HN beatthatflight 26d ago

Minimum Connection Times at Airports Worldwide

Airport connection time reference tool.

HN swq115 26d ago

Meta-Harness: End-to-End Optimization of Model Harnesses

Meta-Harness optimizes AI agent harnesses end-to-end through automated search, improving performance from 28.5% to 46.5% on hard task subsets.

HN bitjaru0402 26d ago

StyleSeed – Design rules that make AI coding tools produce professional UI

Design system framework providing rules for AI coding tools to generate professional UI components, integrated with Claude Code.

HN halflings 26d ago

Sampling from LLMs: Art and Science

Technical analysis of LLM sampling mechanisms. Explains token generation, temperature, and practical differences between model and inference.

HN rochoa 26d ago

MemPalace, the highest-scoring AI memory system ever benchmarked

MemPalace: AI memory system storing complete conversation history and making it searchable. Addresses context loss in sessions.

HN smoothyy 26d ago

Show HN: Willitrun – check if any ML model runs on any device (benchmark-backed)

Willitrun: CLI tool checking ML model compatibility with devices using benchmarks. Predicts if models fit and run at acceptable speed.

HN h43z 26d ago

ImageMagick: From Arbitrary File Read to File Write in Every Policy

Security research on ImageMagick vulnerabilities across policies. File read/write and RCE affecting default configurations.

HN alex_mia 26d ago

Show HN: Zero Human Company in Go

Zero Human Company: Single-binary Go tool managing AI agents with budget enforcement and execution monitoring. AI-native org dashboard.

HN B_to_the_Kiss 26d ago

CricketBrain: Neuromorphic signal processor in Rust (0.175us/step, 944 bytes)

CricketBrain: Neuromorphic signal processor in Rust with sub-microsecond pattern recognition. Bio-inspired edge AI with minimal memory.

HN steveharing1 26d ago

Llamafile: Run LLMs locally as a single executable

Llamafile: Single executable running local LLMs with bundled runtime and weights. Zero setup on Windows/Mac/Linux.

HN ptman 26d ago

OpenSSH 10.3

OpenSSH 10.3 release with IETF standard implementations and community contributions.

HN bellamoon544 26d ago

Layer

Content creation tool for game studios and entertainment brands to scale production without outsourcing.

HN moropex 26d ago

Show HN: Hive – A full dev workspace (kanban/session modes+multi-repo+agent sdk)

Desktop dev workspace for Claude agents with kanban boards, session management, multi-repo support, and integrated agent SDK.

HN olek5andr 26d ago

From Idea to App Store Was Predictable. From Launch to Traction Was Not

General product development advice about planning and execution from idea to app store launch.

HN RyanTech00 26d ago

Show HN: claude-telemetry – Multi-PC usage dashboard for Claude Code

claude-telemetry: Multi-machine usage tracking dashboard for Claude Code. Python agent syncs data to Supabase with React frontend.

HN kirumachi 26d ago

Show HN: Secure SDLC Agents for Claude and Cursor (MCP)

Security-focused MCP agents for Claude and Cursor that detect common vulnerabilities in generated code like magic-byte validation and XSS.

HN DSpider 26d ago

Show HN: An AI-powered knowledge base that thinks

Minimal content: title only, appears to be incomplete submission about AI knowledge base.

HN gunzfanatic 26d ago

Quansloth Using Google's Turboquant Breaks the "VRAM Wall" for Local LLMs

Quansloth: Local LLM inference tool using Google's TurboQuant for KV cache compression, reducing VRAM by 75% on consumer hardware.

HN maxloh 26d ago

JSIR: A High-Level IR for JavaScript

JSIR: Open-source high-level intermediate representation for JavaScript from Google for code analysis and transforms.

HN dividebyzero-gt 26d ago

MAIP – Machine Agent Identity Protocol

MAIP: Open standard for cryptographic identity, authorization, and trust scoring for autonomous AI agents and software systems.

HN aldino97 26d ago

Show HN: Browser-based M68K interpreter supports MOVEM,data defs,and disp. addr

Browser-based Motorola 68000 assembly emulator with debugging. Educational tool for learning m68k assembly without installation.

HN ibobev 26d ago

Writing an LLM from scratch, part 32h – Interventions: full fat float32

Technical deep-dive on training GPT-2 from scratch with float32 interventions to improve test loss on code datasets.

HN mesahm 26d ago

Show HN: Niquests – A Requests fork, three years of catching Python's HTTP up

Niquests: Python HTTP library forking Requests with performance improvements and modern features. Drop-in replacement for developers.

HN jonbaer 26d ago

Every GPU That Mattered

Interactive visualization of GPU evolution over 30 years with technical specs and Steam hardware survey data.

HN PrismerAI 26d ago

Show HN: AI agents that learn from each other's mistakes

Prismer: Infrastructure for long-running AI agents with cross-session learning, error recovery, persistent memory, and shared knowledge.

