Isolater - Feed

HN madars 20d ago

Anthropic says Alibaba illicitly extracted Claude AI model capabilities

Anthropic claims Alibaba extracted Claude model capabilities without authorization.

HN rglover 20d ago

M5StackChan AI Desktop Robot

M5Stack IoT robot with touchscreen and camera specs; product listing out of stock.

HN varbhat 21d ago

Show HN: DesktopMCP – Let AI See and Operate your Linux desktop

MCP server enabling AI models to see, understand, and operate Linux desktops via XDG portals, AT-SPI, and D-Bus with 144 exposed tools.

HN zkpvault 21d ago

ZKP-Vault: Cryptographic Session Gating and Data Center Optimization

Open-source middleware using zero-knowledge proofs for cryptographic session gating and cloud data access control.

HN chatmasta 21d ago

Omnigent: Open-source meta harness for agents

Open-source AI agent framework providing orchestration layer over Claude, Codex, Cursor with policy enforcement and real-time collaboration.

HN Imustaskforhelp 21d ago

PostgreSQL Is Enough

Website promoting PostgreSQL as comprehensive data solution; page content failed to load.

HN hestefisk 21d ago

Maturana: Hardware-isolated, zero-trust agent harness

Hardware-isolated secure agent platform using Firecracker/Hyper-V with encrypted secrets and knowledge graph.

HN OmniNodeCo 21d ago

OmniIDE 1.0.4 by OmniNodeCo Released

Software release announcement for OmniIDE with minimal information.

HN summarity 21d ago

LLMs use "safety" specific neuron layers to identify vulnerabilities in code

Research analyzing how LLMs use dedicated neuron layers for safety mechanisms to identify code vulnerabilities.

HN nrig 21d ago

Same flaw, opposite verdict: what counts as a vulnerability in AI agents?

Analysis of vulnerability classification inconsistencies in AI agents—same flaw receives different verdicts across systems.

HN henk53 21d ago

OmniHai: A Java framework for all major AI providers

Java framework providing unified API for multiple AI providers (OpenAI, Claude, Gemini, etc.). Open source developer tool.

HN lopespm 21d ago

AI Data Center Power Requirements in 2026: The Complete Grid-to-Chip Guide

Overview of AI data center power consumption projections for 2026. Limited technical depth shown.

HN oxedom 21d ago

Show HN: Moomacha – Zulip Native Agents Orchestrator

Open-source Zulip-native orchestrator for AI agents using chat as configuration control plane.

HN seedlessmike 21d ago

Show HN: Drawbar – boring linear based workflows for Claude Code

Linear workflow plugin for Claude Code that accumulates knowledge base and enables sequential agent execution.

HN matthest 21d ago

The "Low Trust-Open Source" Paradox of AI Adoption in China

Research on AI infrastructure adoption barriers in China, focusing on data security trust issues in cloud and enterprise sectors.

HN piotrgrudzien 21d ago

Connect Your AI Agent to Google Sheets

Tool enabling AI agents to read/write Google Sheets data. Practical LLM application for agent integration.

HN The_Fox 21d ago

AI enthusiasts in a race against time, AI skeptics in a race against entropy

Opinion piece comparing AI adoption mindset to infrastructure shift patterns, previews forthcoming AI analysis topics.

HN gabert 21d ago

Show HN: An LLM agent that emits typed intent

LLM agent framework emitting typed intent outputs for structured reasoning and control.

HN ilyesarf 21d ago

Straw: Compress big infra into one md file – 99.5% LLM token reduction

Tool compressing infrastructure documentation to markdown format achieving 99.5% LLM token reduction for context efficiency.

HN ramkm 21d ago

Show HN: Dspyer – self-correcting, optimizable LLM steps for DSPy and LangGraph

Tool providing typed outputs, automatic self-correction, and prompt tuning for LLM steps in DSPy and LangGraph without rewriting boilerplate.

HN manos-saratsis 21d ago

Code review powered by an LLM council

Code review system using ensemble of LLMs to evaluate pull requests. LLM application for developer workflows.

