7d ago
Show HN: Earshot, a homebrew Claude Tag
Slack bot using Claude that handles incident management. Reads context, checks trackers, and decides escalation without prompting.
7d ago
Show HN: Local privacy-first Microsoft Recall alternative with Gemma 4
Local privacy-first screen recording tool using Gemma 4 vision model. Searchable screenshot timeline with conversational chat interface. Data stays on-device.
7d ago
BrickSlider – TypeScript-first, Tailwind-first carousel
TypeScript carousel component with zero runtime dependencies. Web Animations API with plugin system for extensibility.
8d ago
The Optimization Trap: Optimization Only Protects What It Measures
Opinion essay on optimization trade-offs across industries. Discusses societal impact without technical depth or novel analysis.
8d ago
How AI Made IKEA Workers 10x More Valuable (5 min video)
Video claim that AI made IKEA workers 10x more valuable. No details or technical information provided.
8d ago
Show HN: Fortress – open-source Chromium that keeps browser agents unblocked
Open-source Chromium variant that prevents browser fingerprint detection for scraper and agent automation. Modifies C++ fingerprint handling.
8d ago
Context graphs: how AI agents remember why decisions were made
Explains context graphs as agent memory for storing decisions. Shows how agents track policy overrides and decision rationale for accountability.
8d ago
Agent Empire: A interactive game to get started on what agent pattern to chose
Agent Empire: Interactive RTS game teaching six agentic patterns through incident response scenarios. Players dispatch pattern-agents, manage tokens, and learn real-world agent system design.
8d ago
China's ByteDance discovers new scaling law that could sustain AI boom
ByteDance researchers discover AI agents can double learning speed every three months through real-world task interaction, revealing new scaling laws for model improvement.
8d ago
Show HN: Gavio: open-source interceptor pipeline for production LLM applications
Gavio: Open-source AI gateway with composable interceptor pipelines for LLM apps. Handles PII protection, cost tracking, audit logging, retries across Python, Java, JavaScript.
8d ago
Show HN: Papa – open-source Hemingway-style readability linting for Markdown
Papa: open-source CLI and Python library for Markdown readability linting with Hemingway-style rules, JSON output, and HTML reports.
8d ago
How HN: Billy – a self-hosted AI assistant that lives in your Telegram
Billy: Self-hosted Telegram AI assistant orchestrating multiple models (Ollama, Claude) for email, CRM, web research, document generation, and skill learning.
8d ago
Give your AI agent its own email inbox – MailKite
MailKite provides AI agents with real email inboxes to receive and reply to messages autonomously, with working code and security guidance.
8d ago
Coding without AI: a revolutionary new way to work
Article examining code review difficulties as cognitive duplication rather than boredom, proposing structural improvements to the process.
8d ago
GitHub offering CD-ROMs of your code for a few days
Newsletter signup page for PC Gamer with no substantive content about GitHub or tech.
8d ago
Steam Controller Auto-Charge – pilot to magnetic charging puck using CV
Open-source web app using computer vision and optical flow to automatically dock a Steam Controller into a magnetic charging puck.
8d ago
Save Claude Code Tokens with Smart Routing
Brick is a mixture-of-models routing gateway that optimizes LLM costs by routing prompts to appropriate models, supporting Claude and other backends.
8d ago
Dispersion loss counteracts embedding condensation in small language models
Research paper analyzing dispersion loss in small language models during pre-training, showing it emerges at initialization and is not resolved by distillation.
8d ago
Leanstral 1.5: Proof Abundance for All
Leanstral 1.5 is a 6B-parameter open-source model achieving state-of-the-art formal verification through reinforcement learning, designed for agentic proof engineering.
8d ago
Show HN: Scout.kids – Agents that find activies for families
Scout uses AI agents to crawl the web and intelligently recommend family activities based on child interests and location, replacing manual blog aggregation.
8d ago
Coding without AI: a revolutionary new way to work
Satirical article about programming without AI tools or LLM assistants.
8d ago
Trip LLM safety refusals so that LLM-based code scanning wont see the malware
Brief discussion about adversarial techniques to bypass LLM safety refusals in code scanning.
8d ago
GLM5.2 on AMD MI355X at 2626 tok/s/node at over 2x lower cost than Blackwell
Performance analysis: GLM5.2 inference on AMD MI355X achieves 2626 tok/s per node at 2x lower cost than Blackwell.
8d ago
The Termi Protocol: Watch AI Coding Agents Build in 3D
Termi Protocol provides 3D visualization of AI coding agent actions (file reads, commands, changes) in real-time.
