3/29/2026
UEdu – Student writing mental health signals with 40 psycholinguistic features
Open-source Python NLP library detecting mental health distress signals in student writing using 40 psycholinguistic features and XGBoost classifier.
3/29/2026
Show HN: AgentLens – Chrome DevTools for AI Agents (open-source, self-hosted)
Open-source Chrome DevTools for debugging AI agents with AI-powered failure analysis and trace replay.
3/29/2026
Spatial Audio Notifications for Multi Window Claude Code –> Claudio
Claudio tool adds spatial audio notifications to Claude Code windows, using stereo pings to indicate which terminal needs attention.
3/29/2026
100% Interception of Multi-Turn Jailbreaks on GPT-4o-Mini and Gemini
Research paper presenting four-layer defense architecture achieving 100% interception of multi-turn jailbreak attacks on GPT-4o-mini and Gemini models.
3/29/2026
AI software for smart glasses wins £1M prize for helping people with dementia
Smart glasses using AI chatbot to assist dementia patients. Application of LLMs but limited technical depth.
3/29/2026
An open-source tool for designing homes using AI
Browser-based home design tool using Claude Code and Three.js for AI-assisted interior design.
3/29/2026
Cc-budget – Know your Claude Code budget before you hit the wall
Cc-budget is a tool adding budget tracking intelligence to Claude Code editor status line with cost pacing and threshold warnings.
3/29/2026
Product manager skill for Claude
Open-source Claude Skill providing product management frameworks, templates and structured thinking playbook for early-stage teams lacking dedicated PMs.
3/29/2026
Claude Code Chronicles
User narrative about using Claude Code to fix system issues via conversational AI assistance for kernel panic and hardware problems.
3/29/2026
LLMs Do Not Grade Essays Like Humans
Research comparing LLM essay grading to human grading. arXiv paper on machine learning evaluation.
3/29/2026
Three LLM Agents for My Knowledge Garden
Using three LLM agents to maintain and connect a personal knowledge garden from notes and highlights.
3/29/2026
Proof – The agent-first document editor
Document editor designed for human-agent collaboration with mobile-friendly comment workflows.
3/29/2026
Show HN: Pglens – 27 read-only PostgreSQL tools for AI agents via MCP
PostgreSQL MCP server with 27 tools for schema inspection, data exploration, and health monitoring for AI agents.
3/29/2026
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands
CLI proxy reducing LLM token consumption 60-90% by filtering and compressing command outputs. Single Rust binary.
3/29/2026
MarCognity-AI – Epistemic failure rates in LLMs across 8 domains
Open-source framework analyzing LLM epistemic failures across domains with claim verification and semantic coherence checks.
3/29/2026
The open context engine for AI agents
Wren Engine: open-source semantic context layer for AI agents to understand business data, metrics, and relationships.
3/29/2026
Show HN: Tinyvision:-Building Ultra-Lightweight Models for Image Tasks
Project exploring ultra-lightweight image classification models, achieving 25KB model for cat vs dog tasks by stripping models to bare minimum.
3/29/2026
Catching the LiteLLM and Telnyx supply chain zero-days via semantic analysis
Technical analysis of LiteLLM and Telnyx supply chain attacks using semantic analysis to bypass content filters.
3/29/2026
Generative AI Can Harm Learning (2024)
Agent Observatory: monitoring system for AI coding agents built entirely by autonomous agents. 115 commits, 26K TypeScript LOC, 1,103 tests, zero human code.
3/29/2026
The world of AI contributions in Open Source
Overview of AI contributions in open-source projects. Title only, no substantive content.
3/29/2026
Moving Towards Determinism with LLMs
Research on improving determinism in LLM behavior and outputs. Title only, no content provided.
3/29/2026
Number of AI chatbots ignoring human instructions increasing, study says
Study documenting AI chatbots increasingly ignoring user instructions. Title only, limited detail.
3/29/2026
Show HN: ACP – Like MCP, but for controlling existing application UIs
ACP: protocol for AI agents to control existing application UIs, similar to MCP but for UI automation.
3/29/2026
Which Claude AI Do I Need? (The Fractional CTO)
Comparison guide explaining different Claude AI product tiers and entry points. Developer tool selection guidance with practical context.
3/29/2026
I gave an AI SSH access to my production infrastructure – 3 months later
3-month case study of Claude AI as autonomous SSH agent managing production financial infrastructure. Real-world AI agent deployment with technical insights.
3/29/2026
Noteriv – Free Open-Source Notes App with AI and Markdown
Open-source markdown notes application with AI features. Developer tool combining LLMs with productivity software.