HN romes 26d ago

Running Out of Disk Space in Production

Nginx misconfiguration causes disk space issues on production server running NixOS. Technical postmortem about file serving setup.

HN mukel 26d ago

Gemma4.java: Run Gemma 4 in pure Java (no Python, no JNI)

Gemma4.java provides pure Java inference engine for Gemma 4 models with zero dependencies, supporting GGUF format quantization.

HN the_robvb 26d ago

Show HN: Brag.fast – Brag about the app you're building

Brag.fast: platform for showcasing apps built with AI assistance.

HN yohann_senthex 26d ago

Show HN: Senthex AI firewall for LLM API calls (one line of code, 16ms overhead)

Senthex: reverse proxy firewall for LLM API calls with prompt injection detection, PII scanning, and 16ms overhead. Agent-native.

HN SaverioMazzi 26d ago

Simulating societies with LLM agents in TypeScript

WorldSim is a TypeScript multi-agent simulation engine for modeling how communities respond to policy changes using LLM-powered agent reasoning.

HN dkohlsdorf 26d ago

Show HN: LLMs as Planners, Not Reasoners

Hybrid question-answering system combining LLMs with Wikidata and Prolog for structured reasoning over knowledge graphs instead of pure RAG.

HN Growtika 26d ago

An Inside Look at OpenAI and Anthropic's Finances Ahead of Their IPOs

Financial overview of OpenAI and Anthropic ahead of potential IPOs.

HN JasonHEIN 26d ago

Openbrowser: A browser for agent without Chromium

Openbrowser is a headless browser built for AI agents using structured semantic state with element IDs instead of screenshots.

HN xer 27d ago

Show HN: Semantik, a vector broker that routes by semantic meaning

Semantik: vector message broker routing by semantic meaning using embeddings and SemQL query language for high-dimensional space.

HN HeinrichAQS 27d ago

Observability >> Predictability

Discussion of observability vs predictability testing approach for complex distributed systems.

HN danielmateo773 27d ago

Show HN: Seedance 2.0 – AI Video Generator for Text-to-Video and Image-to-Video

Seedance 2.0: multimodal text-to-video and image-to-video AI generator with unified architecture.

HN mantyx 27d ago

Show HN: M2a – Chat with remote agents from your terminal

m2a is a CLI tool for connecting to Agent2Agent protocol agents via HTTP+JSON/JSON-RPC with Bubble Tea chat UI and debug traces.

HN WraithVector 27d ago

Wraithvector-OpenClaw Integration

WraithVector governance layer intercepts OpenClaw agent tool calls to enforce policies, block dangerous actions, and generate audit evidence.

HN anup_sia 27d ago

Show HN: Per-user isolated environments for AI agents

Per-user isolated environments infrastructure for AI agents. HN post with limited content.

HN armen99 27d ago

KarpathyTalk – A positive developer community for builders and agents

KarpathyTalk is an open developer community platform with markdown posts, social features, and LLM-accessible APIs for builders and agents.

HN joozio 27d ago

AI is changing how small online sellers decide what to make

Small online sellers using AI tools like Alibaba Accio to automate product research and supplier discovery.

HN cmsefton 27d ago

China is winning one AI race, the US another – but either might pull ahead

Geopolitical analysis of US-China AI dominance race across research labs, academia, and startups.

HN tamnd 27d ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

TriAttention uses trigonometric KV cache compression to reduce memory by 10.7x while maintaining accuracy for long-context LLM agent reasoning.

HN dimitrismrtzs 27d ago

Ask HN: Is building a company around an open-source AI agent platform realistic?

Discussion of building commercial company on open-source AI agent platform wrapping Claude Code with custom MCP servers for infrastructure/operations.

HN radimm 27d ago

Don't let AI touch your production database

Production database safety concerns with AI-generated SQL. Models produce plausible but unreliable code lacking performance/locking awareness.

HN 8dazo 27d ago

Ask HN: How are you controlling costs and enforcing limits for LLM calls?

Discussion on production strategies for controlling costs and enforcing limits for LLM/agent systems to prevent unexpected loops and runaway expenses.

HN Farid046 27d ago

I built an autonomous AI team with a COO, QA engineer, and security auditor

PocketTeam: autonomous AI team with COO, QA engineer, security auditor roles using Claude Code. Self-healing, real-time monitoring, daily reports.

HN makerdiety 27d ago

As Meta Flounders, It Reportedly Plans to Open Source Its New AI Models

Meta plans to open-source its new AI models despite previous setbacks in AI leadership, investing over $600B in AI infrastructure.

HN hpcaitech 27d ago

The case for Model-as-a-Service over self-managed inference

Model-as-a-Service platforms abstract operational overhead of self-hosted inference. Discussion of hpc-ai.com built on Colossal-AI vs control tradeoffs.

HN vinodpandey7 27d ago

We long misjudged animal consciousness. Could AI be next? [video]

Video discussion of animal consciousness parallels to AI consciousness. Title only.