and safety beyond benchmark performance.

HN svett 1d ago

Show HN: One dev environment for humans, CI, and AI agents

Framework for unified dev environments supporting humans, CI systems, and AI agents, addressing the multi-audience complexity of modern development workflows.

HN NBenkovich 1d ago

Show HN: Agyn, an open-source Kubernetes runtime for AI agents

Agyn is an open-source Kubernetes platform for deploying AI agents to enterprise infrastructure with built-in security, budget controls, and secret management.

HN danborn26 1d ago

HTML-anything – The agentic HTML editor – your local AI agent writes the HTML

HTML-anything is an agentic HTML editor where local AI agents autonomously write and generate HTML code.

HN eandre 1d ago

Benchmarking AI agents across five TypeScript back end frameworks

Benchmark comparison of AI agent performance across five TypeScript backend frameworks.

HN jspann 1d ago

Using an LLM for Research

Title only: Using an LLM for Research. No content provided.

HN mox-1 1d ago

Ask HN: Who is working on applying AI to learning?

Hacker News discussion question about AI applications in education and learning. Minimal content.

HN mustaphah 1d ago

LLMs pass a standard three-party Turing test

Brief claim that LLMs have passed a three-party Turing test. Minimal details provided.

HN gmays 1d ago

Toto 2.0: Time series forecasting enters the scaling era

Toto 2.0 is a family of open-weights time series foundation models (4m-2.5B parameters) demonstrating scaling improvements on Hugging Face.

HN startages 1d ago

Google Search Is Becoming an AI Agent

Google Search evolving into AI agent that answers, follows up, and takes actions beyond ranking links. Impact on web economics.

HN ayoubnabil 1d ago

Rust Database from Scratch

PostgreSQL-compatible database engine in Rust supporting relational, graph, and vector queries. Open source.

HN gpvos 1d ago

The slow creep of epistemic apocalypse

Critical analysis of LLM-generated content polluting peer review, research, and academia, causing epistemic erosion.

HN steveharing1 1d ago

Google's Next AI Push Is About Agents, Not Chatbots

Google shifts focus from chatbots to agents with Gemini 3.5 Flash, emphasizing coding pipelines, autonomous research, and multi-agent coordination.

HN 3littlefish 1d ago

Why multi-agent AI breaks in prod and how Yugabyte's Meko is trying to fix it

Yugabyte's Meko addresses multi-agent AI production issues with shared memory and coordination layer for state synchronization.

HN johnleslie_pm 1d ago

AI companies' DNS: 17 Anthropic-verified, 23% have spoofable email

DNS records analysis of 39 AI company domains revealing vendor relationships, email spoofing risks, and DMARC/SPF gaps.

HN pranshuchittora 1d ago

Show HN: Open-Source Agentic QA Harness with Memory

Open-source agentic QA harness with memory capabilities, includes live demos for testing.