4/13/2026
Show HN: OQP – A verification protocol for AI agents
OQP: MCP-compatible verification protocol for autonomous AI agents. Defines standards for verifying agent-generated code meets business requirements via four core endpoints.
4/13/2026
Show HN: Mercury – No-code orchestration for human and agent teams
Mercury: orchestration platform for managing multiple AI agents across tools. No-code interface for coordinating agent workflows in enterprise settings.
4/13/2026
Show HN: OQP – A verification protocol for AI agents
OQP: MCP-compatible verification protocol for autonomous AI agents. Defines standards for verifying agent-generated code meets business requirements via four core endpoints.
4/13/2026
The US-China AI Gap Widens in 2026
Analysis of US-China AI capabilities gap in 2026. Premium content discussing relative progress and competition in AI development.
4/13/2026
Larql: LLMs Are Databases. Query neural network weights like a graph database
LARQL: query language for decomposing transformer weights into queryable vector indices. Decompile models into vindex format for browsing and editing knowledge without GPU.
4/13/2026
The Lucy Syndrome: Why LLMs Forget Corrections
Study examining why LLMs fail to retain corrections across multiple interactions. 19,600-word analysis with lab data from civil engineering firm using Claude Code.
4/13/2026
N-Day-Bench – Can LLMs find real vulnerabilities in real codebases?
N-Day-Bench: benchmark measuring LLM capability to find real vulnerabilities in codebases beyond knowledge cutoff. Monthly-updated adaptive test suite for security evaluation.
4/13/2026
Your intuition of LLM token usage might be wrong
Analysis of LLM token usage patterns through agent harness implementation. Real-world example of token consumption in multi-service agent tasks.
4/13/2026
Stanford report highlights growing disconnect between AI insiders and everyone
Stanford annual AI report documents diverging views between AI experts and public, rising anxiety about jobs and societal impact.
4/13/2026
Show HN: Automate onboard developer to your codebase 20x faster
SaaS product using GitHub integration to onboard developers faster through automated codebase documentation.
4/13/2026
Claude is getting worse, according to Claude
Analysis of Claude API service quality decline, outages, and cost increases reported by users and internal testing.
4/13/2026
Aibom Scanner- find AI SDKs, BIS Entity List flags, compliance gaps in your code
Aibom Scanner open-source tool detects AI SDK usage in codebases and maps compliance gaps to NIST, ISO 42001, EU AI Act frameworks.
4/13/2026
Poke makes using AI agents as easy as sending a text
Poke startup launches AI agent accessible via iMessage, SMS, Telegram for personal assistance and smart home control.
4/13/2026
Show HN: Continual Learning with .md
Proposal for LLM continual learning using Markdown files and semantic filesystem for cheap long-term memory without code.
4/13/2026
Twelve Graphs That Explain the State of AI in 2026
Analysis with graphs of AI industry trends: rising investment, accelerating model capabilities, mixed job/perception impact heading into 2026.
4/13/2026
ContextNest: Persistent Memory Protocol for LLMs Using YAML Graph Navigation
ContextNest is open standard for structured knowledge management in AI agents using versioned markdown, deterministic queries, and audit trails for enterprise context governance.
4/13/2026
Why Engineering Teams Need an Agentic Layer, Not Just AI Chat
Analysis of shift from AI chat to agentic layers in software engineering. Discusses workflow orchestration and system integration beyond prompt-based tools.
4/13/2026
Show HN: The Harness for Creative Agents
Flickspeed provides shared workspace harness for multimodal creative agents handling image, video, audio, and research tasks. Orchestration platform.
4/13/2026
Show HN: On-Device vs. Cloud LLMs for Agentic Tool Calling in a Real iOS App
Comparison of on-device vs cloud LLMs for agentic tool use in iOS travel concierge app. Tests Apple Foundation Models 3B vs GPT-OSS 20B for multi-step agent tasks.
4/13/2026
Show HN: AImeter shows you how much money your agents are burning
AImeter tracks costs and value metrics for AI agents with zero dependencies, local-first, no cloud required. Developer tool for agent economics.
4/13/2026
Coyns – MCP-native currency for AI agent-to-agent transactions
Coyns enables AI agent-to-agent transactions using MCP-native currency. Economic layer for autonomous agent interactions.
4/13/2026
Sentō – Open-source AI agents on your Claude subscription, one command setup
Sentō provides open-source AI agents running on Claude API subscription with one-command setup. Developer tool for agent deployment.
