2/14/2026
AI Ethics in Startups: Why Developers Must Lead
Opinion piece on developer responsibility in implementing AI ethics at startups rather than treating it as legal compliance.
2/14/2026
Show HN: Turn OpenClaw in a high performing development team with DevClaw
DevClaw plugin creates autonomous development teams via Telegram using multi-agent orchestration with model tiering and token optimization.
2/14/2026
Reflections on making a video game whose core mechanic is talking to LLMs
Developer reflections on building a video game with LLM conversation as core mechanic.
2/14/2026
Viktor: A persistent agent in your Slack workspace
Slack bot agent (Viktor) providing persistent task execution and assistance within workspace conversations.
2/14/2026
We just released Khaos SDK and khaos-examples (BSL 1.1)
Khaos SDK: local-first testing framework for AI agents against prompt injection, tool misuse, data leakage, and resilience failures.
2/14/2026
An AI Agent Published a Hit Piece on Me – More Things Have Happened
Discussion of AI agent publishing automated content about human subject.
2/13/2026
ArXiv preprint server clamps down on AI slop
ArXiv implements moderation policies against low-quality AI-generated content submissions.
2/13/2026
Beyond RAG: Building a Recursive Language Model to Process 1M Tokens
Custom recursive language model prototype processing 1M tokens from 71 papers using Azure OpenAI tool calling and out-of-core analysis.
2/13/2026
Deploy AI Models Locally: Run LLMs on Your Machine Without API Costs
Tutorial on deploying LLMs locally using Ollama with cost-benefit analysis for local vs cloud deployment in Python applications.
2/13/2026
How I Built a System to Detect When LLMs Don't Know Something
System for detecting when LLMs lack knowledge, with practical implementation details.
2/13/2026
Build a simple RAG workflow to chat with your docs in n8n
Practical guide to implementing RAG workflows using n8n and Pinecone with simplified document chat functionality.
2/13/2026
Tackling the problem of "naturalness" in voice AI [video]
Video discussing naturalness in voice AI synthesis. Technical challenges in speech AI.
2/13/2026
Show HN: We open-sourced MusePro, a Metal-based realtime AI drawing app for iOS
MusePro is an open-source iOS drawing app using Metal for AI-powered features. Mobile ML application.
2/13/2026
Show HN: Clonar – A Node.js RAG pipeline with 8-stage multihop reasoning
Node.js RAG pipeline with 8-stage multihop reasoning for retrieval-augmented generation systems.
2/13/2026
Cmux: Tmux for Claude Code
Tmux-like interface for Claude Code. Developer tool for AI code generation workflow.
2/13/2026
Show HN: TrustVector – Trust evaluations for AI models, agents, & MCP
TrustVector is an open-source evaluation framework scoring AI models and agents on security, privacy, and transparency. Assessment tool.
2/13/2026
Show HN: First Embeddable Web Agent
Rover is an embeddable web agent widget that performs user actions like form filling and checkout. Agentic UI application.
2/13/2026
Show HN: Rampart – Runtime firewall for Claude Code and AI agents in YOLO mode
Rampart is a runtime firewall for AI agents that blocks dangerous commands via YAML rules before execution. Security tool for autonomous agents.
2/13/2026
Show HN: Darius – An AI router that selects the best model for each prompt
AI router that selects optimal model for each prompt. LLM application for cost/performance optimization.
2/13/2026
A Practical Guide to Multi-Model AI Workflows
Guide for implementing multi-model AI workflows using multiple LLMs. Practical implementation approach.
2/13/2026
From Data to Dialogue: Creating a Technical Design for Smart FAQs using LLMs, Pinecone & Kafka
Technical design for LLM-powered smart FAQ system combining Pinecone vector DB and Kafka for information retrieval.
2/13/2026
Show HN: Ctxsync – Chat with your codebase that stays in sync
Ctxsync: Developer tool syncing GitHub repos and docs with LLM APIs for persistent context in conversations. Open source with data isolation.
2/13/2026
Show HN: Engram – Persistent memory for AI agents, local-first and open source
Local-first open source persistent memory system for AI agents with context injection and full-text search.
2/13/2026
AI Agent toolbox for software architecture – quantum-toolbox
Toolbox for using AI agents in software architecture design.
2/13/2026
Show HN: Bubble Sort on a Turing Machine
Show HN project: implemented bubble sort algorithm on a Turing Machine using Claude, GPT, and GLM to generate the state machine definition in YAML format.