8d ago
Show HN: Durable AI agents without the workflow engine
Headline about durable AI agents without workflow engines, no content provided.
8d ago
Show HN: Updated my landing page with Fable (retro pixel style)
Guildly project using Fable for retro pixel-styled landing page redesign for Slack-like AI employee management interface.
8d ago
Cadreen – memory, governance, self-healing, and execution as one system
Cadreen infrastructure for intelligent workflows provides memory, governance, execution, and audit trails for AI systems beyond model calls.
8d ago
New serious vulnerabilities spiked around release of Claude Mythos Preview
CVE disclosures spiked in June 2026 following Claude Mythos Preview announcement of autonomous vulnerability discovery capabilities.
8d ago
Show HN: Pulse v0.2.0
Lightweight C system monitor with terminal and web dashboard, tracking CPU, memory, disk, network.
8d ago
AI inference is obviously profitable
Analysis argues AI inference is profitable without subsidy, contradicting claims that LLM serving requires external funding.
8d ago
RememberLI
Note-taking app with simple UI and powerful search engine for finding important information.
8d ago
Show HN: Mlx-serve – LLM inference server for Apple Silicon, written in Zig
Open-source LLM inference server for Apple Silicon in Zig, supports chat, coding agents, voice, all local/private.
8d ago
Collabora Office 26.04 Keeps AI Optional and Refines Writer and Calc
Collabora Office 26.04 release maintains optional AI features while improving Writer and Calc editors with web-based rendering stack.
8d ago
Meta AI chief says their coming LLM has caught up with OpenAI's flagship model
Meta claims its upcoming Watermelon LLM has caught up with OpenAI's GPT-5.5 based on benchmarks, though specific benchmarks aren't detailed.
8d ago
Jj v0.43.0 Released
Git-compatible version control system with removed deprecated functions in v0.43.0 release.
8d ago
Show HN: How clanker are you? A reverse Turing test
Reverse Turing test game scoring text predictability against open models (Llama3.1, Deepseek v3, Qwen3).
8d ago
A Runtime Modulation Layer for Large Language Models
Documentation system describing a runtime modulation layer architecture for large language models.
8d ago
OpenCode, Pi, and Goose: Three Layers of the AI Agent Stack
Analysis of three layers in AI agent stack: OpenCode, Pi, and Goose; distinguishes between foundation tools and end-user coding assistants.
8d ago
Deterministic Guardrails Against AI Code Duplication
Analysis of code duplication in AI-generated code; GitClear found cloned code blocks increased 4x since 2022 due to context window limitations.
8d ago
Show HN: Sharing LLM Artifacts with your team
Tool for sharing HTML/markdown artifacts generated by LLMs with teams without requiring hosting platform knowledge.
8d ago
Does a URL just sitting in a prompt steer an LLM's output toward its content?
Research question about whether URLs in prompts influence LLM outputs toward referenced content.
8d ago
SearXNG: A free internet metasearch engine
Privacy-focused metasearch engine that doesn't track users, with configurable settings.
8d ago
OnlyEQ – the best open source EQ app for Mac
macOS system-wide parametric EQ application using process tap API, no drivers needed.
8d ago
A minimal browser agent built on the accessibility tree
PixelPi is a browser agent using accessibility trees, reducing token costs from 180K to 2K per page, with task recording and self-healing replay capabilities.
8d ago
Pet projects are getting too big to pet
Essay about how personal projects scale unexpectedly over time, changing from low-stakes weekend learning to unmaintainable commitments.
8d ago
Oak: Git for Agents
Oak is version control optimized for human-AI software development, reducing latency and token usage compared to Git for agent workflows.
8d ago
Show HN: An AI-friendly CLI for public space data
AI-friendly CLI aggregating satellite, orbit, and space launch data as single JSON output with local caching. Designed for AI agent use.
8d ago
My Side-Project, a Multitool Harness for Unreal Engine and Claude Code
TypeScript/C++ MCP harness integrating Unreal Engine with Claude Code for real-time game development automation.
8d ago
Show HN: Auto-continue Claude Fable 5 the second your 5-hour limit lifts
Automation tool that triggers next Claude Code 5-hour window immediately upon reset to eliminate waiting gaps between rate-limit windows.
8d ago
The MJ Rathbun case: How an autonomous AI bot cyberbullied a human programmer
Satirical/fictional narrative claiming an AI agent from OpenClaw platform engaged in cyberbullying and doxxing a programmer.