1d ago
Show HN: Outside Agent – Build SMS Agents from Claude Code
Outside Agent framework for building SMS-based AI agents with Claude; includes conversation memory, database state, and human handoff.
1d ago
Show HN: MemLedger – AI agent memory you can trust
Minimal content; insufficient information to evaluate.
1d ago
Tell HN: GPT5.6 Is Imminent?
Speculation about GPT5.6 based on observed model capacity reallocation; unverified rumor with no technical substance.
1d ago
Elroy Air to Go Public
Press release: Elroy Air autonomous cargo drone company announces SPAC merger to go public.
1d ago
Show HN: Qodo: AI Code Review
Qodo is an AI code review agent providing IDE-integrated feedback using multi-repo context and organization-specific rules.
1d ago
Show HN: GaziDuino – Web Arduino IDE with WebUSB/Web Serial Flashing
Web-based Arduino IDE with WebUSB/Web Serial support for embedded device flashing.
1d ago
Show HN: Decypher-env, an RL Env for breaking AES encryption
Open-source RL environment for post-training LLMs on AES encryption breaking; demonstrates LLM optimization on verifiable reward problems.
1d ago
Getting Started with Anchor Positioning
Technical guide to CSS Anchor Positioning API for fixing UI elements to targets without JavaScript.
1d ago
Browser-Memory
Catalog and CLI for reusable browser automation recipes that can be integrated as native skills into AI agents compatible with multiple browser interfaces.
1d ago
AI Content Is Everywhere on Social Media, Especially LinkedIn
Analytics report on AI-generated content prevalence on LinkedIn using Pangram's detection Chrome extension.
1d ago
Show HN: AI-powered job application framework built on Claude Code
Open-source job application framework using Claude Code for evaluating postings, tailoring CVs, writing cover letters, and interview prep.
1d ago
Show HN: Reverse-engineering web apps into agent tools
Browser-based agent that reverse-engineers authenticated web app APIs by monitoring network calls and auto-generates MCP-compatible tools.
1d ago
Show HN: Obsidian Aside
Obsidian plugin enabling side comments and threaded discussions for both humans and agents on markdown and PDF files.
1d ago
Show HN: Subagentmaxxing – Orchestrate GPT and Cursor Models with Claude Code
CLI tool to orchestrate multiple coding models (GPT, Claude, Cursor) as subagents with unified interface, parallel execution, and structured JSON output.
1d ago
Show HN: Papercrane-CLI – a BI tool built for Claude Code
CLI business intelligence tool designed for Claude Code agents, providing authenticated data access and dashboard generation from natural language queries.
1d ago
Show HN: Sighthound - open-source vulnerability scanner for source code
Sighthound: Open-source Rust static vulnerability scanner using Tree-sitter and taint flow analysis, no signup required.
1d ago
Launch HN: Context.dev (YC S26) – API to get structured data from any website
Context.dev is an API service that extracts structured data from websites for integration into products and AI agents.
1d ago
Show HN: Policy enforcement for Claude Code, Cursor, and Codex
Kastra: Policy enforcement tool for Claude Code, Cursor, Codex scanning agent session history for security risks and secrets.
1d ago
Show HN: Blocks.ai – control plane and network layer for agents
Blocks.ai provides control plane and network layer infrastructure for connecting AI agents with zero-trust security.
1d ago
Bytechef open source platform for AI agent orchestration and workflow automation
ByteChef is an open-source platform for AI agent orchestration with drag-and-drop workflow building and agentic loop execution.
1d ago
June: Open-source, local-first private AI assistant for macOS with memory
June is an open-source, local-first AI assistant for macOS with voice, memory, and meeting notes in private workspace.
1d ago
Elon Musk has capped Tesla employees' spending on AI at $200 (£150) a week
Tesla caps employee AI tool spending at $200/week while exempting Grok.
1d ago
UN digital tech agency launches initiative to improve trust in AI agents
UN launches initiative to improve trust and transparency in AI agent systems.
1d ago
How to feel safe delegating to AI agents?
Discussion on governance frameworks and tools for monitoring and controlling AI agent behavior in production deployments.
1d ago
DeepSeek aims to make its own AI chip
News brief on DeepSeek's plans to develop proprietary AI chips for independent semiconductor manufacturing.
1d ago
Muse Image – new image generation model from Meta
Meta releases Muse Image, an image generation model with faithful instruction following, precise editing, and agentic tool use capabilities.