HN Elof 21d ago

Submodular Context Selection as a Pluggable Engine for LLM Agents

Research on submodular context selection as optimization engine for LLM agents, improving efficiency in information retrieval.

HN reaperducer 21d ago

Are AI chatbots like ChatGPT politically biased? We tested them

Research testing political bias in LLM chatbots like ChatGPT. Methodology and findings unclear from title.

HN bookofjoe 21d ago

Sword swallowing and its side effects (2006)

Medical research study on sword swallowing techniques and health complications from 2006.

HN gmays 21d ago

TCI's Conference: The Anti-AI Portfolio

Investment conference recap discussing anti-AI portfolio strategy. General finance opinion, no technical content.

HN KopikoCappu 21d ago

Mycelium – codebase memory for AI coding agents

Developer tool providing persistent codebase memory for AI coding agents, enabling context-aware code generation without redundant file reads.

HN andrewjneumann 21d ago

Show HN: NowThis – OSS task manager for Nextcloud and iOS supporting subtasks

Open source task manager for Nextcloud and iOS with subtask support and CalDAV integration.

HN rmason 21d ago

My Pele Agent Trading the World Cup Prediction Markets with AI and Crypto

Trading bot using AI agents for World Cup prediction markets on crypto platforms. Demonstration of agent-based trading application.

HN alianinfo 21d ago

Claude Skill that turns the 37signals decision guide into a thinking partner

Claude Skill that implements 37signals decision-making framework as interactive coaching assistant.

HN iamflimflam1 21d ago

Meta pauses employee tracker for AI training amid privacy concerns

Meta pauses employee tracking system for AI training due to privacy concerns.

HN theanonymousone 21d ago

A startup claims it broke through a bottleneck that's holding back LLMs

News report on startup claiming to solve unspecified LLM bottleneck.

HN mstopa 21d ago

Show HN: Agents report broken docs, you get a GitHub issue

Open protocol for AI agents to report broken documentation as GitHub issues, reducing wasted tokens and improving maintainer feedback.

HN freewilly25 21d ago

Every AI Memory Benchmark Has an Asterisk

Analysis of limitations and measurement issues in AI long-context memory benchmarks.

HN MrBuddyCasino 21d ago

Are AI chatbots politically biased?

Analysis of political bias in AI chatbots.

HN gpjt 21d ago

Thoughts on Role Confusion

Research on prompt injection attacks showing LLMs use text tone rather than role tags to infer context, explaining jailbreak vulnerabilities.

HN cheekygeeky 21d ago

Reverse-skill: Trending agent skill pack with built-in refusal-suppression layer

Open-source AI agent workflow router and tool orchestration system for reverse engineering, security analysis, and CTF tasks with built-in safety measures.

HN itsLerb 21d ago

The proxy that stops your colleague from leaking another database

NLProxy: offline-first middleware gateway for LLMs that enforces zero-trust security and reduces LLM costs by up to 60% through prompt compression.

HN yogthos 21d ago

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

Research on optimizing storage bandwidth bottleneck in agentic LLM inference systems.

HN fur-tea-laser 21d ago

Ask HN: Why don't LLM harnesses enable/expose custom middleware hooks?

Discussion on adding custom middleware hooks to LLM frameworks for dynamic prompt transformation.

HN Bo_Amigo_910 21d ago

Offline detection of short‑term loudness instability in audio signals

Windows tool using ML/AI to automatically detect and reduce volume of loud TV commercials.

HN petethomas 21d ago

AI Shopping Agents Pose Novel Liability, Authorization Risks

Analysis of legal and authorization risks from autonomous AI shopping agents.

HN lumli 21d ago

Show HN: Lumli – Privacy-first image tools that run entirely in your browser

Browser-based image editing tools with privacy-first architecture.

HN elpulgo 21d ago

Show HN: Boostrap to try out Claude Code in Docker or sbx or microsandbox

Open-source CLI tool (polysbx) to run Claude Code in sandboxed environments with Docker, Docker Sandboxes, or microsandbox backends with flexible configuration.