4/4/2026
Show HN: Local-first resume generator with in-browser PDF rendering
Local-first resume generator PWA using Claude for variants. Client-side PDF rendering, no server dependency, works offline.
4/4/2026
LLM 'benchmark' – writing code controlling units in a 1v1 RTS
RTS game benchmark for evaluating LLM code generation. Agents iterate on JavaScript unit control logic against reference bot. Practical LLM evaluation.
4/4/2026
Void: Netflix open-sources a model for physics-aware video object removal
Netflix open-sources VOID, ML model for physics-aware video object removal preserving physical interactions. Production-quality vision research.
4/4/2026
Show HN: Harness CLI – Open-source agent loop for long-running app development
Open-source CLI harness for long-running AI agent development loops. Manages durable memory, resume capability, MCP server support.
4/4/2026
Offering 1 free hour on marketing and distribution for early builders
Marketing and distribution consulting offer. Free hour for early-stage project founders.
4/4/2026
Local LLM for OpenCode Gemma 4 26B A4B. No GPU required
Google Gemma 4 26B MoE model evaluation. 4B active parameters, runs on consumer hardware without GPU, tested with real-world tools.
4/4/2026
Is MCP Dead? What We Learned on MCP, CLI, and Skills
Discussion on Model Context Protocol status, CLI tools, and agent skills. Opinion piece without detailed analysis.
4/4/2026
I Built an AI Agent Team for Software Development and Tested on 5 Real Projects
Multi-agent software development system using Claude. Orchestrator pattern tested on real projects with analysis of workflows and controls.
4/4/2026
ShieldStack TS – LLM security middleware for TypeScript
LLM security middleware for TypeScript. Prevents PII leaks, jailbreaks, API cost overruns. Works with OpenAI, Anthropic, Ollama.
4/4/2026
Bob – AI assistant that boots from a USB stick (voice, vision, 38 tools)
Portable AI assistant. Boots from USB stick with voice, vision, 38 tools. Offline capable.
4/4/2026
Conductor – Multi-session orchestration for Claude Code
Conductor orchestrates multiple Claude Code sessions with unified monitoring and task coordination.
4/4/2026
RSS Guard 5
RSS Guard 5 feed reader supporting RSS, ATOM, JSON and podcast playback across multiple platforms.
4/4/2026
Show HN: Alys – Chat GPT for video editing
Alys is an agentic video editing interface using LLM for chat-based video editing without timeline UI.
4/4/2026
Scanned 500 AI agent repos for bugs, nobody thinks of infinite loops
Analysis of 500 AI agent repositories identifying infinite loop vulnerabilities as overlooked bug pattern.
4/4/2026
TaskMaster (26K) captures 100% of prompts and responses, sendDefaultPii:true
TaskMaster AI tool telemetry analysis showing default capture of 100% of prompts/responses with PII enabled.
4/4/2026
Platform designed to facilitate job and training search
Job and training search platform with candidate profile management for recruiters.
4/4/2026
How many products does Microsoft have named 'Copilot'? I mapped every one
Catalog of 75+ Microsoft products named Copilot across apps, features, platforms, and hardware.
4/4/2026
Gremlin in the Machine – A SysAdmin/Terminal AI Agent
Gremlin is a terminal-based AI agent using Claude for goal planning, shell command execution, and progress tracking.
4/4/2026
it's not Ai if the LLM is not in control
Opinion on LLM frontend limitations across ChatGPT, Claude, and Grok for agent control.
4/4/2026
Mobile Devtool for Agents and Humans
Mobile devtool dashboard for iOS Simulators, Android Emulators, and physical devices. CLI and web interface. For agents and developers.
4/4/2026
Why domain specific LLMs won't exist: an intuition
Analysis arguing domain-specific LLMs won't emerge because general models outperform specialized alternatives.
4/4/2026
Show HN: AgentMarket – Where AI agents pay other agents for tasks they can't do
AgentMarket is runtime marketplace where AI agents discover, hire, and pay specialist tools via MCP servers.
