2/28/2026
Switch between different Claude Code profiles
Tool for managing multiple Claude Code profiles. Direct developer tooling for LLM-powered coding.
2/28/2026
Show HN: I dump all my private notes into an LLM and tell it to build me a site
Publishing platform that generates sites from unstructured notes using agentic LLM with minimal guardrails. Explores creative LLM applications.
2/28/2026
Ask HN: If AI boosts productivity so much, why would a company lay anyone off?
HN discussion thread on AI productivity economics and employment. Speculative, off-topic.
2/28/2026
Show HN: Mdspec.dev – open-source spec management platform for technical teams
Open-source spec management platform optimized for agentic software development. Targets AI-assisted development workflows.
2/28/2026
Should AI chatbots have ads? Anthropic says no
Anthropic's position against ads in AI chatbots. Business/policy commentary, not technical.
2/28/2026
Show HN: AIQuotaBar – See Claude/ChatGPT usage limits in your macOS menu bar
macOS menu bar utility tracking Claude and ChatGPT usage limits. Niche developer tool for LLM API management.
2/28/2026
DeepSeek to release new AI model next week in new challenge to US rivals
News report about DeepSeek planning to release new AI model next week as competitive challenge to US AI companies.
2/28/2026
Show HN: Voice-coded a Doom-scroll Hacker News (Twitter-style feed)
Hacker News infinite-scroll clone built entirely via voice coding using OpenAI Codex. Demonstrates LLM-assisted development workflow.
2/28/2026
Show HN: GitShow Repo Showroom – a landing page for any GitHub repo
GitShow generates showroom landing pages for GitHub repositories, aggregating contributor info, languages, commit activity, and health metrics.
2/28/2026
Show HN: Lightweight, S3-compatible object storage server with built-in web dash
S3-compatible object storage server with web dashboard. Infrastructure tool without AI/ML focus.
2/28/2026
LLMs killed the privacy star, we can't rewind, we've gone too far
Research shows LLMs can deanonymize internet users more efficiently than humans, extending privacy risks beyond traditional de-anonymization methods.
2/28/2026
We measured 62% token reduction
LLM output verification and compliance tool achieving 62% token reduction with Python SDK and MCP integration.
2/28/2026
S2S – Physics-certified motion data for Physical AI (7 biomechanical laws)
S2S provides physics-certified motion data for training physical AI systems, validating sensor data against biomechanical laws for robots and prosthetics.
2/28/2026
Simplifying OpenClaw: I built a library for community workflows
Library for OpenClaw community workflows.
2/28/2026
Show HN: XFolder – A powerful multi-pane file manager for Mac
macOS file manager with multi-pane views and smart directory navigation built with C# and Swift.
2/28/2026
Show HN: Using a mobile LLM app to safely operate a desktop computer
Computer-using AI agent that uses mobile LLM apps (ChatGPT/Claude) as intelligence source with external execution gateway for OS actions.
2/28/2026
Show HN: I built a Canva-like editor at 14 – it ranked #4 organically in 30 days
Web-based design editor focused on manual workflows with optional AI features. Built by 14-year-old developer.
2/28/2026
Show HN: LLM-JSON-guard – Middleware to auto-repair broken AI outputs
Middleware to auto-repair and validate malformed JSON outputs from LLMs. Improves reliability of AI model outputs.
2/28/2026
Show HN: LinkPrism – Route URLs to the right Chrome profile automatically
macOS app that routes URLs to correct Chrome profiles based on domain rules.
2/28/2026
Show HN: Mowgli – Figma for the agent era, with Claude Code and design export
AI-native design canvas with Claude Code integration and design export. Targets product scoping and ideation bottleneck in agent-driven development.
2/28/2026
Show HN: The rust of Knox:anti-ASIC lattice L1 built by a dad and his 11yo son
KNOX Protocol: a post-quantum lattice-based Layer-1 blockchain built in Rust by a developer and his son.
2/28/2026
New habits for tech writers in the age of LLMs
Article about tech writing practices in LLM era. Minimal content provided.
2/28/2026
Show HN: Enclv – A lightweight Docker containment environment for AI agents
Docker containment environment for running AI-generated code and autonomous scripts locally with network/file restrictions and credential isolation.
2/28/2026
Show HN: Shodh– AI memory that learns from use, no LLM calls, single Rust binary
Offline persistent memory system for AI agents that learns from use. Single Rust binary, no LLM calls required. Addresses context loss between sessions.
2/28/2026
Anthropic vs. DoD: "Any lawful use" is a fight about control
Opinion piece on Anthropic's "any lawful use" policy and AI in military applications, from perspective of former defense technologist.
