3/30/2026
Hawkeye – a flight recorder for AI agents
Hawkeye is debugging and observability tool for coding agents. Provides session recording, error tracking, and audit logs for agent workflows.
3/30/2026
MXFP8 GEMM: Up to 99% of cuBLAS Performance Using CUDA and PTX
Technical deep-dive on optimizing MXFP8 GEMM kernels using CUDA and PTX, achieving 99% of cuBLAS performance on modern GPUs.
3/30/2026
AI-powered migrations from Postgres to ClickHouse
Guide on using AI agents with MooseStack harness to automate Postgres to ClickHouse database migrations. Includes implementation steps.
3/30/2026
Agentic Hive – Manage Claude Code and Codex Tmux Sessions from a Browser
Agentic Hive is a lightweight web app for managing tmux sessions across remote hosts, with support for Claude Code and shell access via browser.
3/30/2026
Show HN: Real-time visualization of Claude Code agent orchestration
Agent Flow is a real-time visualization tool for debugging Claude Code agent orchestration, showing agent decision trees and coordination during execution.
3/30/2026
We audited our own AI-written codebase. 13 issues, 5 categories
Koalr audited own Claude-written codebase, found 13 issues across 5 categories. Reports specific quality problems in AI-assisted development.
3/30/2026
Stop wasting tokens–Entroly teaches AI which context matters.Save tokens. Save $
Entroly is context engineering tool for AI coding agents. Reduces token usage by 78% by identifying relevant codebase context. Works with Cursor, Claude, Copilot.
3/30/2026
Show HN: Sandbox agents without losing your dev environment
Drop is Linux sandboxing tool for isolating programs and AI agents while preserving dev environment. Inspired by virtualenv workflow.
3/30/2026
MLB pitches AI-powered commentary in its play-by-play app
MLB uses Google Cloud Gemini AI for automated sports commentary in Gameday app. Consumer application with limited technical depth.
3/30/2026
Operators, Not Agents: Engineering Structure Around LLMs
Technical essay arguing for constrained 'operators' over autonomous agents for LLM-based coding. Discusses common failure modes and control structures.
3/30/2026
Is the Future of AI Local?
Analysis of scenario where open source models running locally on workstations dominate AI deployment, matching frontier model performance within 6 months.
3/30/2026
How I Run SEO for a Startup Without Engineers or SEO SaaS Tools
Non-technical startup leader uses camelAI agent for SEO tasks including keyword research, blog publishing, and analytics without engineers or SaaS tools.
3/30/2026
Batch_forge – A bare-metal Jax/Equinox runner in Rust for Mac
batch_forge is a Rust-based inference engine for JAX/Equinox models supporting Transformers, Diffusion, and SSMs on edge devices with Metal/Vulkan backends.
3/30/2026
AI Hot Takes from a Platform Engineer / SRE
Opinion piece by platform engineer skeptical of AI agents in production systems, noting most real-world implementations underperform or fail.
3/30/2026
Bluesky leans into AI with Attie, an app for building custom feeds
Bluesky launches Attie, an AI assistant for building custom social media feeds using natural language prompts on its AT Protocol framework.
3/29/2026
AI agents can safely browse
arXiv research on how LLMs can transmit behavioral traits through hidden signals in training data.
3/29/2026
Bluesky's next product is an AI assistant that helps build social media feeds
SafeBrowse Python client for AI agents to safely browse external websites with local policy enforcement daemon.
3/29/2026
Show HN: Manifold – generate CLI and MCP surfaces from one .NET operation
.NET framework that generates CLI and MCP surfaces from single operation definition, solving drift problems in multi-surface capability exposure.
3/29/2026
Subliminal learning: LLM transmit behavioral traits via hidden signals in data
Bitterbot is a local-first persistent AI agent with memory, web browsing, code execution, and P2P skill marketplace.
3/29/2026
Bitterbot – A local-first AI agent with a P2P skill marketplace
HN post seeking release guidance for transformer-alternative architectures including linear RNNs for faster CPU performance.
3/29/2026
The Playbook That Elon Musk Relies on to Make His Wild Ideas Work
Analysis of how AI is automating non-engineering work, shifting software development focus from planning to code generation.
3/29/2026
OxCaml Labs
AI-powered semantic search system for matching automotive electrical connectors using Qdrant ACORN algorithm.
3/29/2026
There is No Spoon. A software engineers primer for demystified ML
ML primer for software engineers explaining machine learning systems design from first principles without mystification.
3/29/2026
Show HN: SwarmDock – P2P marketplace where AI agents bid on tasks and earn USDC
P2P marketplace platform where AI agents compete for tasks and earn cryptocurrency rewards. Title only provided.
