HN bhaviav100 1d ago

Show HN: I visualized how AI agent systems accidentally become org charts

Analysis and visualization of how AI agent system deployments unintentionally evolve organizational structures through emergent routing and specialization.

HN walterbell 1d ago

Intel Arc Pro B70 Brings 32GB VRAM to Local AI for $949

Intel Arc Pro B70 GPU with 32GB VRAM for $949 targets local AI inference workloads, undercutting NVIDIA alternatives but facing software limitations.

HN delavalom 1d ago

Graft – Go AI Agent Framework with Temporal/Hatchet/Trigger.dev Support

Go framework for building AI agents with multi-provider LLM support, type-safe tools, agent handoffs, guardrails, MCP integration, and graph orchestration.

HN Parkado 1d ago

Show HN: Chiral – Pentesting inside Chrome webtools

Chrome DevTools extension for lightweight penetration testing with intercepting, fuzzing, and attack sequence capabilities.

HN quarkcarbon279 1d ago

Show HN: MCP is for tools. A2A is for agents. What's for websites?

Proposal for standardized protocol enabling agents to execute multi-step website tasks with site owner consent, complementing MCP and A2A standards.

HN Indigenism 1d ago

Lightweight self-hosted internet radio management

Self-hosted internet radio streaming management system with web interface and AutoDJ features.

HN Jet_Xu 1d ago

Strong feeling: we are in a folded AI reality

Opinion piece contrasting perceptions of agentic AI capabilities versus limitations of current LLM chatbots.

HN datalater 1d ago

Catalog of AI Knowledge Retrieval, Memory and RAG Systems

Catalog analyzing AI memory and RAG systems through biological memory parallels, mapping vector databases, knowledge graphs, and episodic memory architectures.

HN inktype 1d ago

Code on Incus: Security-Hardened Container Runtime for AI Coding Agents

Incus container runtime with security hardening for AI coding agents like Claude Code and Aider, featuring isolation and threat detection.

HN fxtentacle 1d ago

What comes after Open Source?

Commentary on open source sustainability challenges and the economics of free software development.

HN asixicle 1d ago

Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC

Artist demonstrates two Claude instances collaborating through shared memory on low-cost hardware, addressing context management and project continuity challenges.

HN jonno-nz 1d ago

An LLM That Watches Your Logs and Kills Compromised Services at 3am

Satirical/fictional piece about Claude Mythos model for cybersecurity (appears to be speculative fiction).

HN hooch 1d ago

The biggest advance in AI since the LLM

Opinion piece claiming Claude Code represents biggest AI advance since LLMs due to pattern-matching kernel, cites unverified source code leak.

HN newsathere 1d ago

Bella: Hypergrah memory for AI agent(10x time horizon)

Bellamem Python package for persistent hypergraph memory in AI agents across sessions, tasks, and domains to maintain continuity.

HN obilgic 1d ago

Show HN: Posse – Open-Source Web UI for Anthropic Managed Agents

Open-source web UI for Anthropic Managed Agents with session management, memory stores, and multi-agent orchestration via browser interface.

HN try-working 1d ago

A Mac Studio for Local AI – 6 Months Later

Long-term review of running 600B parameter language models locally on Mac Studio M3 with 512GB memory, including performance findings.

HN volatilityfund 1d ago

My research has build errors now and honestly should have always worked this way

Wheat CLI tool that adds structured validation and evidence tracking to AI coding decisions, preventing silent conflicts in long LLM sessions.

HN sho_hn 1d ago

LLM Time

Stub entry with no content.

HN breve 1d ago

We spoke to the man making viral Lego-style AI videos for Iran

BBC report on viral Lego-style AI propaganda videos created for Iran by Explosive Media.

HN whycombinetor 1d ago

Ask HN: Former grok-code-fast-1 users, what coding model are you using now?

HN discussion on coding model alternatives after grok-code-fast-1 deprecation. Users share experiences with Minimax M2.5, grok-4.1-fast, and Claude Opus for feature coding.

HN gmays 1d ago

AI Can't Read an Investor Deck

Analysis of frontier AI models' capabilities on financial analysis tasks relevant to investment banking, arguing AI displacement concerns for analysts are premature.

HN volatilityfund 1d ago

Walked dog, did groceries, folded laundry. Claude Code shipped. Thanks Farmer

Farmer is a dashboard tool for approving/denying AI coding agent tool calls in real-time from desktop or mobile, enabling human oversight of agent actions.

HN cdrnsf 1d ago

Agentic Engine Optimization (AEO)

Agentic Engine Optimization discusses how AI coding agents consume documentation differently than humans, proposing optimizations for agent-facing developer tools and interfaces.

HN hamzmu 1d ago

Used Graphify to turn incidents into a queryable knowledge graph

Knowledge graph tool built on Graphify that transforms incident data into queryable graphs with communities and confidence scores, applied to incident management.

HN ccakes 1d ago

Ze networking tool you didn't know you were looking for

Ze is a networking tool for Linux servers implementing BGP routing with CLI and web UI, not related to AI or machine learning.