4/13/2026
Show HN: I benchmarked Gemma 4 E2B – the 2B model beat the 12B on multi-turn
Benchmark of Google Gemma 4 E2B (2B parameter model) vs larger Gemma variants on 10 enterprise task suites. Local inference on Apple Silicon.
4/13/2026
(AMD) Build AI Agents That Run Locally
GAIA is an open-source framework for building local AI agents in Python and C++ on AMD hardware without cloud dependency.
4/13/2026
Show HN: Claude Code skills for network engineering and homelabs
Claude Code skills for network engineering enable LLM assistance on enterprise networking concepts, protocol explanations, and homelab troubleshooting.
4/13/2026
Show HN: Lint-AI by RooAGI, a Rust CLI for AI Doc Retrieval
Lint-AI is a Rust CLI for indexing and retrieving evidence from AI-generated documentation corpora, extracting context from large task traces.
4/13/2026
AI Agents Are Control Systems
Conceptual essay framing AI agents as control systems similar to autonomous vehicle architecture, emphasizing execution, verification, and telemetry.
4/13/2026
Sometimes I Don't Use AI at All
Personal narrative on choosing to work without AI assistance due to client restrictions and preference for traditional coding flow.
4/13/2026
AI ran into the cold hard reality of the legal profession
Analysis of AI adoption challenges in legal profession, examining claims versus practical implementation realities.
4/13/2026
AI Frontier Model Tracker with API
Tracker comparing frontier AI models with benchmarks, pricing, and API capabilities across proprietary and open-weight options.
4/13/2026
Building a Robust Documentation Agent with DigitalOcean Gradient AI Platform
DigitalOcean platform for building and deploying AI agents and applications.
4/13/2026
Ask HN: Do Agent skills make a difference?
Discussion on practical effectiveness of AI agent skills versus manual team processes.
4/13/2026
Evaluation of Claude Mythos Preview's cyber capabilities
Evaluation of Claude Mythos Preview model's cybersecurity capabilities and performance.
4/13/2026
AI Agents for Economics Research
Applies AI agents to economics research tasks.
4/13/2026
Training AI models doesn't emit that much
Analysis challenging claims about AI model training environmental emissions.
4/13/2026
Evaluating Netflix Show Synopses with LLM-as-a-Judge
Netflix uses LLM-as-judge approach to evaluate and improve show synopsis quality for personalization.
4/13/2026
We built our own PDF converter benchmark
Custom PDF conversion benchmark with evaluation methodology.
4/13/2026
AI chatbots misdiagnose in over 80% of early medical cases, study finds
Study showing AI chatbots misdiagnose medical conditions in over 80% of early-stage cases.
4/13/2026
Show HN: Ix. Sick of rebuilding context every session. We mapped it instead
Open-source tool that maps codebase architecture for AI agents, eliminating context loss between sessions.
4/13/2026
Meta creating AI version of Mark Zuckerberg so staff can talk to the boss
Meta develops AI chatbot trained on Mark Zuckerberg's communications for employee interactions.
4/13/2026
Show HN: Hitoku Draft – context aware local macOS assistant
Open-source voice-first local AI assistant for macOS with context awareness, using Gemma and Qwen models.
4/13/2026
Running (and Coding with) Local AI on a Mac
Guide on running and coding with local AI models on macOS. Practical developer resource.
4/13/2026
Linux 7.0 debuts as Linus Torvalds ponders AI's bug-finding powers
Linux 7.0 kernel release announcement with mention of AI applications in bug-finding. Limited AI focus.
4/13/2026
Want to understand the current state of AI? Check out these charts
Stanford's 2026 AI Index report analyzing AI progress, development rates, and industry trends with data.
4/13/2026
Mist: Open-source Markdown editor with AI-native comments and suggested edits
Open-source Markdown editor featuring AI-native comments and suggested edits functionality.
4/13/2026
Tell HN: Claude-code prompt-cache fix
Bug fix for Claude Code prompt caching using environment variable workaround to avoid tool-block blocking.
4/13/2026
Gas Town Notes and Spaced Repetition Prompts
Educational resource deconstructing Steve Yegge's Gas Town agent orchestration framework with spaced repetition prompts and linked concepts.
4/13/2026
The GPU Moat Has a Side Door: AI Research Outside the Frontier Labs
Analysis of AI research outside frontier labs using alternative approaches to GPU constraints.
4/13/2026
Agentic Search Leaderboard
Leaderboard evaluating LLMs on agentic search tasks with open methodology and real shopping queries.
4/13/2026
Show HN: Bloomberg Terminal for LLM ops – free and open source
Open-source LLM operations dashboard monitoring provider health, costs, latency, and concentration risks.