2/28/2026
Show HN: Fava Trails – Git-backed memory for AI agents using Jujutsu (JJ)
Git-backed memory system for AI agents using Jujutsu. Addresses memory poisoning through version-controlled agent state and history.
2/28/2026
Show HN: SQLite for Rivet Actors – one database per agent, tenant, or document
SQLite storage backend for Rivet Actors (Durable Objects alternative). Per-agent/tenant databases for AI agent state, message history, embeddings.
2/28/2026
Claude and Gemini debate AI consciousness then analyze their debate performances
Debate transcript between Claude and Gemini on AI consciousness with meta-analysis of debate quality. Philosophical discussion.
2/28/2026
Istota is a powerful (non-claw) AI agent that lives in Nextcloud
AI agent that integrates with Nextcloud as native user. Collaborates on files, manages calendars via Claude Code. Data stays on-premises.
2/28/2026
WebMCP Not Quite a Standard Yet
Minimal stub post about WebMCP standard.
2/28/2026
Show HN: Rust-powered document chunker for RAG – 40x faster, O(1) memory
Rust-based document chunking library for RAG pipelines with Python bindings, 40x faster than LangChain with O(1) memory complexity.
2/28/2026
Show HN: Ditch your budget app subscription. Surebeans is a modern YNAB4
Desktop/web budget management application as alternative to YNAB4, unrelated to AI/ML interests.
2/28/2026
Show HN: LexPrep – reproducible lexical preprocessing for research experiments
Linguistic data preparation toolkit for wordlist processing with support for multiple languages and NLP tasks like POS tagging and sampling.
2/28/2026
Show HN: Telos – A structured context framework for humans and AI agents
Intent and decision tracking framework layered on Git that captures queryable rationale for code changes in machine-readable format.
2/28/2026
All LLM
Directory listing major LLM models and AI agents with minimal original content, primarily aggregating existing model releases.
2/28/2026
Don't trust AI agents
Security analysis arguing AI agents should be treated as untrusted threats, requiring defensive architecture rather than permission-based controls.
2/28/2026
Show HN: Grantex – Delegated authorization protocol for AI agents
Production-ready identity and authorization framework for AI agents with scoped permissions and audit trails; OAuth equivalent for agentic systems.
2/28/2026
Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
Research on improving LLM-agent tool use reliability by learning to rewrite tool descriptions for better instruction following.
2/28/2026
Nao: Open-Source Analytics Agent
Open-source analytics agent framework with CLI for context creation and chat UI deployment enabling non-technical users to query data.
2/28/2026
AI companies want you to stop chatting with bots and start managing them
Industry shift from conversational AI to agent team management: Anthropic and OpenAI release products for supervising parallel working agents.
2/28/2026
Our agreement with the Department of War
Company announces classified AI deployment agreement with Pentagon, claims stronger guardrails than competitors.
2/28/2026
The AI field guide for people with real jobs
Commentary on AI hype cycle explaining LLMs, agents, and copilots with critical perspective on unearned hype.
2/28/2026
Show HN: AI Agent Team Framework
Framework for building and orchestrating autonomous AI agent teams. Includes multi-agent coordination, GitHub routing, and documentation.
2/28/2026
Show HN: Prompt-run – run .prompt files against any LLM from the terminal
CLI tool for version-controlling and testing prompts as first-class artifacts with YAML configuration and cross-model execution.
2/28/2026
Show HN: hosted or self-hosted open-source Intercom alternative, Convex Backend
Opencom: open-source Intercom alternative for customer messaging. Developer tool but not AI-focused.
2/28/2026
Sync your coding agent activity across sessions and users
Codaph: CLI tool for inspecting and sharing AI coding agent activity across sessions with persistent memory integration.
2/28/2026
Show HN: H-CLI – Manage network infrastructure with natural language
H-CLI tool for managing network infrastructure via natural language commands. LLM-powered multi-vendor network automation with Claude or self-hosted models.
2/28/2026
Show HN: Core – Constitutional governance runtime for AI coding agents
Constitutional governance runtime for AI coding agents. Enforces 92 architectural rules at runtime via deterministic engines to prevent constraint violations.
2/28/2026
From Slop to Skill: An Agent Proficiency Engine Using RLM
Agent proficiency development engine built using Recursive Language Models for continuous improvement through RLM feedback loops.
2/28/2026
Show HN: Jarvish – The J.A.R.V.I.S. AI inside your shell investigates errors
Jarvish: Shell integration tool using LLM to investigate and resolve terminal errors without breaking workflow.