1d ago
VSM Loop: Viable-System Orchestration for Multi-Agent R&D
Framework for orchestrating multi-agent systems for R&D tasks using viable systems model. Directly addresses AI agent coordination.
1d ago
Ask HN: Shouldn't Google need to give a public statement about Railway incident?
Discussion about Google's communication regarding a Railway GCP account suspension incident.
1d ago
Show HN: Prism Coder – Qwen3.5-14B fine-tuned for MCP tool-routing decisions
Prism Coder is a Qwen3.5-14B model fine-tuned for MCP tool-routing decisions in AI agents, adding persistent memory and semantic search capabilities.
1d ago
Will agents like Git any more than we do?
Opinion piece questioning whether AI agents will adopt Git for version control and whether Git's UX issues matter differently for non-human users.
1d ago
Show HN: Catio - AWS Diagrams and Architecture Copilot
Catio tool generates AWS architecture diagrams with AI copilot for Q&A and recommendations. Developer tool combining infrastructure visualization with LLM.
1d ago
Show HN: Server-side analytics catches AI crawlers and attackers JS misses
SysWP Radar detects AI crawlers and bots server-side for WordPress. Developer tool for analytics and bot detection.
1d ago
"This paper is LLM reviewed" > "this paper is peer-reviewed"
Opinion piece questioning whether LLM review is superior to peer review for papers. Commentary on LLM applications in research.
1d ago
Show HN: Homecrew – Share agent skills across your team and keep them in sync
Homecrew is an open-source tool for sharing and syncing AI agent skills across teams using git-based version control and management.
1d ago
Show HN: Formae now supports Kubernetes, Helm, .tfvars and a public plugin hub
Formae is an open-source Infrastructure-as-Code system with new support for Kubernetes, Helm, Terraform, and a public plugin hub.
1d ago
Show HN: Diom – Back end primitives (queue, rate limit, etc.) in one Rust binary
Diom backend server provides cache, queues, rate-limiting, idempotency in single Rust binary. Open-source developer infrastructure tool.
1d ago
Stopgap for Claude -p before Anthropic's June 15 billing split
Stopgap announcement for Claude pricing changes before June 15 billing split.
1d ago
Learning Systems and Innate Behavior
Essay on learning systems and innate behavior in organisms. Off-topic.
1d ago
Verifying EDA and compiler optimizations once and for all
ParaBit solver verifies correctness of EDA and compiler optimizations using parametric bitvector theory, presented at CAV 2026.
1d ago
StepStone: LLM-Based GPU Kernel Driver Fuzzing via User-Space Libraries [pdf]
Research paper on using LLMs to fuzz GPU kernel drivers via user-space libraries. Novel ML application for security testing.
1d ago
Show HN: We wrote forensic intelligence reports on 20 open-source codebases
Forensic analysis reports on 20 open-source codebases examining architectural assumptions and design flaws.
1d ago
Show HN: Lance – image/video generation and understanding in one model
Lance is an open-source multimodal model with 3B active parameters for image/video generation and understanding, released by ByteDance with code and paper.
1d ago
You never learned to delegate. AI just made it obvious
Opinion article about AI changing delegation practices in organizations.
1d ago
AI-generated abandonware is hollowing out open source
Opinion piece about AI-generated low-quality packages degrading open source ecosystems.
1d ago
Chat client for Meshtastic LoRa mesh networks in Emacs
Emacs chat client for Meshtastic LoRa mesh networks using direct USB serial connection.
1d ago
Localgcp: LocalStack for GCP, emulating 14 Google Cloud services locally
LocalStack-equivalent open-source emulator for 14 GCP services including Vertex AI and BigQuery, works offline with standard client libraries.
1d ago
Formal Verification Gates for AI Coding Loops
Research on formal verification methods for ensuring reliability in AI coding agent loops.
1d ago
Benchmarking AI coding agents for distributed SQL: 350 runs, 17 models
Benchmark study evaluating 17 AI coding agents across 350 runs on distributed SQL tasks.
1d ago
Co-Scientist: A multi-agent AI partner to accelerate research
Co-Scientist: multi-agent AI system designed to partner with researchers and accelerate scientific discovery.
1d ago
Betlang: A tiny (50kb) programming language detection model
Betlang is a 50KB machine learning model for CPU-based programming language detection supporting 30+ languages with ranked probability outputs.
1d ago
Microsoft Agent 365: Autonomous AI for enterprise governance by 2026
Microsoft announces Agent 365 for autonomous enterprise governance by 2026. Product announcement for AI agents in enterprise.
