HN Beefin 18d ago

Context Engineering for AI Coding Agents

Article on context engineering techniques for AI coding agents. Limited content preview.

HN beeeenorm 18d ago

Guinndex. AI-agent called 3k Irish pubs to map the price of a pint of Guinness

AI agent autonomously called 3000 Irish pubs to gather Guinness pricing data. Demonstrates agent task automation.

HN samkim 18d ago

Show HN: Spicedb-dev. Claude Code plugin that adds authorization as you build

Claude Code plugin integrating SpiceDB for fine-grained authorization, assists designing permission models and generating auth code.

HN akyuu 18d ago

Koharu: Rust desktop application for ML-powered manga translation

Rust desktop app for manga translation combining object detection, OCR, inpainting, and LLMs using candle and llama.cpp.

HN ri-vai 18d ago

Tried the HappyHorse AI video model recently, better than I expected

Commercial video generation platform using HappyHorse model. Marketing content, no technical depth.

HN speckx 18d ago

What Game Engines Know About Data That Databases Forgot

Typhon: embedded ACID database engine optimized for game servers using ECS architecture. Not ML/AI focused.

HN strangewolf 18d ago

Peer-to-peer GPU rental marketplace

Stub entry with no content.

HN antonioful 18d ago

Summalytics – Privacy-first analytics with AI traffic and visibility

Analytics tool tracking AI chatbot referrals with privacy-first approach. Commercial product pitch.

HN olvy0 18d ago

Cyberpunk Legend Neal Stephenson: The Real Threat Isn't AI–It's Us [video]

Neal Stephenson video on AI risks. No substantive content provided.

HN lifeofjer 18d ago

Crane Ledger – Headless Accounting API with REST, GraphQL, and MCP

Crane Ledger API supporting REST, GraphQL, and MCP protocols for accounting automation.

HN Archerlm 18d ago

Show HN: Open-source, machine-bound licensing with a single POST request

Lightweight licensing server for desktop apps using machine-bound keys. Developer tool for software monetization.

HN karlhughes 18d ago

AI agents can now open business bank accounts

AI agents gaining capability to autonomously open business bank accounts.

HN matthewkosarek 18d ago

Show HN: Miracle Release v0.9.0 – A hackable Wayland compositor

Wayland compositor with WebAssembly-based plugin system using Rust API for window management and animation.

HN vrinda_future 18d ago

What's breaking in your LLM gateway in production?

Discussion of LLM gateway production issues. Limited content preview.

HN juancruzguillen 18d ago

A WhatsApp chatbot that becomes smarter the more you use it

WhatsApp chatbot that improves from user interactions.

HN taariqlewis 18d ago

Enterprise AI does not have a model problem. It has an adoption problem

Analysis of enterprise AI adoption barriers beyond model limitations, focusing on user adoption challenges.

HN sh_tomer 18d ago

Show HN: MCP Servers

MCP Servers implementation or collection for Model Context Protocol integration.

HN bsgada 18d ago

Let's talk about LLMs

Discussion prompt about LLMs. No substantive content.

HN ctoth 18d ago

The 200k Ghost: Instruction Degradation in Long-Context LLM Sessions

Research on instruction degradation in long-context LLM sessions at 200k tokens. Limited preview.

HN elvinefendi 18d ago

VMs Are Enough

Design philosophy document arguing VMs and existing cloud primitives are sufficient. Infrastructure opinion piece, not AI-focused.

HN yrzhe 18d ago

Show HN: PageFly – Personal Knowledge OS Inspired by Karpathy's LLM Wiki

Personal knowledge management system inspired by Karpathy's LLM wiki. Limited content preview.

HN Cider9986 18d ago

iCloud-Linux

FUSE filesystem implementation mounting iCloud Drive on Linux with caching. Developer tool but no AI component.

HN zdw 18d ago

Will Your Job Exist in Five Years: Are you coal, or are you a horse?

Opinion piece about AI impact on job security and future employment.

HN mhb 18d ago

Explanation for why we don't see two-foot-long dragonflies anymore fails

Biology research about extinct giant dragonflies and atmospheric oxygen levels. No AI relevance.

HN kanjun 18d ago

Show HN: Control your X/Twitter feed using a small on-device LLM

Chrome extension and iOS app filtering Twitter feeds using on-device Qwen3.5-4B LLM with semantic matching. Shows algorithm feedback loop.

HN kokakiwi 18d ago

We cut Codex's input token cost by 49.5% with a compression gateway (benchmark)

Benchmark showing 49.5% input token cost reduction using compression gateway with Codex.