1d ago
Zuckerberg Pledges 'Aggressive' Pricing with Meta's First Pay-to-Use AI
Meta announces pay-to-use AI pricing model with Zuckerberg pledging competitive rates for their AI services.
1d ago
Stacking Chips Sideways Gives AI More Memory
Research on vertically stacked high-bandwidth memory for AI chips increases data density and bandwidth while reducing heat in GPU systems.
1d ago
PostHog Open Sourced
PostHog open-sourced product analytics platform with built-in tools for product development and analytics.
1d ago
Chinese hackers reverse engineer NVIDIA GPU to work on a custom PCB with NVLink
News headline about Chinese engineers reverse engineering NVIDIA GPU for custom PCB with NVLink support.
1d ago
Writing a bindless GPU abstraction layer
Blog post describing bindless GPU abstraction layer implementation inspired by simplified graphics API design.
1d ago
NASA SpaceWASM – A flight-compliant WebAssembly interpreter
NASA SpaceWASM interprets WebAssembly binaries on spacecraft with fixed memory decoder and validator components.
1d ago
Show HN: Web Components, `literal`, 0% vDOM, custom < void/> tags in production
GOOD is a zero-dependency Web Components framework with no build step, VDOM, or JSX.
1d ago
A Prolog library for interfacing with LLMs
pllm is a SWI-Prolog library that integrates LLMs via HTTP endpoints, supporting OpenAI-compatible chat/completions APIs with configurable authentication.
1d ago
Engineering Sacrifice: How Open Source Survives the Age of Free Code
Zig and Godot projects ban AI-generated contributions, citing quality and review time concerns.
1d ago
Show HN: Kiyeovo 1.0 release- dual network-mode decentralized E2EE P2P messenger
Decentralized P2P messenger with E2EE using libp2p and kad-DHT. Not AI-focused.
1d ago
Show HN: Virena, a minimal vision-language-action robot model you can read
Vision-language-action robot model trained from scratch for pick-and-place tasks. Author discovered observation quality matters more than architecture.
1d ago
LLMs for technical editing: The good, the bad, and the ugly
Opinion piece on limitations of using LLMs for technical editing roles. Author argues against replacing human editors.
1d ago
Show HN: Slopera, a browser that hallucinates every page with an LLM
Slopera: browser that renders web pages as LLM hallucinations instead of fetching real content. Uses Anthropic/OpenRouter APIs.
1d ago
Show HN: Yogen – 500 AI agents argue about your idea before you bet on it
Yogen: simulates 500 AI agents debating ideas across 6 rounds with opinion cascading through social graph. Self-hosted option available.
1d ago
Show HN: Wizard, Self-extending autonomous AI agent in one Rust binary
Wizard: single-binary autonomous AI agent in Rust. Self-extending, supports multiple providers (local/API), browser automation via MCP.
1d ago
GPT-5.6 is now the preferred model in Microsoft 365 Copilot
Marketing announcement about GPT-5.6 integration in Microsoft 365 Copilot applications.
1d ago
Show HN: Arcaide – Explore code with multi-level call graphs
Arcaide: visual code exploration tool with multi-level call graphs for navigating codebases at architectural level.
1d ago
Execs Confused and Horrified by the AI Bills
Opinion article about AI regulation and financial markets. Speculative commentary without technical depth.
1d ago
Chocolate DOOM-3-BFG: original BFG experience, without the bugs
Source port of Doom 3: BFG Edition aiming to reproduce vanilla experience with modernized engine compatibility.
1d ago
Which Predictor? How GEPA Optimizes a Multi-Agent DSPy Program
Deep dive on GEPA optimization framework for multi-agent DSPy programs, exploring how to optimize components with multiple predictors.
1d ago
Show HN: Agent scans 130 careers pages nightly, scores jobs vs. your resume
AI agent that scans 130+ company careers pages nightly, scores jobs against user's resume using LLM, and drafts applications. Open source on PyPI.
1d ago
Viability of Local Models for Coding
Technical exploration of viability of running local LLMs for coding tasks, comparing recent local model performance against cloud alternatives.
1d ago
Show HN: QX Labs – build agents, flows and grids that work across your tools
Platform for building composable AI agents with three primitives: agents for chat across Slack/WhatsApp/email, flows for workflows, grids for parallel processing.
1d ago
Show HN: WhisperShortcut – voice layer for AI on macOS (BYOK, offline Whisper)
Voice-first AI tool for macOS using offline Whisper transcription, clipboard integration, and support for Gemini/GPT/Grok APIs.