Show HN: CRSS v0.1 – a primitive for sharing agent memory and behavior
Primitive for agent memory/behavior sharing using deterministic event sourcing, enabling agents to share learned preferences and characteristics.
Primitive for agent memory/behavior sharing using deterministic event sourcing, enabling agents to share learned preferences and characteristics.
Collection of 562 generative media skills for AI agents, integrating 431 models through unified API with Claude Code plugin support.
Technical guide explaining agent communication protocols (MCP, A2A, UCP, AP2, A2UI, AG-UI) and their purposes for tool/API integration.
Agent Control: runtime guardrails layer for AI agents, blocks prompt injections and PII leakage via configurable rules.
Analysis of code verification challenges as AI-generated code adoption accelerates, with examples from major tech companies and defense sector.
Service for deploying ML policies and models to robotics with 1-click deployment; minimal technical detail provided.
Open-source persistent memory system for AI agents with local GPU retrieval, compatible with Claude Code and OpenClaw via SQLite vault.
OpenAI plans workforce expansion to 8,000 employees by 2026 across engineering, research, product, and sales.
Security tool providing audit trails, policy enforcement, and visibility for AI agent shell command execution across teams.
Multi-agent system achieved top performance on OpenAI's Parameter Golf leaderboard, demonstrating swarm-based optimization approach.
arXiv framework announcement; appears to be placeholder/boilerplate content.
Experimental analysis of goal-free AI agents showing emergent behavior patterns; Claude consistently replicated Conway's Game of Life.
Study demonstrating that heavy LLM use produces blander writing with less divergent meaning compared to human-written responses.
Paywalled Financial Times article about AI labs training humanoid robots in China.
Research showing language models exhibit detectable internal signals before hallucinating, measuring gate activations across open-source LLMs to predict model uncertainty.
Safety study finding top chatbots fail to prevent or actively enable violent attack planning by teen users.
Terminal-style AI coding agent running on Cloudflare Workers with SQLite-backed sessions and dynamic worker sandboxing for code execution.
Native macOS app with built-in MCP servers enabling AI agents like Claude Code to control iOS development lifecycle and App Store submission.
CLI tool using AI to auto-generate and maintain codebase documentation and changelogs tied to git commits for AI-assisted development teams.
Metadata about marked-dead HN post regarding Trivy security incident.
Free open-source local AWS emulator alternative to LocalStack with 20+ services, no authentication requirements, and permanent free tier.
WordPress SEO plugin with AI-powered writing assistance for optimizing rankings, titles, and meta descriptions.
OpenClaw, an open-source AI coding project, rapidly gained popularity and was featured at Nvidia's GTC conference as a significant development in AI tooling.
Article about lessons learned from building 33 AI agents related to alignment considerations.
Open-source GPLv3 secure remote access solution preventing data exfiltration during remote server access with audit mechanisms.
MCP server enabling code agents to determine full behavioral change surface with deterministic retrieval for safe local LLM-based code modification.
Open-source entity resolution toolkit using LLM scoring, Polars, RapidFuzz, and FAISS for deduplication and record matching without Spark.
Discussion of attracting AI agents to contribute to open source projects through Claude and other LLM-based PR automation.
Git commit reverting birthDate field addition to user records due to privacy and legal considerations regarding age attestation.
Magic: The Gathering rules engine and compiler built in Rust with parser-driven card behavior logic and multiplayer game runtime.
Security vulnerability (CVE-2026-33068) in Claude Code CLI allowing workspace trust bypass via malicious settings.json files.
Open-source agentic curriculum engine using AI agents with research capabilities to generate pedagogically structured course content applying learning science principles.
Kagi Translate tool using LLMs to translate text into creative 'languages' like LinkedIn Speak and Gen Z slang.
Fireworks partnership with Microsoft Azure for distributed training via cross-region rollouts and periodic snapshots instead of mega clusters.
Curated list of open-source projects for OpenClaw ecosystem.
Apifold converts OpenAPI specifications into live MCP (Model Context Protocol) servers, enabling API integration with AI agents.
Health research article on absence of evidence for cannabis effectiveness treating anxiety, depression, and PTSD.
macOS application for running vLLM models locally.
Atomic: self-hosted personal knowledge base with semantic connections for information organization and retrieval.
Video about whether AI can perform intelligent disobedience.
NVIDIA open-sources OpenShell agent runtime with security guardrails for autonomous enterprise AI agents.
Platform providing public pages for production AI agents with live work history and shareable links.
Open-source agentic data transformation platform with visual IDE and AI assistant for building Python pipelines with natural language.
Open-source browser designed specifically for AI agents with agent-first UX instead of human automation.
Headless macOS VM client supporting hardware video encoding (H.264, HEVC, ProRes) via paravirtualized VideoToolbox.
Analysis of how bundling model quality with app business models creates poor user experiences; discusses API keys and LLM environments.
Circuit breaker mechanism that prevents AI agents from executing incorrect actions before execution occurs.
Philosophical essay on Plato's Phaedrus discussing writing and memory, updated March 2026.
AI product photography tool for e-commerce stores with minimal details provided.
Opinion piece on DoorDash's Tasks gig work app using AI for task assignment and monitoring.