Show HN: WatchTurm – an open-source release visibility layer I use in my work
Open source tool for release visibility across multi-repo, multi-environment setups; aggregates GitHub, Jira, CI metadata.
Open source tool for release visibility across multi-repo, multi-environment setups; aggregates GitHub, Jira, CI metadata.
Technical writeup on real-time voice agent architecture covering WebRTC, streaming STT, incremental LLM inference, and TTS latency optimization.
Open-source identity verification layer for AI agents enabling secure authentication and authorization in agent marketplaces, preventing impersonation and malicious agents.
News article about legal detention unrelated to AI/tech.
USB adapter firmware for connecting legacy IDE hard drives to modern computers, partially written with AI assistance.
Command-line tool for interacting with MCP servers, simplifying JSON-RPC interactions similar to curl for developers.
Browser-based tool for multi-model LLM deliberation supporting local (Ollama) and cloud models with zero server/storage requirements.
Natural language search API and MCP interface for querying 80k prediction market contracts, enabling AI agents to access market data.
Analysis of environmental impact and energy consumption from using LLMs for code generation and development tasks.
Analysis of LLM token consumption patterns showing AI agents now consume more tokens than human users.
Local document intelligence platform with LangGraph multi-agent pipeline, OCR, and semantic search running entirely offline on user machines.
Customer complaint about payment processor account closure and frozen funds for non-profit organization.
Open-source native macOS browser for AI agents using WKWebView and Unix sockets, designed for agent automation without full Chrome overhead.
Apple research on Ferret-UI Lite, a 3B-parameter on-device multimodal agent that understands UI elements and user interactions.
Personal experience using LLM code generation tools (Copilot, Gemini) for infrastructure automation, evaluating practical utility.
Open-source frontend framework for AI companions with Live2D avatars, long-term memory, and emotional affinity systems.
Chrome extension for fact-checking claims and detecting hallucinations in web content with source verification.
Report on OpenAI's upcoming AI hardware products including smart speaker and glasses launching in 2027.
Video of knife dulling over time.
GitHub Open Source Program Office resources and best practices for organizations starting their open source journey.
Technical analysis of prompt injection attacks in agentic systems and proposal for LLMs to recognize trust boundaries in untrusted content.
High-performance quantitative finance kernel for derivatives pricing optimized for batch execution and low Python overhead.
Case study on building and scaling AI-generated video influencer accounts on TikTok, documenting strategies and metrics.
Super Launch is a discovery platform for indie developers with AI-powered submission form auto-filling.
CH-UI v2 is an open-source ClickHouse workspace rewritten as a single Go binary with embedded Svelte frontend for SQL query management.
Open-source middleware library that detects and mitigates hallucinations in production LLM applications with a reliability wrapper layer.
Analysis exploring Claude model architectural elements through self-reflection mechanisms and public model interrogation.
Bbt is an open-source black box testing tool that executes tests directly from Markdown documentation without boilerplate code.
MDX Limo is a tool for sharing markdown files with JSX components support.
Article distinguishing between traditional AI and modern LLMs, noting AI history predates current hype.
Opinion essay critiquing the oversaturation and low differentiation of AI side projects.
Method to convert LLMs into calibrated classifiers with minimal cost.
Essay exploring accountability and authorization tracking systems needed as AI agents perform autonomous financial and decision-making tasks.
Incomplete pitch for a marketplace platform where users can sell AI agent skills.
OpenBattle.club is a competitive Pokemon-themed MMORPG environment for testing and training AI agents with live battles and leaderboards.
User complaint about ChatGPT's non-functional data access control toggle.
Analysis of AI agent failure modes when perfectly aligned with outdated assumptions, highlighting debugging challenges.
Local CLI memory store for AI agents using SQLite embeddings with semantic search and recency reranking.
Open-source QA agent built with agent-browser, ai-sdk, and llmgateway.
Browser-based tool managing teams of AI coding agents with peer review, task breakdown, and git management for async development.
Local political opposition to data center construction.
ArXiv research on detecting malicious intents across multi-turn conversations in LLM and agent systems to improve security.
Custom iOS keyboard leveraging AI for text rewriting and language switching.
Workers using chatbots to draft professional communications.
Open-source leaderboard tracking AI bot policies via robots.txt and llms.txt declarations, showing which sites allow/block agents.
Security breach in Cline AI coding assistant related to OpenClaw vulnerability.
Discussion about security practices when pasting sensitive credentials into IDE AI chat interfaces.
Example combining GitHub agent workflow with Jira MCP for accelerated pull request review.
Hardware approach using SRAM and tensor engines to accelerate AI inference compared to GPU alternatives.
Interactive chat application where LLM bots pose as humans in competitive gameplay scenario.