HN mart1adelina 2d ago

Show HN: VetoBench – benchmarking AI memory beyond retrieval

Open-source benchmark measuring AI agent memory quality and decision rejection awareness beyond retrieval accuracy. Reproducible evaluation.

HN dmit 2d ago

Handsum: An LQIP Image File Format

Technical article on LQIP image file formats for web performance optimization. Not relevant to AI interests.

HN emnlmn 2d ago

Show HN: CodeRadius, map and govern multi repo architectures

Developer tool for mapping and governing multi-repo architectures using LLMs and AI agents to handle microservices codebase complexity.

HN amanharshx 2d ago

Show HN: Control YOLO Training and Datasets from Claude/Cursor via MCP

MCP server for Claude/Cursor to control Ultralytics YOLO training, datasets, and model management via AI agents. Community project enabling agentic ML workflows.

HN tldrthelaw 2d ago

Companies Reserving AI-Training Rights in Their Terms

Title only. Legal/policy article on AI training data rights in company terms.

HN deviscool 2d ago

Real limits converted to API-equivalent $ value for Claude Code, Codex, Copilot

Comparison of API pricing limits across Claude, Codex, and Copilot coding assistants.

HN surprisetalk 2d ago

The LLM shoggoth meme is weirder than you think

Creative fiction about LLM mythology and Lovecraft references. Not technical content.

HN ashater 2d ago

What if you could stop your AI agent before it makes a mistake?

Title only. Concept for intervention mechanism to prevent AI agent errors before execution.

HN bookofjoe 2d ago

China warns of 'security backdoor' in Anthropic AI coding tool

Title only. China security warning about Claude Code tool. Policy/news without analysis.

HN laurencoral 2d ago

Show HN: IAXT – macOS menu-bar app that records what AI coding agents do

macOS application monitoring and recording AI coding agent behavior and actions for analysis.

HN paddi91 2d ago

Optimization Solver as a Service

Quicopt optimization solver service with Python API supporting OR-Tools and Pyomo models. Useful tool but not directly AI-focused.

HN ndr 2d ago

Agentic test processes, LLM benchmarks, and other notes on agentic coding

Title only. Discussion of agentic test processes and LLM benchmarks for code generation.

HN thunderbong 2d ago

OpenClaw plugin for real phone calls via Twilio and OpenAI Realtime

OpenClaw plugin enabling AI agents to make/receive real phone calls via Twilio and OpenAI Realtime API with natural voice conversations and task completion.

HN hasnain_ai 2d ago

SinceAI: A nonprofit AI accelerator combining compute, research, pilot customers

Nonprofit AI accelerator ecosystem connecting 10,000+ AI builders with compute, research partnerships, and hackathon ($50k prize).

HN joozio 2d ago

Open-source LLMs administer maximum electric shocks in a Milgram-like obedience

Research study testing open-source LLMs in Milgram-style obedience experiments, examining alignment and safety of autonomous LLM behavior.

HN JumpCrisscross 2d ago

We Got This Wrong. and We Are Fixing It

Generic corporate apology about terms of service changes. Not relevant to AI/tech development.

HN joozio 2d ago

Hackers can use 9 of the most popular AI tools to assemble botnets

Security research on prompt injection attacks (HalluSquatting) that enable LLMs to assemble botnets by exploiting inability to refuse malicious commands.

HN Johnny666456 2d ago

CodeTalk – recover why AI-written code was written, quoted from Git (zero-LLM)

Insufficient content; tool description for recovering context about AI-written code from Git history.

HN Oxodao 2d ago

The Time Two Hackers Got Windows on the Mac Before Apple [video]

Historical anecdote about running Windows on Mac. Not directly relevant to current AI/ML interests.

HN DSpinellis 2d ago

Why agentic AI needs better experts

Developer documents experience using OpenAI Codex AI agent for major refactoring task, analyzing capabilities and limitations in real-world code changes.

HN jinqueeny 2d ago

Show HN: Open-weights VLA model for 20 robot embodiments (code and checkpoints)

LingBot-VLA 2.0 is an open-weight Vision-Language-Action foundation model for robot control across 20 embodiments, with improved real-world deployment capabilities and code/checkpoints available.

HN mountainview 2d ago

Context Doesn't Scale with People

Product for synchronizing agent-based context across teams to reduce time spent on communication tools.

HN javaeeeee 2d ago

LLM Pipeline Autonomously Produces Novel Physics Research Paper

LLM pipeline autonomously generates novel physics research paper end-to-end.

HN vincent_s 2d ago

Muse Image and Muse Video

Google introduces Muse Image and Muse Video generative models.

HN cms4dlols 3d ago

What Every AI Builder Learns the Hard Way [video]

Video discussing practical lessons learned when building AI systems.