3/29/2026
Can LLMs bring the Berkshire Hathaway web site into the 21st century?
Technical exploration of using LLMs for HTML/CSS web design vs. programming tasks. Testing LLM capabilities on design complexity.
3/29/2026
Researchers examine how AI chatbots are shaping government operations
Research on AI chatbot integration in government operations. Title only, limited detail.
3/29/2026
Claude Skill Collection
Claude Skill Collection: modular production-ready agents and tools for coding, security, and specialized domains using Claude AI.
3/29/2026
AltClaw – A secure scripting layer for AI agents with a module marketplace
AltClaw is an open-source AI agent orchestrator with sandboxed JavaScript execution, module marketplace, and system integration APIs (file ops, commands, databases, git) deployable as single Go binary.
3/29/2026
Show HN: I built a Git extension to capture AI-code context and tied to commits
GitWhy is a Git extension that captures reasoning and context behind AI-generated code and ties it to commits for PR reviews and code verification.
3/29/2026
Show HN: Agent Orchestrator, a local-first Harness Engineering control plane
Agent Orchestrator is a local-first control plane for AI-assisted software delivery that addresses verification bottlenecks by moving validation earlier in the development workflow.
3/29/2026
Show HN: Ticking Away, a Dark Side of the Moon Watchface Written in Zig
Watchface application built in Zig targeting multiple platforms (browser, Raspberry Pi, Pebble). Used Claude as development assistant but not AI-focused.
3/29/2026
Show HN: PromptLedger – local-first prompt versioning in SQLite
PromptLedger: local-first version control for prompts using SQLite. CLI, Python API, and Streamlit viewer with no backend services.
3/29/2026
I built a better, human like memory, for Agents
elfmem: adaptive memory system for LLM agents with decay and relevance tracking. Single-file, no external infrastructure required.
3/29/2026
Show HN: Think Fu – Metacognition as a service
ThinkFu is a service addressing LLM creative limitations by reducing RLHF constraints to improve creative reasoning capabilities beyond predictable outputs.
3/29/2026
Local-first AI knowledge layer. Extract architecture, query from any AI tools
TaskWing extracts code architecture into local SQLite knowledge base for AI tools, enabling offline sessions without cloud dependency or account requirements.
3/29/2026
Are LLMs a Dead End? [video]
Multi-agent orchestration platform managing concurrent LLM agents in containers with isolated identities, credentials, and workspaces.
3/29/2026
DaVinci-MagiHuman: Open-source AI model for realistic video generation
Open-source DaVinci-MagiHuman model generates realistic human videos with improved lip-sync and audio alignment. Video generation research.
3/29/2026
Vibe physics: The AI grad student
Harvard physicist supervises Claude through theoretical physics research calculation without touching code. AI agents for scientific research.
3/29/2026
Tried a New AI Image Tool for Real-World Design Work (Nano Banana Pro)
Review of Nano Banana Pro image generation tool for design work. Commercial tool application.
3/29/2026
ARC-AGI solver via Plücker geometry – 316 tasks solved with zero learning
OpenClaw skill enabling GPU machines to run parallel autonomous ML research agents with nightly experiments and knowledge synthesis.
3/29/2026
LLMs Can Write Production Quality Code
Developer at Airbnb writes 99% production code using LLMs across 1000+ microservices. Practical LLM application at scale.
3/29/2026
What if AI doesn't need more RAM but better math?
Google's TurboQuant compression algorithm reduces LLM memory usage by 6x without quality loss. ML optimization research.
3/29/2026
Show HN: Liter-LLM, Universal LLM client in Rust with bindings for 11 languages
Liter-LLM: universal LLM client in Rust with 11 language bindings and 142 provider support. Open-source developer tool.
3/29/2026
Show HN: Built tool to turn n8n workflows into OpenClaw-compatible agent skills
CLI tool converting n8n workflows into OpenClaw-compatible agent skills using LLM for transpilation.
3/29/2026
Google's TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x
TurboQuant compression algorithm reduces LLM memory 6x while maintaining quality and improving speed. ML optimization.
3/29/2026
Show HN: Shoofly – pre-execution security for Claude Code Cowork and OpenClaw
Shoofly: pre-execution security layer for Claude Code and OpenAI agents, intercepts tool calls to block injection and malware. AI agent security.
3/29/2026
Mr. Chatterbox is an LLM trained exclusively on Victorian-era British texts
LLM trained exclusively on Victorian-era British texts. Specialized language model with narrow training data.
3/29/2026
AI Hot Takes from a Platform Engineer / SRE
Platform engineer critiques AI hype, noting lack of real-world production agentic systems that perform reliably.