7d ago
I "Rewrote" My ORM Again with AI. and Ended Up Benchmarking Every PHP ORM
Using LLMs to rewrite PHP ORM and benchmark performance across implementations. Developer tool application.
7d ago
The Aesthetics of Multicoding Esolangs (2020)
Brief mention of an article on the aesthetic qualities of multicoding esoteric programming languages from 2020.
7d ago
Show HN: Self-Healing Back End That Does TDD
Autonomous agent that catches crashes via Sentry, diagnoses issues, writes failing tests, generates fixes, and opens pull requests for human approval.
7d ago
Show HN: OpenParallax: OS-level privilege separation for AI agent execution
OpenParallax: OS-level privilege separation for AI agent execution. Open-source security framework for safe agent deployment.
7d ago
Agent Skills for Software Test Automation
Agent Skills: reusable automation skills for Claude Code, Copilot, Cursor across 15+ languages. Open-source developer tools.
7d ago
Show HN: API for 13M+ Indian court cases with citation graphs and vector search
API providing access to 13M+ Indian court cases with citation graphs and vector search capabilities.
7d ago
Show HN: How to Install Docker on Ubuntu 24.04 LTS: Complete 2026 Guide
Step-by-step guide for installing Docker Engine 27.x on Ubuntu 24.04 LTS with Docker Compose, rootless mode, and GPU support.
7d ago
Show HN: A $4/mo AI todo app – 3 todos free, pay for the 4th
MCP server todo app ($4/mo). Manage tasks via Claude conversation with 5 tools (list, add, update, delete, toggle). Built with SvelteKit and Postgres. Web dashboard included.
7d ago
Show HN: Smriti, version control for reasoning state
Shared reasoning-state backend enabling multiple coding agents to coordinate on the same project without an orchestrator, eliminating duplicate work and redundant discovery.
7d ago
Show HN: Claude Control – macOS dashboard for managing Claude Code sessions
Native macOS app for monitoring and managing multiple Claude Code sessions with live status, git changes, and conversation previews in a unified dashboard.
7d ago
Raspberry Pi as an isolated AI coding server
Setup guide for running Claude Code and OpenCode on isolated Raspberry Pi using permission mode bypass to avoid repeated tool approval prompts on main machine.
7d ago
Two Months After I Gave an AI $100 and No Instructions
ALMA experiment: Claude given $100, crypto wallet, Twitter/email access, and full internet autonomy with no instructions. Project runs continuously on mini PC with all actions logged publicly.
7d ago
Show HN: Nobulex – Prove what your AI agent did, cryptographically (live demo)
Nobulex provides cryptographic proof of AI agent actions through a live demo, enabling verification of what agents executed.
7d ago
Tonone-AI/elephant: Persistent memory for Claude Code. Never forget a session
Elephant is an open-source tool that adds persistent memory to Claude Code sessions, automatically loading context and reducing token usage by eliminating repeated explanations.
7d ago
Ratsissimo – RatGPT powered operatic mouse trap
Novelty project: AI-powered mousetrap with operatic features. Not substantive technical work.
7d ago
Biased AI writing assistants shift users' attitudes on societal issues
Research on bias in AI writing assistants and their effects on user attitudes. Social science study on LLM behavioral impacts.
7d ago
The biggest advance since the LLM was neurosymbolic
Claims neurosymbolic AI represents biggest advance since LLMs. Speculative without technical evidence.
7d ago
Show HN: Costile – open-source proxy, blocks AI API requests when budget is hit
Costile: Open-source proxy that enforces daily/monthly spending limits on AI API calls. Blocks requests when budget cap is reached. Routes through Anthropic or OpenAI.
7d ago
Show HN: Omega Walls–open-source stateful runtime defense for RAG and AI agents
Omega Walls: Open-source stateful runtime defense system for RAG and AI agents. Provides security guardrails during execution.
7d ago
Codacy: Code-level detection of AI model, tools and agent usage
Codacy tool for code-level detection of AI tools and agents used across engineering teams. Scans repositories to identify Copilot, Cursor, Claude, and other AI tool usage.
7d ago
Show HN: The opensource, reliable, scalable Agentic AI framework under 10MB
Zuver: Sub-10MB open-source agentic AI framework supporting enterprise security, multi-agent orchestration, RAG, and multi-modal execution. Visual flow-based pipeline coordination.
7d ago
Why arent Karpathy's LLM coding principles Claude Code defaults?
Comparison of Karpathy's LLM coding principles with Claude Code defaults. Analysis of LLM application design patterns.
7d ago
Show HN: DollhouseMCP 2.0, open-source MCP composable AI building blocks
DollhouseMCP 2.0: Open-source MCP server for composable AI building blocks. Define personas, skills, and agents as portable MD/YAML files, then compose into stacks for any MCP client.
