3/14/2026
Direnv Is All You Need to Parallelize Agentic Programming with Git Worktrees
Using Git worktrees and direnv to parallelize AI coding agents like Claude Code. Developer workflow optimization.
3/14/2026
Show HN: Kube-pilot – AI engineer that lives in your Kubernetes cluster
Kube-pilot: autonomous AI agent running in Kubernetes that writes code, builds containers, deploys, and closes tickets.
3/14/2026
Can LLMs Do Matching Decompilation? I Tested 60 Functions to Find Out
Testing LLMs for matching decompilation across 60 functions using AI-powered VS Code decompiler tool. Evaluation.
3/14/2026
Optimizing Content for Agents
Opinion piece arguing for optimizing web content specifically for AI agents rather than just humans and APIs.
3/14/2026
Show HN: DAAO – Deploy AI agents to your servers via Zero-Trust tunnels
DAAO deploys AI agents to servers via zero-trust outbound-only mTLS tunnels, enabling remote coding sessions without VPN or SSH exposure.
3/14/2026
How Does AI Distribute the Pie? Large Language Models and the Ultimatum Game
Research studying LLM behavior in Ultimatum Game with varying stake sizes and opponent types, showing heterogeneous behavior across models.
3/14/2026
Agentic AI: Workflows vs. Agents
Post comparing workflows versus agents in agentic AI systems. Minimal content provided.
3/14/2026
Show HN: What agentic collaborative pentesting looks like
Turbopentest enables collaborative pentesting between AI agents and human operators via web, VSCode, Burp Suite, GitHub Actions, and MCP servers.
3/14/2026
AutoContext: closed-loop system for improving agent behavior over repeated runs
AutoContext is a closed-loop system that improves AI agent behavior by executing tasks, evaluating outcomes, updating knowledge, and distilling successful behaviors into cheaper local models.
3/14/2026
Show HN: A Claude Skill that teaches Rails conventions for LLM calls
Claude Skill teaching Rails conventions for LLM calls, providing patterns for retry logic, cost tracking, and prompt management.
3/14/2026
Mega-OS – 38-agent operating system that runs inside Claude Code
OS with 38 specialized AI agents organized into 5 categories, runs inside Claude Code with interactive setup and structured command center.
3/14/2026
Show HN: Monetize your APIs by injecting agent targeted instructions
ad-injector is a Python library that embeds agent-targeted instructions into JSON API responses for affiliate links and product recommendations.
3/13/2026
Spaced Repetition Algorithm: A Three‐Day Journey from Novice to Expert
Research on spaced repetition scheduling algorithms optimizing memory retention. Academic papers on algorithm dynamics for learning applications.
3/13/2026
Show HN: diz – SSH key exchange in one command each side
CLI tool for simplified SSH key exchange between machines without manual copying. Developer tool with limited AI/ML relevance.
3/13/2026
Execwall – firewall to stop ModelScope CVE-2026-2256 (AI agent command injectn)
Execwall: execution firewall for AI agents using seccomp-BPF filtering to prevent prompt-injection command execution exploits.
3/13/2026
Ask HN: Has anyone built an AI agent that spends real money?
Developer asks about building autonomous shopping AI agent; discusses MCP payment integrations and infrastructure challenges.
3/13/2026
Stop repeating yourself to Claude Code
Tool that learns Claude Code user preferences and injects them automatically. Developer productivity utility.
3/13/2026
Email as the Context Substrate for Ambient AI Agents
Revo AI building ambient AI agents using email as context substrate, leveraging existing protocol infrastructure for cold-start grounding.
3/13/2026
Probabilistic Machine Learning: An Introduction
Comprehensive textbook on probabilistic machine learning with reproducible code, figures, and exercises. MIT Press publication with CC-BY-NC-ND license.
3/13/2026
Generate tests from GitHub pull requests
Using AI to generate end-to-end tests from GitHub PRs to address gap left by Copilot-style tools lacking test coverage.
3/13/2026
Show HN: EdgeWhisper – On-device voice-to-text for macOS (Voxtral 4B via MLX)
macOS voice-to-text app running Voxtral 4B locally via MLX framework. Zero data leaves device. Swift/SwiftUI implementation.
3/13/2026
TinyForge: Letting a 0.8B coding model learn from failure feedback on a MacBook
TinyForge: 0.8B coding model learns from test failures via evolutionary search and LoRA training on MacBook, improving HumanEval performance.
3/13/2026
Show HN: Open-Source Perplexity Comet and ChatGPT Atlas
Open-source browser agent for Chromium sidebar automating clicks, typing, form filling. Alternative to Perplexity Comet and ChatGPT Atlas.
3/13/2026
Redis for AI Agent Collaboration
Redis-based coordination framework for multi-agent AI systems with reduced setup overhead using cursor agent experimentation.
