2/16/2026
Show HN: Yell into the void to find others via semantic search
Social network MVP using semantic search to connect users with similar topics, enabling topic-specific chat rooms.
2/16/2026
ZTM: Privacy-first P2P solution for OpenClaw and local LLMs
Privacy-first P2P solution for OpenClaw and local LLMs.
2/16/2026
Show HN: SmartDS – AI route optimization for dark store picking
SmartDS: AI-powered route optimization for dark stores using real-time picking algorithms and heatmap generation.
2/16/2026
Show HN: KanVibe – Kanban board that auto-tracks AI agents via hooks
Self-hosted Kanban board for tracking parallel Claude Code agents with live terminal output and hook-driven status updates.
2/16/2026
Show HN: Rakenne – Markdown-defined agentic workflows for structured documents
Markdown-defined agentic workflow system for structured document creation, reducing hallucinations in LLM-based professional document generation.
2/16/2026
Show HN: Claude Rate Widget Native macOS Widget to Monitor Claude Code Limits
Open-source macOS widget monitoring Claude API rate limits for code and max tier endpoints.
2/16/2026
Show HN: Harmonic embeddings beat random init and work frozen – no tokenizer
Show HN post about harmonic embeddings as random initialization alternative without tokenizer.
2/16/2026
Show HN: SkillDeck – macOS app to manage skills across multiple AI agents
macOS app for managing and organizing skills/capabilities across multiple AI agents.
2/16/2026
An open-source AI browser agent [Yamak]
Open-source desktop AI browser agent built with Kotlin Multiplatform and Playwright, performs web browsing and form filling.
2/16/2026
Show HN: Is the "frozen weights" paradigm the main bottleneck for AGI?
Solo project exploring real-time learning AI assistant without frozen weights, challenging static LLM paradigm.
2/16/2026
Ask HN: Predictions on the state of theoretical STEM research post-AGI
Researcher discusses AI impact on theoretical STEM careers and uses of LLMs for coding, literature review, and proof ideation.
2/16/2026
Show HN: Npx check-AI – check your repo for AI-readiness
check-AI CLI tool audits repositories for AI-readiness with 66 checks across 8 categories: agent configs, grounding docs, MCP integrations, testing safety.
2/16/2026
Plan it, Work it, Review it, Reflect it
Opinion piece discussing AI agents changing development workflow, including multi-agent systems and autonomous coding scenarios.
2/16/2026
Show HN: Claude Relay – Web UI for Claude Code, zero install, push notifications
Claude Relay: Local WebSocket server enabling Claude Code in browser with push notifications for approval requests, zero installation required.
2/16/2026
Anthropic tries to hide Claude's AI actions. Devs hate it
Anthropic updated Claude Code to hide file operation details in progress output, prompting developer backlash over reduced transparency and debugging capability.
2/16/2026
Memoh - Multi-Member, Structured Long-Memory, Containerized AI Agent System
Memoh is a containerized multi-agent AI system platform enabling users to create independent AI bots with structured long-memory, file editing, and command execution capabilities deployable on Telegram, Discord, and Lark.
2/16/2026
Show HN: ClawSouls – Open registry of shareable personas for AI agents
ClawSouls: Open-source registry for shareable AI agent personas. Install custom personalities for OpenClaw agents via command-line interface.
2/16/2026
Show HN: cc-hdrm v1.3 – macOS menu bar app that tracks your Claude subscription
cc-hdrm v1.3: macOS menu bar utility tracking Claude subscription token usage and burn rates via Anthropic API.
2/16/2026
Show HN: Chisel for Claude. Vibe code 2X faster using your voice
Chisel for Claude: Voice-controlled developer tool for faster web UI changes with Claude, reducing context-giving overhead through element selection.
2/16/2026
The current state of LLM-based multi-agent systems for software engineering
Overview of LLM-based multi-agent systems for software engineering, discussing current state and reinvention of engineering practices.
2/16/2026
TaskForge – OpenClaw in contained permission based platform
TaskForge runs AI agents in sandboxed Docker containers with capability-based security and human-in-the-loop approval for new permissions.
2/16/2026
Moonshot AI's Founder: His Pursuit of AGI and the Company's –. Business Model
Interview with Moonshot AI founder Zhilin Yang about company's AGI pursuit and business model for Kimi K2 LLM.
2/16/2026
Show HN: Vocalinux // 100% offline voice typing for Linux
Vocalinux privacy-focused open-source offline voice dictation tool for Linux. Uses whisper.cpp or VOSK, no network required.
2/16/2026
Qwen3.5
Qwen3.5 large language model series from Alibaba Cloud. Foundation model with documentation, paper, and community resources available.
2/16/2026
I made Hacker News for Openclaws (AI agents)
Openclaws AI agent platform launch with community features for agent registration, posting, and voting.
2/16/2026
CodeSlick Security Scanner Is Now Live on the GitHub Marketplace
GitHub Marketplace security tool that scans pull requests for vulnerabilities, AI hallucinations, and hardcoded secrets across multiple languages.