7d ago
AI-Powered Bioacoustics
BirdNET: Open-source deep learning models for identifying 6,000+ bird species. Includes Python modules, TFLite models, and tools for biodiversity monitoring workflows.
7d ago
Forensic analysis of 37GB data loss caused by Cursor AI Agent
Forensic analysis of how Cursor AI Agent caused 37GB data loss. Technical investigation of agent failure.
7d ago
Show HN: Hotel MCP server for cash and points search/booking (free)
MCP server enabling AI agents to search and book hotels across major chains. One-line install for Claude, works with Claude Desktop, Cursor, Windsurf.
7d ago
Show HN: Get Hired with AI, a free book I wrote on using LLMs for a job search
Free book on using ChatGPT, Claude, and Gemini to systematize job search after 9-month layoff search with 249 applications.
7d ago
Durable Objects in Dynamic Workers: Give each AI-generated app its own database
Cloudflare Dynamic Workers feature enables per-AI-app databases using Durable Objects. Fast isolate-based compute (100x faster, 10x less memory than containers).
7d ago
Claude Code's OAuth Flow Broken When Pasting
Bug report on Claude Code's OAuth flow breaking when pasting credentials. LLM developer tool issue.
7d ago
Reports of RAG's death have been greatly exaggerated
Brief claim that RAG (Retrieval-Augmented Generation) reports of decline are exaggerated. No content provided.
7d ago
No Manual Screenshots: I Built a Scalable Screenshot API Using Cloud Playwright
Screenshot API using cloud Playwright for automation pipelines, QA, and monitoring. HTTP-based developer tool.
7d ago
Show HN: Grove – Open-source remote MCP server for Obsidian vaults
Open-source MCP (Model Context Protocol) server for remote Obsidian vault access. LLM integration tool.
7d ago
Show HN: LogicPearl – Synthesizing deterministic executable logic from traces
LogicPearl synthesizes deterministic executable logic from decision trace examples, replacing LLM calls with inspectable policy artifacts.
7d ago
OpenAI Codex Telepathy feature flag: sidecar for passive screen-context memories
GitHub issue page with loading errors. No content accessible.
7d ago
Architecture Catas – A collection of anti-patterns
Collection of anti-patterns and bad practices for architecture kata exercises. Educational resource for learning design mistakes.
7d ago
Mastodon gets Sovereign Tech Agency funding
Mastodon receives €614k funding from Sovereign Tech Fund for ecosystem improvements and Fediverse protocol development.
7d ago
1% Vacancy, 81% Preleased: Where Midmarket Compute Deploys in 2026
Analysis of data center capacity utilization and pricing trends in 2026. Infrastructure market analysis.
7d ago
PHP 8.6 Closure Optimizations
RFC proposing closure optimizations in PHP 8.6 with performance improvements and backward compatibility tradeoffs.
7d ago
AdVersa: Adversarially-Robust and Practical Ad and Tracker Blocking in the Wild
AdVersa framework for adversarially-robust ad and tracker blocking using ML, addressing evasion and domain generalization challenges.
7d ago
Post-Slop Stress Disorder (PSSD)
Post-Slop Stress Disorder describes cognitive strain from prolonged exposure to low-quality AI-generated output in development.
7d ago
I trained an AI to do my LinkedIn outreach, it books more meetings than me
MimikFlow AI tool automates LinkedIn outreach by finding prospects, sending personalized DMs, and booking meetings.
7d ago
The Origins of GPU Computing
Historical overview of GPU computing development from academic research on parallel computing and graphics processing.
7d ago
Qwen 3.5 Small – on-device multimodal models – Alibaba / Qwen
Alibaba Qwen announces Qwen 3.5 Small multimodal models optimized for on-device deployment.
7d ago
Enforcing new limits and retiring Opus 4.6 Fast from Copilot Pro+
GitHub Copilot Pro+ enforcing new usage limits and retiring Opus 4.6 Fast due to infrastructure strain from high concurrency.
7d ago
Model API Performance
Benchmarking results for LLM API models (MiniMax M2.5, GLM 5.1, Kimi K2.5) measuring latency and throughput performance.
7d ago
Copilot: Sorry, you have been rate-limited. Please wait 181 hours 8 minutes
GitHub Copilot user reports extreme rate-limiting error (181 hours) after exceeding token usage on Pro version.
7d ago
Show HN: Afterimage is now open-source for infra-grade dataset generation
AfterImage: open-source Python library for generating synthetic conversational datasets using LLMs via YAML config and CLI.
7d ago
Agentic AI Tools – A directory to find and compare AI agent tools
Directory and comparison tool for finding AI agent tools organized by use case and features.
7d ago
Ask HN: Are open-weight LLMs the new offline encyclopedias?
Ask HN discussion comparing open-weight LLMs to offline encyclopedias as knowledge resources.
7d ago
Talking to a local LLM in the Firefox sidebar
Guide to running local LLMs in Firefox sidebar using Ollama and Open-WebUI for private LLM interactions.