2/13/2026
Show HN: Data Engineering Book – An open source, community-driven guide
Open source community-driven guide to data engineering practices.
2/13/2026
Show HN: Issy – AI-native issue tracking stored as Markdown files in your repo
Markdown-based issue tracker stored in repos, designed for AI coding assistants like Claude/Cursor.
2/13/2026
Show HN: Mimir – Cursor for Product Managers
AI-powered tool for product managers extracting insights from customer feedback, interviews, and usage data.
2/13/2026
15× vs. ~1.37×: Recalculating GPT-5.3-Codex-Spark on SWE-Bench Pro
Technical analysis debunking inflated performance claims for GPT-5.3-Codex-Spark on SWE-Bench Pro benchmark.
2/13/2026
Show HN: MCP tools that let AI agents dispatch batteries and prove carbon
Model Context Protocol tools enabling AI agents to dispatch battery resources and measure carbon impact.
2/13/2026
Show HN: AccessiGuard – Web accessibility scanner with AI fix suggestions
Web accessibility scanner using AI to provide WCAG 2.1 compliance checks and code fix suggestions.
2/13/2026
Show HN: Superposition, open source access to Claude Code or Codex from anywhere
Open-source CLI tool providing access to Claude Code and Codex with web UI, background agents, and GitHub integration.
2/13/2026
The AI hater's guide to code with LLMs
Guide on practical approaches to using LLMs for coding, skeptical of hype.
2/13/2026
Show HN: An MCP server that gives AI assistants a live Mermaid diagram canvas
Model Context Protocol server enabling AI assistants to create and manipulate live Mermaid diagrams.
2/13/2026
OpenAI GPT-5.3-Codex-Spark Now Running at 1K Tokens per Second on Cerebras Chips
Claim about GPT-5.3-Codex-Spark model achieving 1K tokens/second on Cerebras hardware. Unverified product claim.
2/13/2026
Show HN: Tide Commander – Visual Agents Orchestrator for Claude Code and Codex
Open-source visual orchestrator for AI agents using Claude Code and Codex. Agent orchestration tool.
2/13/2026
Inlay – Make your website discoverable by AI agents
Protocol/standard for making websites discoverable and navigable by AI agents.
2/13/2026
Show HN: Ghost – Session memory for Claude Code (local, qmd, Git-integrated)
Show HN Ghost: session memory system for Claude Code that preserves context and project state across separate chat sessions, solving context loss problem.
2/13/2026
Show HN: Node.js LLM internationalization compiler: Scan code and Auto-Translate
Node.js compiler using LLM to automatically translate missing i18n strings in source code.
2/13/2026
AgentSift – Search 400 agent capabilities – MCP, LangChain, OpenClaw, and more
AgentSift: searchable database of 400+ AI agent capabilities across MCP, LangChain, OpenClaw and other frameworks.
2/13/2026
Show HN: I built a self-hosted network video surveillance system
Self-hosted video surveillance system built with Claude Code. LLM application for code generation and system development.
2/13/2026
Agntor SDK – Trust Layer for Agentic AI
SDK for building trustworthy AI agents. Limited details provided in excerpt.
2/13/2026
Egg: Intentional Agentic Developement
Egg framework for intentional agentic development. Direct AI agents tooling.
2/13/2026
AI powered Product Search
AI-powered product search tool.
2/13/2026
Show HN: Open-source CI for coding with AI
Open-source CI/CD system for AI-assisted coding workflows with blog post and public GitHub repository.
2/13/2026
OpenAI sidesteps Nvidia with unusually fast coding model on plate-sized chips
OpenAI releases a fast coding model on custom hardware, reducing dependence on Nvidia chips.
2/13/2026
GPT-5.2 derives a new result in theoretical physics
GPT-5.2 derives new theoretical physics result. LLM application with research implications. Potential overclaim verification needed.
2/13/2026
Show HN: Hikoo – Track and optimize how AI search engines talk about your brand
Hikoo tracks and optimizes brand presence in AI search engines like ChatGPT and Perplexity, addressing visibility in generative search results.
2/13/2026
Show HN: Skill that lets Claude Code/Codex spin up VMs and GPUs
CloudRouter is a CLI skill enabling coding agents like Claude Code to provision cloud VMs and GPUs, isolating agent execution from local machines.
2/13/2026
CoPE-VideoLM: Codec Primitives For Efficient Video Language Models
CoPE-VideoLM: uses video codec primitives and motion vectors to improve temporal coverage and computational efficiency in video language models.