HN keertahacker 19d ago

Show HN: AgentMint – Open-source OWASP compliance for AI agent tool calls

AgentMint is an open-source tool for ensuring OWASP security compliance in AI agent tool calls.

HN lorenzotenti 19d ago

Show HN: Retevisione – Italian YouTube as Old School Cable TV Guide

Website presenting Italian YouTube videos in 2000s cable TV guide format. No AI or tech development content.

HN schmorptron 19d ago

Fixing AMDGPU's VRAM management for low-end GPUs

Technical article about Linux GPU VRAM management for low-end AMD graphics cards. No AI relevance.

HN alexbit2019 19d ago

Npx codemod AI: make your coding agent great at large migrations

Npx codemod AI tool for enabling AI agents to handle large-scale code migrations.

HN locknitpicker 19d ago

DDD Bounded Contexts: Clear Domain Boundaries for LLM Code Generation

Using DDD bounded contexts to improve LLM code generation by providing architectural clarity and reducing cognitive overload.

HN Brajeshwar 19d ago

Benchmarking LLM Tool-Use in the Wild

Research on LLM tool-use benchmarking. Limited preview content.

HN dial481 19d ago

Show HN: Proposal for a real long-term AI memory benchmark

Audit of AI memory benchmarks reveals flawed evaluation: wrong answer keys, biased LLM judges, unreliable comparisons.

HN bastscho 19d ago

Show HN: Mdpdf a 2k line C CLI to convert Markdown to tiny PDFs

CLI tool converting Markdown to PDFs. Author mentions using agentic coding during development but tool itself unrelated to AI.

HN veganmosfet 19d ago

Show HN: BrokenClaw Part 5: GPT-5.4 Edition (Prompt Injection)

Security research demonstrating prompt injection vulnerabilities in GPT-5.4 model, showing untrusted code execution risks.

HN gk1 19d ago

Agents Need a Database to Break

Infrastructure requirements for AI agents: real-time data streaming and database branching for safe sandboxed execution.

HN ashed96 19d ago

LLM-Wiki but for Early Founders

LLM-Wiki adapted for early-stage startup founders as a knowledge management tool.

HN steveharing1 19d ago

Open-source AI assistant that watches your screen and points at things

Open-source AI assistant that monitors screen content and provides contextual assistance.

HN jakehulberg 19d ago

Coding Agents Are Reading Your .env

Security research showing how coding agents can inadvertently expose secrets from .env files.

HN rida123 19d ago

Nyth AI – Local LLM Inference on iOS Using MLC-LLM and TVM

Nyth AI enables local LLM inference on iOS using MLC-LLM and TVM compiler framework.

HN onthemarkdata 19d ago

Petri, a multi-agent orchestration framework for building AI context

Petri is a multi-agent orchestration framework for coordinating AI context across agents.

HN karimfan 19d ago

Foxhound – helping LLMs better navigate codebases

Foxhound helps LLMs better navigate and understand codebases.

HN liminnnnnng 19d ago

AET: A transpiler that compresses code for LLMs (saves 30-55% tokens)

AET transpiler compresses code for LLM input, reducing token usage by 30-55%.

HN theahura 19d ago

Show HN: Ship of Theseus License

Discussion of cleanroom implementation legal theory for circumventing software licenses using AI.

HN atzeus 19d ago

AI alignment: the signal is the goal

Title only, no content. Appears to address AI alignment concepts.

HN kuberwastaken 19d ago

I Read Anthropic's 244 Page Reason to Not Release Mythos So You Don't Have To

Commentary on Anthropic's decision not to release a model, referencing historical GPT-2 release. Incomplete article with unclear relevance.

HN ddp26 19d ago

I think Anthropic is worth $100B more than last week

Opinion piece forecasting Anthropic's market valuation based on announced revenue growth.

HN himanshudongre 19d ago

Show HN: PropOps – AI agent that reads Indian govt property data nobody checks

Title only. AI agent application reading Indian government property data for insights.

HN SpaceJudas 19d ago

Datadog: We built a real-world evaluation platform for SRE agents at scale

Title only. Datadog platform for evaluating SRE AI agents in production environments at scale.

HN rarce 19d ago

An Agent Skill that implements Karpathy's LLM-wiki on personal GitHub Repo

Agent skill implementing Karpathy's LLM-wiki pattern for persistent knowledge management on GitHub repos with hybrid search.