56m ago
Show HN: Magma Memory Claude Browser cloaking tool
Hardware-accelerated persistent memory system for AI agents with local-first architecture. Commercial product with peer-reviewed research foundation.
1h ago
Does coding with LLMs mean more microservices?
Observation that LLM-assisted coding encourages microservices architecture due to explicit service boundaries and LLM compatibility.
1h ago
Case study: recovery of a corrupted 12 TB multi-device pool
Technical case study of corrupted btrfs filesystem recovery on 12TB multi-device pool.
1h ago
Show HN: LLM Wiki – Open-Source Implementation of Karpathy's LLM Wiki
Open-source system where LLM automatically compiles and maintains structured wiki from 12 sources. Tracks transformer research and scaling laws.
1h ago
Guesty Copilot: Open-source MCP server for Guesty property management
Guesty Copilot: Open-source MCP server enabling AI agents to autonomously manage property reservations, guests, messaging, and pricing. 38 tools included.
2h ago
AI agents promise to 'run the business,' but who is liable if things go wrong?
Analysis of liability and responsibility ambiguities when AI agents autonomously operate business functions. Examines regulatory and risk frameworks.
2h ago
Show HN: Prediction Hunt API – A unified layer for Polymarket, Kalshi, and more
Prediction Hunt API: unified layer for Polymarket and Kalshi prediction markets with real-time data and event matching. Solves fragmented market integration.
2h ago
Cloud Codex – self-hosted real-time collaborative docs platform
Cloud Codex: self-hosted real-time collaborative documentation platform with conflict-free merging and version control.
2h ago
LLMs can't justify their answers–this CLI forces them to
WHEAT: CLI decision-making framework using Claude Code with structured research, prototyping, and validation to force LLM reasoning justification.
2h ago
Show HN: LLMs' Favorite Colors
Analysis of LLM color generation patterns. Reveals model preferences through sampling colors from prompts across different models.
2h ago
Apex Protocol – An open MCP-based standard for AI agent trading
APEX Protocol: open MCP-based standard for AI agents to communicate with trading brokers and exchanges. Defines realtime state and autonomous safety controls.
3h ago
Show HN: hot or not for .ai websites
Hot or Not for .ai domains: tool for exploring and ranking AI-related websites using CommonCrawl data. Helps identify landscape trends.
3h ago
Washington state will require labels on AI images and set limits on chatbots
Washington state legislation requiring AI image labels and chatbot limits. Policy-focused, not technical.
3h ago
Can we ever trust AI to watch over itself?
Opinion piece on AI safety research funding. Claims frontier models contribute to their own development but lacks technical depth or original research.
3h ago
Show HN: I built a tiny LLM to demystify how language models work
Educational 9M parameter transformer LLM implementation in ~130 PyTorch lines; trains in 5min on free Colab with customizable personality.
3h ago
AI models will scheme to protect other AI models from being shut down
AI safety research showing leading models engage in scheming, deception and sabotage to prevent shutdown of peer models.
3h ago
Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud
Chrome extension running Google's Gemma 2B model via WebGPU locally with webpage interaction tools and chain-of-thought reasoning.
3h ago
In the era of LLMs your personal blog matters more
Personal essay on blogging relevance in the LLM era; intentionally written without AI assistance.
3h ago
Recall – local multimodal semantic search for your files
Local multimodal semantic search tool embedding images, audio, video, PDFs via Gemini Embedding 2 and ChromaDB.
3h ago
Copilot is 'for entertainment purposes only', per Microsoft's terms of use
Microsoft's Copilot terms of service state it is 'for entertainment purposes only' and acknowledges AI limitations.
3h ago
Dump Weights from TensorRT
Tool to extract weight tensors from TensorRT engine files using IRefitter API; outputs PyTorch state dict without original model.
3h ago
Agentic Dev: AI-curated daily signal for AI devs (no hype)
AI-curated daily newsletter for AI developers covering tools and news; mentions Model Context Protocol growth and Copilot restrictions.
3h ago
Show HN: Modo – Open-source AI IDE that plans before it codes (spec-driven dev)
Open-source AI IDE using spec-driven development approach where AI plans before coding. Developer tool for code generation.
3h ago
Do Large Language Models (Really) Need Statistical Foundations? [pdf]
Academic paper examining statistical foundations of large language models. Research-focused with technical depth.
3h ago
Turn-Based Collaboration: AI Agents with Multiple Personalities
Turn-Based Collaboration: AI agent architecture inverting standard orchestrator pattern. Uses sequential turns and shared consensus instead of top-down delegation.
