Show HN: OpenTangl – Autonomous AI dev engine for multi-repo products
OpenTangl: Open-source autonomous AI development agent for multi-repo products; proposes tasks, writes code, manages cross-repo dependencies, creates PRs via GPT-4o/Claude.
OpenTangl: Open-source autonomous AI development agent for multi-repo products; proposes tasks, writes code, manages cross-repo dependencies, creates PRs via GPT-4o/Claude.
P2P file transfer tool using WebRTC and E2E encryption without server storage, built with React and TypeScript.
deck2video: Tool converting Markdown slide decks to narrated MP4 videos using local LLM voice cloning and text-to-speech.
Flexprice MCP Server: Exposes billing system operations as structured tools for AI agents to manage pricing, subscriptions, and overages.
AWS enhances Kiro's agentic AI capabilities for automated code quality improvement.
Research on science and methodology for improving AI agent reliability.
Opinion piece questioning if software engineering research has over-focused on AI at the expense of other problems.
AgentKeeper: cross-model memory system for AI agents preserving context when switching between LLM providers.
Overview of AI-assisted coding tools and landscape.
Discussion about whether game developers should use AI-generated assets and assistance.
Open Computer Use: open-source platform enabling AI agents to control computers via browser automation, terminal, and desktop interaction.
Mnemosyne: persistent memory system for AI agents enabling learning and multi-agent knowledge sharing without repeated LLM calls.
Unconfirmed announcement of GPT-5.3-codex API availability with code example.
Moonshine open-weights speech-to-text models with streaming capability and lower error rates than Whisper v3.
LLM-neofetch-plus: system information tool for local LLM users showing GPU VRAM, model capacity, and quantization comparisons.
AI agent architecture using Subjective Logic for earned autonomy, allowing agents to gain permissions over time based on performance.
Personal productivity system combining GTD and bullet journaling using Claude Code, markdown files, and Git for task management.
MCP Gateway: sandboxed tool for collapsing multiple LLM tools into efficient context by using JavaScript code execution.
Open-source KYC compliance plugin for Claude using public data sources, reducing fintech verification time from 95 to 27 minutes.
OpenPawz: open-source Rust/Tauri desktop AI agent platform with 75+ tools, local-first privacy, and multi-channel integration.
Brief announcement that gpt-5.3-codex model is available on API.
Brief mention of MatX raising $500M for inference chip development. Insufficient detail provided.
Developer uses Claude Code to accelerate climate model development, reducing multi-hour/day tasks to minutes with careful prompting and code review.
Intellegix HN Daily: open-source pipeline scraping HN stories, generating LLM summaries, and publishing as podcast on Spotify.
MCPs gain frontend UI interface, improving usability and data visualization for AI tool integration.
Article on using ChatGPT to analyze customer interviews and develop ideal customer profiles quickly.
Brainstorm-MCP: MCP server enabling multi-round debate between multiple LLMs (GPT, DeepSeek, Groq, Ollama) with synthesized output.
Disk Inventory X: Mac disk space visualizer rewritten in Swift for Apple Silicon.
Technical article on porting TeX from Pascal to TypeScript using LLMs for code translation.
Personal prompt technique for adopting a persona when interacting with Claude.ai.
Hyperterse 2.0: schema-first open-source framework for building MCP servers on production databases for AI agents.
Cryptic title comparing AI agents to Tamagotchi virtual pets. Insufficient information provided.
Linux GPU PCIe path validator for NVIDIA GPUs using CUDA and NVML for transport health analysis.
weight-inspect: tool to examine ML model file formats (GGUF, safetensors, ONNX) without loading weights.
Lneto: userspace TCP/IP networking library in Go for microcontroller units.
Study on reliability of LLMs in multi-turn conversations. Title only, insufficient content.
Brief mention of AI agents playing boardgames. Suggests benchmark/evaluation work with minimal details.
BMAD: open-source agile AI-driven development framework with scale-adaptive intelligence.
Brief announcement of GPT-5.3-Codex model availability on OpenRouter. Minimal information.
Academic analysis showing AI research convergence toward similar topics/methods, reducing research pluralism and intellectual diversity in social sciences.
Interactive tournament platform testing LLM adversarial reasoning via Texas Hold'em poker with imperfect information and inter-model dialogue.
Approach for preserving model openness, originality, and safety through antidistillation techniques. Minimal detail provided.
Analysis of reverse engineering Excel AI agents. Limited content in excerpt.
AMD announces MI400 GPU series and Helios rack systems targeting 2H 2026 for AI inference.
LLM-powered incident report automation tool correlating Slack messages with technical logs for post-mortem analysis via OAuth integration.
Duck Python web framework with native HTTP/2, HTTPS, and real-time features without separate infrastructure.
Video about Scholastic Book Fair Computer without details provided.
MantleDB anonymous JSON storage service for quick prototyping without database setup, registration via API.
Basis AI startup raises $100M Series B funding at $1.15B valuation.
Local web app visualizing Claude Code sessions as interactive radial mind maps, reading from Claude's local history files.