1d ago
ChatGPT and other AI bots made errors before Scottish election, study finds
Study finds ChatGPT and AI bots made factual errors during Scottish election. Research on LLM accuracy in political context.
1d ago
Show HN: MulmoClaude – open-source platform where Claude composes tools and GUIs
MulmoClaude is an open-source AI-native application platform where Claude composes tools and GUIs as plugins in a single registry, with examples including accounting systems and obligation engines.
1d ago
Anthropic, Gates Foundation launch $200M partnership for AI in health, education
Anthropic and Gates Foundation commit $200M for AI in health and education. Partnership announcement for public goods.
1d ago
Show HN: I built an AI cloud architect that ships working infrastructure
LLM application that generates cloud infrastructure designs from descriptions/sketches, producing validated code, security grades, and cost estimates.
1d ago
Show HN: Hocuspocus 4 – Yjs collab server
Hocuspocus v4 released under MIT license, a WebSocket backend for real-time collaboration built on Yjs CRDT library, running on Bun, Deno, Cloudflare Workers.
1d ago
Show HN: atrium – a resumable, tiling workspace manager for Claude Code, Codex
macOS workspace manager for Claude Code and other AI dev agents with resumable sessions, terminals, browsers, and task management.
1d ago
Testing distributed systems with AI agents
Framework for AI agents to design and run tests for distributed systems, generating test plans and findings reports with multi-model support.
1d ago
Kickstarting "The Reverse Centaur's Guide to Life After AI"
Book promotion for speculative fiction about life after AI. Kickstarter campaign for DRM-free distribution.
1d ago
Show HN: Free AI headshots from one selfie, no signup
Free AI headshot generator creating studio-quality profile pictures from single selfie input.
1d ago
TokenScale – AI API pricing in words you know (The Hobbit = $0.06)
Browser-based calculator comparing LLM API pricing across models using familiar content examples (novels, emails, contracts).
1d ago
RTMX: Intent Layer for Agentic Engineering
RTMX is a CLI tool for requirements traceability that integrates with AI agents via MCP, allowing agents to build against defined specifications tracked in git.
1d ago
OCL Nexus Local – Open-source local compute fabric for AI agents
OCL Nexus Local is an open-source compute fabric for local-first AI agent development, featuring isolated Ubuntu sandboxes, Model Context Protocol support, and Docker Compose deployment.
1d ago
You can't whisper at an AI agent
Stripe developer relations overview with no technical content about AI agents.
1d ago
Token Saver for AI Tools
Educational tool explaining token economics for AI APIs, comparing tokenization and pricing across Claude, Gemini, and ChatGPT.
1d ago
Max-severity flaw in ChromaDB for AI apps allows server hijacking
Security vulnerability (CVE-2026-45829) in ChromaDB vector database allowing unauthenticated code execution on exposed servers.
1d ago
Good Code, Wrong Feature: The Handoff Problem
Essay on coordination bottlenecks in AI-driven engineering teams, discussing communication failures and documentation practices.
1d ago
Aperion Shield: local guardrail that blocks destructive AI coding agent ops
Open-source MCP server providing safety guardrails for AI coding agents, blocking destructive operations across SQL, git, filesystem, cloud, and kubernetes.
1d ago
We've entered a golden age of idea thieves and liars
Opinion piece about misinformation and plagiarism. Not AI/tech-specific.
1d ago
LLM INQUISITOR: Evaluating how AI models handle long, realistic tasks
LLM INQUISITOR is a methodology and tool for evaluating AI systems in real-world workflows, measuring stability, reliability, and safety beyond benchmark performance.
1d ago
Show HN: One dev environment for humans, CI, and AI agents
Framework for unified dev environments supporting humans, CI systems, and AI agents, addressing the multi-audience complexity of modern development workflows.
1d ago
Show HN: Agyn, an open-source Kubernetes runtime for AI agents
Agyn is an open-source Kubernetes platform for deploying AI agents to enterprise infrastructure with built-in security, budget controls, and secret management.
1d ago
HTML-anything – The agentic HTML editor – your local AI agent writes the HTML
HTML-anything is an agentic HTML editor where local AI agents autonomously write and generate HTML code.
1d ago
Benchmarking AI agents across five TypeScript back end frameworks
Benchmark comparison of AI agent performance across five TypeScript backend frameworks.
1d ago
Using an LLM for Research
Title only: Using an LLM for Research. No content provided.
1d ago
Ask HN: Who is working on applying AI to learning?
Hacker News discussion question about AI applications in education and learning. Minimal content.