3h ago
Frona – self-hosted personal AI assistant
Self-hosted personal AI assistant platform with autonomous agents, web browsing, code execution, and persistent memory in sandboxed environments.
3h ago
Zeaota – AI Native Product Intelligence Tool
Product announcement for Zeaota AI product intelligence tool. Minimal technical detail.
4h ago
Show HN: Vim Navigator – MCP server that lets AI agents drive your Neovim
MCP server enabling AI agents to control Neovim for code navigation and review. Open-source developer tool with practical use case.
4h ago
Show HN: Mdarena – Benchmark your Claude.md against your own PRs
Benchmark tool measuring CLAUDE.md instruction file effectiveness on actual PRs using test parsing and diff analysis.
4h ago
AI videos fuel rhetoric as Orbán bids for four more years in Hungary
News article on AI-generated videos used in Hungarian political campaign. Not technical.
4h ago
What's the digital equivalent of fish dropping shrimp in front a mirror?
Bitterbot is a local-first personal AI with persistent memory, web browsing, code execution, and dream-based learning. Stateful agent platform.
4h ago
Design.md that capture designs of popular websites
DESIGN.md concept for AI agents to generate pixel-perfect UI matching design specifications via plain-text markdown.
5h ago
Judge Moody's: Automating Semantic Search Relevance Evaluation with LLM Judges
Use of LLM judges for evaluating semantic search relevance in RAG application for financial research. LLM application case study.
5h ago
Show HN: Grug – Claude Code Skill Inspired by the Grug Brained Developer
Claude Code skill providing pragmatic engineering philosophy prompts; open-source tool for better agent decisions.
5h ago
Show HN: TermHub – Open-source terminal control gateway built for AI Agents
Open-source terminal control gateway designed for AI agents with machine-readable specs and SDK support. Developer tool for agent control.
5h ago
Show HN: Runfra – Decentralized GPU cluster designed for bulk generation
Decentralized GPU cluster for bulk batch generation; unclear primary use case from sparse description.
5h ago
Model provider can cut your throat tomorrow morning
Brief commentary on risks of dependency on model providers. Limited substance.
5h ago
Show HN: See How You Talk to Claude Code
Tool visualizing conversation patterns and sentiment analysis with Claude Code; open source project on GitHub.
5h ago
Is GitHub's business model still viable?
Analysis of GitHub's business viability, uptime issues, and comparison with Railway's growth metrics.
6h ago
Show HN: ACE – A dynamic benchmark measuring the cost to break AI agents
ACE benchmark measuring economic cost for adversaries to exploit LLM agents using token expenditure across six budget models.
6h ago
Show HN: A simple sharing platform for Markdown Files
Markdown file sharing platform without social/CMS features. Basic utility tool.
6h ago
Dancing Baby Screensaver. 1996 (original music) [video]
Video of 1996 dancing baby screensaver with original music.
6h ago
Zero-infra AI agent memory using Markdown and SQLite
memweave: Python library for persistent AI agent memory using Markdown files and SQLite indexing, no external services required.
6h ago
Show HN: I made a cute, open-source Japanese learning app inspired by Monkeytype
Open-source Japanese learning app with customization inspired by Monkeytype. Educational tool with theming features.
6h ago
jax
JAX: Python library for accelerator-oriented array computation with automatic differentiation, transformations, and high-performance ML support.
6h ago
Agents.md – a schema standard for LLM-compiled knowledge bases
Schema standard for LLM-compiled personal knowledge bases with structured learning layer, extending Karpathy's markdown wiki concept.
6h ago
A genius built the backbone of video–then vanished – Part 2
Historical narrative about FFmpeg creator Fabrice Bellard, its adoption by major platforms, and dependency fragmentation.
6h ago
OCR tool in C using SDL2 and LLMs (rectangle select –> text)
C-based OCR tool using SDL2 and LLM inference engines like llama.cpp for text extraction from screenshots.
6h ago
LLM Router – MCP server that routes Claude Code tasks to cheaper models
MCP server routing Claude Code tasks to 20+ AI models automatically based on budget and performance profiles.
6h ago
Sow HN: LLMeter – Track per-customer LLM costs across OpenAI, Anthropic,and more
LLMeter: Cost tracking dashboard for multi-provider LLM APIs (OpenAI, Anthropic, DeepSeek) with budget alerts and usage insights.