3/29/2026
Coding Agents Could Make Free Software Matter Again
Analysis of how coding agents could revitalize open-source software development. Title only provided.
3/29/2026
Kjell – Safely auto-approve AI agent shell commands through bash parsing
Bash parsing tool for safely auto-approving shell commands executed by AI agents. Title only provided.
3/29/2026
Mnemo – open-source memory and observability for AI agents (2 lines of code)
Open-source memory and observability tool for AI agents with minimal integration overhead. Title only provided.
3/29/2026
Claude Code runs Git reset –hard origin/main against project repo every 10 mins
Bug report: Claude Code automatically runs git reset --hard origin/main every 10 minutes, silently destroying uncommitted changes.
3/29/2026
A Year of Open Source Vulnerability Trends
Analysis of 2025 open-source vulnerability trends: reviewed advisories at 4-year low, malware advisories surged, CNA publishing grew.
3/29/2026
I'm an AI agent trying to run a real business. I've made $0. Here's my brain
Claude-based AI agent attempting to run Acrid Automation business with open-sourced operating system including boot file, skill framework, and memory persistence.
3/29/2026
What Is LLM Advertising? The New Ad Layer for AI-Powered Search
Analysis of advertising strategies within AI search tools and LLM conversations as alternative to traditional search ads.
3/29/2026
QA Panda – Open-source AI QA engineer that tests web apps in a real browser
Open-source AI QA agent that tests web applications in real browsers, finds bugs, generates reports, and can delegate fixes to developer agents.
3/29/2026
Autogrind: Let your agent grind on your projects 24x7 fully autonomously
AutoGrind: AI agent skill enabling autonomous continuous work cycles on coding, ML, research, and design tasks without manual intervention.
3/29/2026
Show HN: Learn from AI Experts
Replit app using LLMs to summarize books for grounding AI in real expertise and discovery.
3/29/2026
Show HN: A war-strategy game played by AI agents
Open-source multiplayer game where teams of AI agents communicate, propose moves, and vote on strategy through emergent gameplay.
3/29/2026
Tell HN: Bug in Claude Code CLI is instantly draining usage plan quotas
Bug report: Claude Code CLI draining usage quotas 2-3x faster than normal since March 23, 2026, affecting multiple users.
3/29/2026
Ootils – An open source supply chain engine designed for AI agents (not humans)
Open-source supply chain decision engine built for AI agents with graph-based, deterministic, explainable API-first design.
3/29/2026
Show HN: Vocab extractor for language learners using Stanza and frequency ranks
Telegram bot using Stanza NLP pipeline and frequency ranks for vocabulary selection in language learning, outperforming GPT-4o-mini at lower levels.
3/29/2026
AI on deck: assessing impact of MLB's new ball-strike system
Cornell study on MLB's AI-augmented camera system for ball-strike calls and stakeholder integration.
3/29/2026
Magellan: AI agents for autonomous cross-disciplinary scientific discovery
Multi-agent system for autonomous cross-disciplinary scientific discovery, finding testable hypotheses without domain expertise.
3/29/2026
Visual reasoning benchmark based on Analog Clocks
ClockBench visual reasoning benchmark evaluating frontier models' ability to read analog clocks.
3/29/2026
Circumstantial Complexity, LLMs and Large Scale Architecture
Blog post on software architecture complexities introduced by machine-assisted programming and LLMs.
3/29/2026
AI drives companies to reorganize around loops, not functions
Analysis of multi-agent system design: avoiding specialized roles, organizing agents around loops instead of functions.
3/29/2026
Show HN: Beval – Simple evaluations for your AI product
Web app for quick LLM-based evaluation of AI product conversations and traces without complex setup.
3/29/2026
Open-source ZK proofs for ML inference – verify AI decisions cryptographically
Open-source zero-knowledge proofs for verifying ML inference decisions cryptographically.
3/29/2026
Security awareness in LLM agents: the NDAI zone case
arXiv paper on security awareness in LLM agents within the NDAI zone case study.
3/29/2026
Gestalt – AI PC builder that compares Amazon vs. eBay prices in real time
Flask web app for AI-assisted PC builds using CrewAI pipeline with compatibility validation, live pricing integration, and Gemini-powered explanations.
3/29/2026
Show HN: I made a "programming language" looking for feedback
Glupe is a semantic metaprogramming language generating code across multiple target languages based on human intent rather than language-specific syntax.
3/29/2026
Show HN: DeepRepo – AI architecture diagrams from GitHub repos
DeepRepo: generates interactive architecture diagrams from GitHub repos using semantic code search and AI chat. Supports multiple languages.
3/29/2026
Ask HN: Settings.json is an insane design choice for OpenClaw?
Discussion of configuration management issues in AI agent frameworks, particularly settings.json corruption and safety controls.