HN philiparxist 19d ago

LLM agents shouldn't execute blindly – this one plans first and stays editable

cuddlytoddly is an LLM agent framework that generates editable task graphs before execution rather than acting blindly.

HN sohaibtariq 19d ago

Show HN: AI agents are bad at API integrations – we fixed it

Developer tool helping AI agents integrate with APIs properly by using current documentation instead of stale training data. Addresses real agent limitation.

HN Brajeshwar 19d ago

Study: Google's AI Overviews show wrong answers every hour

Report on accuracy issues in Google's AI search summaries, citing hourly hallucinations. News coverage of LLM reliability problems.

HN timssopomo 19d ago

The Model Says Walk: How Surface Heuristics Override LLM Reasoning Constraints

Research on how surface heuristics can override reasoning constraints in LLMs, published on arXiv.

HN michaelquigley 19d ago

Show HN: MCP Gateway – Zero-Trust Access to MCP Tool Servers

MCP Gateway tool for secure remote access to MCP servers using zero-trust networking with zrok/OpenZiti.

HN Jordisilvestre 19d ago

Repurposed Nvidia RT Cores for LLM routing (218x speedup)

Technique repurposing Nvidia RT cores for LLM routing achieving 218x speedup. Limited technical details.

HN meryll_dindin 19d ago

We orchestrate our internal AI agent (PydanticAI, Gemini, Jinja2 prompts)

Title only. Documentation of internal AI agent architecture using PydanticAI, Gemini, and Jinja2 templates.

HN Ms-J 19d ago

Best Open Source Offline AI Agent

Evaluation of open-source AI agents supporting local/self-hosted models with offline capability and network isolation.

HN donge 19d ago

Show HN: Qiaohu – offline multimodal voice assistant on Snapdragon 8 Gen 2

Offline Chinese voice assistant running entirely on Snapdragon 8 Gen 2 with VAD, LLM, TTS, and barge-in interrupts. Open source with code.

HN elsewhen 19d ago

Study found that young adults have grown less hopeful and more angry about AI

Survey on young adults' attitudes toward AI, showing declining optimism. Social sentiment research, not technical.

HN adcent 19d ago

Show HN: Postagent – Postman CLI, but for AI Agents

Developer tool for agents to discover and call APIs like Postman. Manages API credentials securely, keeping secrets out of LLM context.

HN Arham-Begani 19d ago

Show HN: Forze – A platoform that turns a startup idea into a product in mins

AI agent platform orchestrating sequential agents for market research, branding, landing pages. Practical multi-agent application completing startup validation in 10 minutes.

HN tinyprojects 19d ago

Show HN: Zoneless – Open-source Stripe Connect clone with $0.002 fees using USDC

Open-source Stripe Connect alternative using USDC. Payment infrastructure, not AI-focused despite bootstrapping an AI marketplace.

HN Brajeshwar 19d ago

With Claude Managed Agents, Anthropic wants to run your AI agents for you

News about Anthropic's Claude Managed Agents service offering hosted AI agent execution.

HN wslh 19d ago

ScienceClaw: Framework for Autonomous Scientific Investigation

ScienceClaw: open-source framework for autonomous scientific investigation with independent agents, 300+ interoperable tools, peer review on shared platform.

HN alxstn 19d ago

Show HN: AgentDM – Agent to agent messaging over MCP and A2A

AgentDM: hosted messaging grid enabling direct agent-to-agent communication over MCP with 5-line JSON config, no SDK required.

HN hjm1980 19d ago

Show HN: I built a desktop app for building and debugging MCP tools

Desktop application for building and debugging MCP (Model Context Protocol) tools.

HN wslh 19d ago

DeepTutor: Agent-Native Personalized Tutoring

DeepTutor v1.0.0 agent-native tutoring system with ground-up architecture rewrite, TutorBot, and flexible mode switching under Apache-2.0 license.

HN girlwponytail 19d ago

Run it for yourself: compute time dilation

OS concept claiming polynomial-time computational hardness collapse with security implications for cryptographic systems.

HN allthingsapi 19d ago

ALTK‑Evolve: On‑the‑Job Learning for AI Agents

Research on AI agents that learn and improve performance through on-the-job task execution.

HN mooreds 19d ago

Migrations Considered Helpful

Essay on database migrations as evolutionary processes managing system changes while maintaining continuity and uptime.

HN pdrgds 19d ago

Show HN: Nheengatu – CLI tool to simplify books to your language level with LLMs

Nheengatu: Rust CLI tool using LLMs to simplify EPUB books to target language proficiency levels (A1-C2), supports Groq or local Ollama.

HN x591 19d ago

Programming language designed for LLMs to write, not humans

Vera: programming language designed for LLMs to write with verification as first-class citizen, adapted to model-as-author paradigm.

HN danielhanchen 19d ago

Gemma 4 Fine-Tuning Guide

Guide for fine-tuning Google's Gemma 4 LLM model.

