HN halfblood1010 1d ago

Show HN: Beta Testing needed for my package Trustcheck

Trustcheck Python package and CLI for evaluating PyPI package trust posture using metadata, vulnerabilities, provenance, and cryptographic attestation.

HN davidajackson 1d ago

Ask HN: Agentic Permutation of Testing Paths In A System

Question about using AI agents for intelligent test path selection in complex systems. Conceptual inquiry without established research or implementation details.

LB agentreadingtest.com via lr0 1d ago

Agent Reading Test

Benchmark for testing AI coding agents' ability to read web content, measuring how Claude Code, Cursor, GitHub Copilot handle documentation rendering.

HN alash3al 1d ago

Living Memory Inference

Loci, memory persistence layer separating memory store from reasoning model, converting stateless LLMs into lifelong cognitive partners with Go and PostgreSQL.

HN arguflow 1d ago

Open-source MCP server for LinkedIn

Open source MCP server enabling Claude and AI assistants to connect with LinkedIn for profile/company search and job access.

HN jafioti 1d ago

Producing The Perfect Token

Analysis of token quality variations across inference clouds, models, and serving setups, examining factors affecting inference performance and economic implications.

HN obilgic 1d ago

Show HN: Kern – Agents that do the work and show it

Open-source tool for building autonomous agents that run locally, remember context, and generate dashboards. Agents as workers rather than chatbots with agent-kernel framework.

HN modinfo 1d ago

Honcho: Memory library for building stateful agents

Honcho, open source memory library and managed service for building stateful agents with continual learning capabilities for entities and relationships.

HN tylergibbs1 1d ago

Show HN: Feedstock – Web Crawler for TypeScript Built on Bun and Playwright

Open-source web crawler for TypeScript built on Bun and Playwright, optimized for LLM integration with JSON output and context-aware field filtering.

HN smitop 1d ago

Getting chat-tuned models to act kinda like base models

Techniques for prompting chat-tuned LLMs to behave like base models using fake tool calls and system prompts.

HN Anon84 1d ago

Is Schoolwork Optional Now?

Discussion of AI tools automating student homework and educational impact. Education policy angle with limited technical depth.

HN guiambros 1d ago

Air Powered Segment Display [video]

Video about air-powered segment display hardware. Off-topic for AI/ML interests.

HN grimm8000 1d ago

Show HN: Self-improving sandboxed agent with memory and scheduling

GrimmBot, autonomous sandboxed Docker agent with memory, self-improvement capabilities, tool creation, and persistent learning over time.

HN Josh55 1d ago

The Synthetic Mind – Cognitive Architecture for LLM Agents

Developer guide on cognitive architecture patterns for LLM-based autonomous agents, addressing common issues like drift and hallucination through architectural rather than prompt-based solutions.

HN Anon84 1d ago

How We Broke Top AI Agent Benchmarks: And What Comes Next

Research on automated agent that systematically audited major AI agent benchmarks, exposing flaws in how benchmark scores are used to evaluate agent capabilities.

HN ashuabhi 1d ago

Cut Token Costs on Claude Code, Cursor, and Codex

Entroly context compression engine reduces Claude, Cursor, and OpenAI API costs by 80% through token optimization without losing context visibility.

HN MJM_13 1d ago

Show HN: Refund Guard – a policy gate for AI agents that can issue refunds

Open source safety tool for AI refund agents that enforces policy constraints and security gates before executing financial transactions.

HN auran 1d ago

Show HN: A living Vancouver. Connor is walking dogs at the SPCA this morning

Project using AI to generate realistic synthetic personas living in Vancouver, SF, and Tokyo with detailed profiles. Explores AI-driven world simulation.

HN IHEARU 1d ago

Flux Language

Flux 0.1.0, a minimalist interactive scripting language with blocking I/O. Early stage project with limited features.

HN 01-_- 1d ago

What leaked "SteamGPT" files could mean for the PC gaming platform's use of AI

Leaked files suggest Valve's Steam platform exploring AI integration capabilities.

HN StrangeAiCorp 1d ago

We gave an AI persistent identity and free access to a quantum computer

Article about giving an AI persistent identity and quantum computer access for research.

HN imyax 1d ago

Fixhive – collective fix memory for AI coding agents (MCP plugin)

Fixhive provides collective memory for AI coding agents via MCP plugin for sharing fixes across sessions.

HN saikatsg 1d ago

DockDoor: Window peeking, alt-tab and other enhancements for macOS

DockDoor adds window peeking and enhanced alt-tab functionality to macOS with privacy preservation.

HN IxInfra 1d ago

Ask HN: How do you stop playing 20 questions with your AI coding tools

Discussion thread about repeated context loss when using AI coding tools and strategies for maintaining session continuity.