HN simplyjosh56 1d ago

Multi-agent memory consistency platform

Engram provides persistent shared memory for multi-agent teams with contradiction detection across sessions, enabling agents to share discovered facts and constraints.

HN totalmarkdown 1d ago

AI models are terrible at betting on soccer- especially xAI Grok

KellyBench study showing frontier AI models from Google, OpenAI, Anthropic, and xAI lost money betting on soccer, revealing limitations in real-world reasoning over time.

HN hxu296 1d ago

Inside the Token Factory: A First-Principles Comparison of vLLM and SGLang

Deep technical comparison of vLLM and SGLang inference engines covering paged attention, RadixAttention, continuous batching, and speculative decoding from first principles.

HN justguyB 1d ago

FullScope-MCP – Cut agent token usage by 60% without lossy summarization

FullScope-MCP is a context optimization layer that reduces token usage by 60% through structural code compression, enabling LLMs to reason over larger codebases without losing logic.

HN simjnd 1d ago

Optimization of 32-bit Unsigned Division by Constants on 64-bit Targets

Research on optimizing 32-bit unsigned division by constants on 64-bit targets. Low-level compiler optimization, tangential to user interests.

HN Mars2011 1d ago

Unified Perception Engine: never render more than humans can see (public domain)

Rendering engine architecture based on human perception using perception-calibrated degradation curves. Game dev focused, minimal AI relevance.

HN duguyue100 1d ago

Midnight Captain – A midnight commander inspired file manager

Terminal file manager inspired by Midnight Commander with Vim bindings. Unrelated to AI/ML/developer tools focus.

HN Achiyacohen 1d ago

Show HN: I benchmarked MCP vs. CLI for browser automation. MCP wins by 25x

Benchmarks Model Context Protocol vs CLI for browser automation. Safari-MCP with 84 tools outperforms hand-wrapped CLI by 25x using automated tool extraction from Zod schemas.

HN handfuloflight 1d ago

React-Debug-Updates

React-Debug-Updates is a one-liner debug tool for visualizing React component re-renders, frequency, duration, and causes without code modification.

HN handfuloflight 1d ago

Predict-Rlm: The LLM Runtime That Lets Models Write Their Own Control Flow

Predict-Rlm: agentic framework using Python sandbox, DSPy signatures, and parallel subcalls for structured LLM workflows with reduced context windows.

HN sroussey 1d ago

Ask HN: How to have a macOS devcontainer in VS Code?

Question about macOS devcontainers in VS Code for local model development and coding agents. Discussion format, limited technical depth.

HN hhs 1d ago

AI will test governments on jobs, training, and public trust

Policy analysis from Hoover Institution on AI's impact on government workforce, training, and public trust.

HN edwardsrobbie 1d ago

Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders

Report on Anthropic meeting with Christian leaders discussing AI ethics and theology.

HN nanfinitum 1d ago

How to Switch AI Chatbots and Why You Might Want To

Consumer guide on switching between different AI chatbots.

HN myth_drannon 1d ago

Tinker: Play with AI, bring your ideas to life

Shopify mobile app integrating multiple AI tools for creative content generation and idea exploration.

HN matt_d 1d ago

AI for Systems: Using LLMs to Optimize Database Query Execution

Research from Stanford, UW-Madison, and Bauplan on using LLMs to optimize database query execution plans. Tests 40+ models for production viability.

HN pierre 1d ago

Show HN: Git why – log your agent reasoning trace along your code

Git-why, open protocol for storing AI reasoning traces and conversations as Markdown files alongside source code, compatible with Claude Code, Cursor, Copilot.

HN cucumberbund 1d ago

Democratic AI to serve the public – OneProject.org

Opinion piece on democratic AI governance and corporate accountability. Advocates for structural change in AI industry but lacks technical depth.

HN matthart1983 1d ago

NetWatch v0.11.0 – TUI network diagnostics, now with connection filtering

NetWatch v0.11.0, terminal UI for real-time network diagnostics with connection filtering and incident recording.

HN pants2 1d ago

Ask HN: Has anyone reconsidered Antivirus software after recent security news?

Discussion about antivirus software and AI-assisted security threats. Tangential to core AI/ML interests.

HN thywis 1d ago

AI Is Tipping the Scales Toward Hackers After Mythos Release

Title-only entry about AI security implications. No substantive content provided.

HN PCasinoAVOS 1d ago

Transaction-level provenance for AI art certificate/signed/license on every sale

Title-only entry about AI art provenance and blockchain. No content available.

HN LopRabbit 1d ago

LPM 1.0 – Video-Based Character Performance Model

Title-only entry about video-based character performance model. Insufficient content for evaluation.

HN usmame 1d ago

Heartbeat – open implementation of KAIROS, the always-on agent hiden in Claude C

Heartbeat, open implementation of KAIROS—Anthropic's hidden always-on background agent in Claude Code—as model-agnostic daemon for autonomous action.

HN pascal-maker 1d ago

Is "Tokenmaxxing" a Flex?

Article about developers optimizing token usage with AI coding tools. Cultural observation with limited technical depth.