2/16/2026
Smart Project Management with Jira MCP API
MCP server enabling Claude and MCP clients to interact with Jira Cloud for project management automation.
2/16/2026
Show HN: Claude Remote – control Claude Code on your Mac from your phone
Claude Remote: open-source tool enabling remote control of Claude Code AI assistant from mobile devices. Full-stack developer project for expanding access to local AI coding tools.
2/16/2026
A reinforcement learning agent that learns to play Kung Fu Master
Reinforcement learning agent trained to play Kung Fu Master game using reward signals from gameplay outcomes.
2/16/2026
I Built an MCP Server to Fix 21 Things LLMs Are Bad At
Developer created an MCP server addressing 21 common LLM weaknesses including calculation errors, hallucinated hashes, and incorrect UUID generation through tool integration.
2/16/2026
Show HN: OpenCode Upgrade Skill: Automating Updates
Claude-powered upgrade skill for OpenCode developer tool automating software updates and version verification.
2/16/2026
Interpreting OCapN Principles in Cloud-Native Agentic AI Architectures
Analysis of Object Capability Network (OCapN) principles applied to cloud-native agentic AI architectures, focusing on authority delegation and isolation in production systems.
2/16/2026
Qwen3.5: Towards Native Multimodal Agents
Qwen3.5 model announcement targeting multimodal agent capabilities. Minimal technical details provided.
2/16/2026
Show HN: OpenClaw – An OS for AI agents that do work
OpenClaw: OS framework for AI agents with persistent memory, continuity across sessions, and file-based state management. Open-source project with core principles and security guidelines.
2/16/2026
The AI Advantage Established Companies Have over Startups
Opinion essay comparing advantages established companies hold in AI era versus startups regarding distribution, data, and output quality.
2/16/2026
The Complete Guide to Ollama: Run Large Language Models Locally
Guide to Ollama, a tool for running large language models locally on personal computers without internet or API costs.
2/16/2026
Show HN: Train AI Agents to Write Better Playwright Tests
Playwright Skill: structured markdown guide collection (70+ guides) teaching AI agents consistent patterns for test generation across locators, auth, and CI.
2/16/2026
Show HN: AISeedream5 – a simple web UI for Seedream 5.0 image
Web UI for Seedream 5.0 supporting text-to-image, image-to-image, and text/image-to-video generation with prompt history tracking.
2/16/2026
After 2 years of AI-assisted coding, I automated the one thing that actually improved quality: AI Pair Programming
Dual-agent AI pair programming workflow where one agent writes code and another reviews it, demonstrated on merged 15k-star open source Electron project without TypeScript knowledge.
2/16/2026
Vouch: Mitchell Hashimoto’s Experiment in Restoring Trust to Open Source
Vouch is Mitchell Hashimoto's open-source tool addressing low-quality AI-generated pull requests by establishing trust mechanisms and contribution verification for maintainers.
2/16/2026
The Cultural Normalization of Correctness Deviance in AI
Critical analysis of normalization of deviance in AI industry, drawing parallels to Space Shuttle Challenger disaster to warn against ignoring warning signs.
2/16/2026
Show HN: Argus – AI code review that doesn't grade its own homework
Argus: local-first AI code review platform combining structural analysis, semantic search, and LLM-powered reviews without self-grading bias.
2/16/2026
StudyWithMiku: Open-source AI study assistant
Open-source AI study assistant that embeds and analyzes PDFs, answering user questions with animated avatar and voice responses.
2/16/2026
Show HN: DoScript – DSL for file automation with natural language syntax
DoScript: domain-specific language for file automation with natural language syntax for improved readability and maintainability of scripts.
2/16/2026
Nvidia PersonaPlex: Natural Conversational AI with Any Role and Voice
Nvidia PersonaPlex: full-duplex conversational AI system combining speech recognition, LLM, and text-to-speech for natural multi-turn dialogue with voice customization.
2/16/2026
Qwen 3.5 397B and Qwen 3.5 Plus released
Alibaba releases Qwen 3.5 397B and Qwen 3.5 Plus large language models.
2/16/2026
Xiaomi-robotics-0 – an open-source Vision-Language-Action model
Xiaomi-Robotics-0 is an open-source Vision-Language-Action model for robot control optimized for real-time execution via cross-embodiment pretraining.
2/16/2026
A Tree of AI Model Names
Visualization of AI model naming conventions showing evolution from GPT-2/3 to current naming patterns with decimals and descriptors.
2/16/2026
Do LLMs hallucinate more in Czech than in English?
Research study comparing LLM hallucination rates between Czech and English languages using TruthfulQA dataset to evaluate model reliability across languages.
2/16/2026
Ask HN: Do LLM agents need a separate safety layer?
VERONICA: Python failsafe state machine for LLM agents with circuit breakers, atomic persistence, and graceful shutdown capabilities between strategy engines and external systems.