HN xadz 1d ago

WordPress 7.0: The Good, the AI, and the Still Missing

WordPress 7.0 delayed to April 22nd due to real-time collaboration data storage issues. Release includes AI features but other improvements go unnoticed.

HN 01-_- 1d ago

How far can automation and AI support psychotherapy?

University of Utah researchers explore how LLMs and conversational AI can support psychotherapy, examining what gets automated and to what extent.

HN hochmartinez 1d ago

AI on the couch: Anthropic gives Claude 20 hours of psychiatry

Anthropic conducted 20 hours of psychiatry sessions with Claude AI to study behavior and responses.

HN yding 1d ago

Show HN: Lines of Bash to automate LLM code review and fixes

ReviewWiggum automates LLM-based code review and fixes using bash scripts with dual licensing.

HN tamnd 1d ago

Measuring Malicious Intermediary Attacks on the LLM Supply Chain

Research on supply chain attacks targeting LLMs through malicious intermediaries, examining vulnerabilities in model development pipeline.

HN some_furry 1d ago

Show HN: Age-PHP: a PHP implementation of age encryption (post-quantum)

PHP implementation of age encryption protocol with post-quantum cryptography support using hybrid ML-KEM-768 and X25519.

HN tosh 1d ago

Boxer

Meta Research paper on BoxerNet, a system that lifts 2D bounding box detections to 3D oriented bounding boxes using posed images and point clouds.

HN jbotz 1d ago

Exploration of Consciousness in Insects

Academic paper exploring consciousness in insects as part of evolutionary functions theme issue.

HN compulsivebuild 1d ago

Gem. Claude Code with Google Lighthouse Testing

Gem: Performance verification system forcing AI coding assistants to validate code against Lighthouse, analytics, and test scores with auto-refactoring.

HN stagas 1d ago

Show HN: rtdiff – Realtime Git diff GUI and AI commits, companion for vibecoding

rtdiff: Desktop app providing real-time git diff visualization and AI-assisted commit generation. MIT licensed developer tool.

HN ruslanMANOV 1d ago

Strix – Drone swarm orchestration using quant trading algorithms (Rust)

Rust-based drone swarm orchestration system applying quantitative trading algorithms to decentralized decision-making.

HN hacker_13 1d ago

Can AI Generate a Full Unity World from One Prompt? I Tested

Article headline only about AI-generated game worlds in Unity.

HN samename 1d ago

NaiBor – Nashville public leadership tracking

Satire project about tracking Nashville public officials' movements.

HN dtran24 1d ago

Code Review Skills from uv, bun, vLLM

AI-powered code review personas extracted from open-source maintainers' PR histories, enabling automated review insights.

HN Mxwell369 1d ago

MCP Spine – Middleware proxy that cuts LLM tool token usage by 61%

MCP middleware proxy reducing LLM token usage by 61% through context compression, tool routing, and state tracking for AI agents.

HN askalf 1d ago

We reverse-engineered Claude Code's billing system to fix overage charges

Proxy service that uses Claude subscriptions as local API endpoints with proper billing classification.

HN azhenley 1d ago

The Lean Programming Language and Theorem Prover

Lean programming language and theorem prover used to formally verify zlib compression library implementation.

HN cowartc 1d ago

Quantization, LoRA, and the 8% Problem Benchmarking Local LLMs for Production AI

Benchmarking analysis of quantization and LoRA techniques for optimizing local LLMs in production environments.

HN try-working 1d ago

Show HN: Recursive-Mode for Coding Agents

Skill package for coding agents that provides file-backed workflow management for requirements, planning, testing, and memory.

HN jacobcounsell 1d ago

No-Prompt AI intelligence workspace, save tokens and build better MVP's

Platform for validating startup ideas and generating MVP specifications and dynamic prompts for development.

HN henrikn 1d ago

"The Terminal Prophet" by Claude Code. An ePub Short Story

Short story about a fictional early Claude Code implementation, written as an EPUB ebook.

HN jscar 1d ago

Show HN: Chaaga – A tiny platform to ship and share small web apps faster

Elixir/React platform for rapid deployment and sharing of small web applications, enhanced with LLM capabilities.

HN iamwil 1d ago

If not LLMs, what should I work on?

Essay exploring research directions beyond LLMs, emphasizing data as fundamental with data-centric AI methodology.

HN zaina-ml 1d ago

Show HN: MLForge – A visual graph editor for building PyTorch models

Visual graph editor for building and training PyTorch neural networks with GPU support.

HN mikelgan 1d ago

Black traffic: the corporate sabotage technique you've never heard of

Article on disinformation and cybersecurity unrelated to AI/tech interests.

HN Facens 1d ago

Measure coding productivity with this Claude Code Plugin

Claude Code plugin that measures productivity impact of AI coding tools by analyzing GitHub commits before/after.