3/13/2026
Teaching Qwen3-4B to Trade: From Hold-Collapse to +9.4% Returns
Fine-tuned Qwen3-4B LLM for stock trading using 5-stage supervised learning pipeline and reinforcement learning. Achieved +9.4% returns.
3/13/2026
An Agent Skill that lets coding agents render rich interactive visuals
Agent skill enabling coding agents to render interactive SVG diagrams, HTML widgets, and live charts inline. Developer tool for AI agents.
3/13/2026
Emergent abilities in text-to-image model
Original research on emergent abilities in text-to-image models, discovering image-to-image capabilities. Reproducible experiments in preparation.
3/13/2026
Open-source LLM-as-judge eval suite with root cause analysis and failure mining
Open-source evaluation suite for LLM-as-judge testing AI agents. YAML test definitions, root cause analysis, failure mining into training data.
3/13/2026
Show HN: Plotting mathematical functions in Ruby inside Jupyter with Ruby-libgd
Ruby library for plotting mathematical functions in Jupyter notebooks. Developer tool with limited AI relevance.
3/13/2026
Re-thinking candidate take-homes in the AI Era: transcripts over code
Identity.txt: Portable text format for storing AI custom instructions, preferences, and voice across multiple AI tools.
3/13/2026
Show HN: AgentMeet – Google Meet, but for AI Agents
Rootly CTO discusses rethinking engineering evaluations using conversation transcripts instead of code artifacts in AI era.
3/13/2026
Show HN: Agents shouldn't operate software–they should coordinate commitments
Covenant Layer: Open protocol for AI agents to coordinate commitments via outcome-based contracts instead of step-by-step tool orchestration.
3/13/2026
ChronologyAI – Open-Source AI
Open-source ChronologyAI engine reconstructs event timelines and detects contradictions in documents for legal, compliance, and fraud investigations.
3/13/2026
Experimenting with healthcare AI agents using OpenClaw
OpenClaw agent templates for healthcare with plug-and-play deployment, customer support automation, and PR review capabilities.
3/13/2026
AI, Human Cognition and Knowledge Collapse – Daren Acemoglu
OpenClaw agent templates for healthcare including support ticket handling, bug triage, and PR review with customizable guardrails.
3/13/2026
AutoHarness: Improving LLM agents by automatically synthesizing a code harness
AutoHarness research on improving LLM agents by automatically synthesizing code harnesses. Machine learning research.
3/13/2026
LightSwarm – A script making ClaudeCodeMax into a free light easy swarm
LightSwarm is a bash script that creates a 3-agent swarm using Claude's API, with roles for architecture, building, and cleanup across multiple projects.
3/13/2026
Show HN: A single CLI to manage llama.cpp/vLLM/Ollama models
Harbor CLI tool for managing multiple LLM backends (llama.cpp, vLLM, Ollama) with unified interface. Open source developer tool.
3/13/2026
Show HN: Loop your agents like a dandy little b*tch
Simple command-line utility for looping and backgrounding commands with configurable delays and alias support.
3/13/2026
You don't need to be "primary source" in a historical record to be Primary in AI
Brief conceptual piece discussing topology and authority in AI inference versus historical primary source concepts.
3/13/2026
Smellcheck – detect AI smells in texts
Offline detection tool for AI-generated text patterns without ML, identifying suspicious fingerprints like unusual punctuation and buzzwords.
3/13/2026
Show HN: Shadow – Editor-agnostic live collaboration (open source)
Open source editor-agnostic live collaborative editing tool enabling simultaneous editing across different editors and locations.
3/13/2026
Show HN: Argo – Turn Playwright scripts into polished demos with AI voiceover
Open source CLI tool converting Playwright test scripts into product demo videos with AI-generated voiceover using local Kokoro TTS.
3/13/2026
LLM inference infrastructure for a systems audience
Systems-level discussion of LLM inference basics and serving runtimes ecosystem from infrastructure perspective. Originally internal, now published for systems developers.
3/13/2026
GitHub infuriates students by removing some models from free Copilot plan
GitHub removes expensive premium LLM models from free Copilot Student plan starting March 12.
3/13/2026
Hawkeye – open-source flight recorder
Hawkeye is an open-source observability layer for AI agents with session recording, drift detection, and guardrails.
3/13/2026
Kalverion_bot a.k.a. AI-bot v1.1.0 release. Overdraft protection
Kalverion_bot is an open-source AI Telegram bot for personal finance using NLP, double-entry accounting, and forecasting.
3/13/2026
Continuum – Unit tests for LLM workflows
Continuum is a testing framework for LLM workflows that records and replays runs to detect output drift in production.
3/13/2026
Papers: A minimal AI/ML research reader
Open source minimal ML research paper reader that fetches arXiv papers daily and summarizes them using local LLMs.
3/13/2026
Show HN: Monet – Claude Code Multisession Management
Monet is a grid-based management interface for organizing and monitoring multiple Claude Code agents on desktop and mobile.