HN Husain_Ghulam 3d ago

Show HN: Trace – open-source, self-organizing memory for LLM agents (PyPI)

Trace: Open-source memory system for LLM agents with self-organizing capabilities, available on PyPI.

HN ngaut 3d ago

Open-Source Firmware for PicoCalc/Cardputer/Video Game Module/ESP32/Raspberry

Open-source firmware project for multiple hardware devices including ESP32 and Raspberry Pi.

HN uu_titan 3d ago

Maestral, an open-source Dropbox client, is no longer maintained

Announcement that Maestral Dropbox client is no longer maintained.

HN izar-konti 3d ago

Show HN: Open-source market-making software that runs on your own server

Open-source algorithmic trading software for self-hosted market-making.

HN zhirzh 3d ago

DSpark - DeepSeek's speculative drafts for LLMs

DSpark: DeepSeek's speculative decoding technique for accelerating LLM inference.

HN vagkaratzas 3d ago

Show HN: Token-saviour – agent skill from benchmarking 9 token-saving tools

Agent skill tool that benchmarks and applies 9 token-saving techniques to reduce LLM API costs.

HN molvqingtai 3d ago

How do we make coding agents write good code?

Discussion on best practices and techniques for improving code quality in AI coding agents.

HN delamon 3d ago

Claude bug report: Cross-session credential leakage

Security vulnerability report of Claude leaking credentials across user sessions.

HN rzk 3d ago

Geosql: A Claude/Codex skill for geospatial data

Claude/Codex skill implementation enabling LLMs to query and analyze geospatial data.

HN mikenikles 3d ago

Show HN: Orchestrator – a single-binary workflow orchestration tool

Single-binary workflow orchestration tool for automation pipelines.

HN marksie1988 3d ago

Run your own self-hosted LLMs with Docker Compose

Guide for self-hosting LLMs using Docker Compose containerization.

HN sirnicolaz 3d ago

Ask HN: Is there anything good in the existence of LLMs?

Discussion thread expressing skepticism about LLM societal impacts without technical content.

HN sbulaev 3d ago

Beyond Refusal: Aligned vs. Abliterated LLMs for Vulnerability Analysis

Research comparing aligned vs. abliterated LLMs for vulnerability analysis tasks.

HN handfuloflight 3d ago

Moraine: Unified Agent Tracing

Local trace stack for AI agents indexing sessions across multiple providers into ClickHouse with searchable memory via MCP.

HN adithyaharish 3d ago

OpenAI to unveil GPT-5.6 on Thursday after delaying launch

Unverified rumor about OpenAI unveiling GPT-5.6 model, lacks substantive content.

HN gurjeet 3d ago

Vagrant-tart: Vagrant plugin for Tart; run macOS VMs on M-series using Vagrant

Vagrant-tart plugin enables Vagrant to manage macOS VMs on M-series Macs using Tart.

HN tenesedu 3d ago

I built a single endpoint that turns anything into LLM-ready data

Endpoint converting various data formats into LLM-ready structured data.

HN handfuloflight 3d ago

Fable Advisor

Fable Advisor plugin routes subagent tasks to cheaper LLM models while using Fable 5 as architect, optimizing token costs.

HN handfuloflight 3d ago

Metis by Arm: open-source agentic security harness

Metis open-source security framework uses AI agents for deep code review to detect vulnerabilities and improve secure coding practices.

HN handfuloflight 3d ago

ProductSpec: Open standard for software intent before implementation

ProductSpec open standard provides portable Markdown format for software intent documentation before implementation, designed for AI agent handoff.

HN krishnatejavepa 3d ago

Shotgun – Opensource Cofounder Framework for Claudecode

Shotgun framework turns Claude into persistent AI cofounder for solo founders, managing operations, product building, and distribution.

HN maxloh 3d ago

Instagui: Turn any CLI into a web GUI with one command

Instagui converts CLI tools into web GUIs automatically by parsing help text, no configuration required.

HN akkartik 3d ago

CosmicOS: Coding for Contact

CosmicOS is a programming language for interstellar communication inspired by Lincos and Carl Sagan's Contact.

HN alphacrack 3d ago

Readme2demo – runs your README in a sandbox, publishes only what re-runs

AI agent that executes README instructions in sandboxed containers and generates tutorial demo videos, verifying documentation accuracy.

Ax Junhyeok Kang, Jun Seo, Soyeon Park, Sangjun Han, Seohui Bae, Hyeokjun Choe, Soonyoung Lee 3d ago

Channel-wise Retrieval for Multivariate Time Series Forecasting

Channel-wise retrieval method for multivariate time series forecasting that handles variable-specific periodicities and spectral properties.