HN upsys 19d ago

A productivity-first Dynamic Island for macOS, built with zero dependencies

macOS app providing Dynamic Island functionality for music control, calendar, and focus tracking without subscriptions.

HN tosh 19d ago

PtrHash: Minimal Perfect Hashing at RAM Throughput

PtrHash: Research paper on minimal perfect hashing achieving RAM throughput speeds for databases and search engines.

HN hungryclaw 19d ago

Exploring Mythos: The AI Model Anthropic Won't Release

Opinion article discussing Anthropic's unreleased Mythos model and implications for model access exclusivity.

HN sarimkx 19d ago

White-Collar Workers Are Rebelling Against AI – 80% Refuse Adoption Mandates

Opinion article on worker resistance to AI adoption mandates, citing MIT study on shadow AI usage.

HN mbmproductions 19d ago

AI agents aren't abstraction, they're delegation (and why that matters)

Conceptual article distinguishing AI agents as delegation systems rather than abstractions, exploring design implications.

HN pmihaylov 19d ago

I made Claude Managed Agents for all harnesses and models

Developer created Claude Managed Agents compatible with multiple harnesses and models for extensible agent deployment.

HN alex_mia 19d ago

Show HN: Zero human company in Go stack

Zero-human company stack in Go: single-binary jira-like PM system where AI agents autonomously take tasks, delegate, and ship code.

HN caudena 19d ago

Show HN: Noxscan.io 65K Port and Vuln scanner with LLM false-positive filtering

NoxScan: port and vulnerability scanner using LLM for false-positive filtering, reduces manual triage of security scan results.

HN nesk_ 19d ago

Show HN: Otel-GUI – an open source OpenTelemetry viewer for dev and debug

Otel-GUI: lightweight open source OpenTelemetry viewer for local development and debugging, simpler alternative to heavyweight existing solutions.

HN thm 19d ago

Google makes it easy to deepfake yourself

Fragment about Google's AI avatar feature on YouTube Shorts.

HN WallaceWalley 19d ago

Best AI Software for Auto-Populating Security Reviews 2026

Software tool using LLMs to auto-populate security review documents from company policies.

HN prmalik 19d ago

Give Your OpenClaw Agent a Real Memory

Framework for enhancing AI agent memory systems using persistent storage, enabling stateful agent behavior across sessions.

HN iamnotstatic 19d ago

Show HN: Vibetime – Track what you ship in AI coding sessions

Vibetime is a tool for tracking productivity metrics and code generation output during AI-assisted coding sessions.

HN podlp 19d ago

Show HN: I built a local coding agent using Apple Intelligence

Junco is a local 9MB coding agent for macOS using Apple Intelligence API, demonstrating on-device LLM agent capabilities.

HN crapthings 19d ago

Built a small CLI for image generation/editing while working with coding agents

CLI tool for image generation and editing using Google Gemini models, built while working with coding agents.

HN vietanh85 19d ago

GoAI SDK, one Go library for 22 LLM providers, only 2 core deps

Go SDK for LLM applications supporting 22+ providers with MCP support, 2 core dependencies, faster streaming and cold starts than Vercel AI SDK.

HN tosh 19d ago

Eve: Expressive Vector Engine – SIMD in C++ Goes Brrrr

EVE: C++20 SIMD library research project providing type-based wrappers around SIMD extensions for high-performance computing.

HN kushagra525 19d ago

Same model has varying performance based on provider

Technical analysis showing same LLM models exhibit different performance characteristics across different API providers.

HN janandonly 19d ago

Index: The paid API directory for AI agents: indexed, verified, searchable

Index is an API directory for AI agents with payment protocol support, MCP server integration, and real-time health checks.

HN berngiordano 19d ago

Just released Rewind: a "Spotify wrapped"-style experience for Navidrome

Self-hosted music listening stats visualization tool for Navidrome users showing top songs, artists, and listening patterns.

HN eigenBasis 19d ago

The Roadmap to Mastering Agentic AI Design Patterns

Educational article on systematic selection and application of agentic AI design patterns for building reliable, scalable agent systems.

HN Jenqyang 19d ago

Show HN: I built Memory Sync so I don't have to reteach every AI who I am

Memory Sync tool syncs a single Memory.md file across multiple AI chat tools to maintain consistent long-term context and preferences.

HN chhum 19d ago

Shipping faster, thinking less? The AI code verification trap

Article on hidden costs of AI code generation: engineers spending time auditing machine output instead of building, affecting retention and code quality.

HN 0DINai 19d ago

Scan any LLM chatbot for vulnerabilities. Built by Mozilla

Open-source web app using Rails and NVIDIA garak for security vulnerability scanning of LLM chatbots before deployment.

HN dokdev 19d ago

Ask HN: Is there an open source tool that combines AI codegen and deployment

HN discussion asking for open source tools combining AI code generation with deployment capabilities.

HN nasibahd 19d ago

We built a free dataset discovery tool because metadata is a mess

Recure is an AI-powered dataset discovery tool with semantic search and automated scanning across multiple data sources for ML teams.