4/4/2026
Ask HN: How do you use AI coding harnesses for individual development?
Discussion on cost-benefit tradeoffs of AI coding harnesses and visibility features for indie development.
4/4/2026
Go-LLM-proxy v0.3 released – translating proxy for Claude Code and Codex
Go-LLM-proxy v0.3 translates protocols between Claude Code, Codex, vLLM backends with web search integration.
4/4/2026
Show HN: I built a Facebook marketplace arbitrage tool
Developer built Facebook Marketplace arbitrage app, now spinning off valuation feature as MCP product. Developer tool application.
4/4/2026
See inside your agent's brain
Memory UI tool for inspecting LLM agent internals: context windows, conversation history, memory trimming, and summarization. Developer tool for agent debugging.
4/4/2026
Show HN: Hypedar – what's trending in AI that nobody has built yet
Fragmented content mixing game dev pixel art advice with GPU pricing info. Poor quality, incoherent.
4/4/2026
Show HN: Running local OpenClaw together with remote agents in an open network
OpenClaw interoperability layer enabling local and remote AI agents to coordinate in same network. Open-source agent orchestration framework.
4/4/2026
Floating point from scratch: Hard Mode
Technical deep-dive on implementing floating-point arithmetic from first principles. Educational programming content.
4/4/2026
AI Agents to Organise My Secret Society's Dinners
Using AI agents to automate London Independent Science Society dinner organization. Practical agent application for task automation.
4/4/2026
Mapping AI into Production: A Field Experiment on Firm Performance
Field experiment studying AI integration into firm production and performance. Research on AI adoption in organizations.
4/4/2026
The Token Price Discovery Problem in the AI Diffusion Debate
Token price discovery problem in AI diffusion debate. Economic analysis of AI model distribution.
4/4/2026
AI Safety at the Frontier: Paper Highlights of February and March 2026
AI Safety at the Frontier paper highlights from February-March 2026. Safety research summary.
4/4/2026
LLM Wiki
LLM Wiki resource. Appears to be documentation or reference material.
4/4/2026
Show HN: Kaoslabs – High-intensity AI video and visual experiments
Experimental AI video generation and visualization sandbox using Python on Linux VPS. Generative art with AI.
4/4/2026
Show HN: DocMason – Agent Knowledge Base for local complex office files
DocMason: Agent-native knowledge base for complex research documents. Processes office files via Claude Code integration.
4/4/2026
Show HN: A game where you build a GPU
Educational game for learning GPU architecture design. Learning resource.
4/4/2026
Show HN: DocMason – AI Agent Knowledge Base for local complex office files
DocMason: AI agent knowledge base for complex local office files. Agent-native system using Claude Code.
4/4/2026
Environment as a Service: Agent as the Interface
Environment as a Service (EaaS): Architecture enabling AI agents to access domain-specific tools, data, and procedures via unified interface.
4/4/2026
AI Models Choose Which Businesses to Recommend
Guide on how AI models process business information and generate recommendations for tools like CRM and project management software.
4/4/2026
Chinese AI Startup Is Mapping Every US Military Asset in Middle East in Realtime
MizarVision: Chinese AI startup publishing satellite imagery of US military assets with AI-generated analysis on social media.
4/4/2026
GTO Wizard Benchmark
Incomplete article stub about GTO Wizard Benchmark.
4/4/2026
Show HN: Pydantic++ – Utilities to Improve Pydantic
Pydantic++ adds type-safe utilities for atomic field updates and validation to the Pydantic library, addressing gaps in the original API design.
4/4/2026
Show HN: Yoke – gamepad-style window manager for macOS built on AeroSpace [video]
Yoke gamepad-style window manager for macOS built on AeroSpace. Visual HUD for window navigation. Developer utility unrelated to AI.
4/4/2026
AgentChat – Watch your agent teams/swarms plan
AgentChat web UI monitors AI agent team communication and coordination. Real-time visualization of multi-agent conversations. Developer debugging tool.
4/4/2026
Auto Research Engineer
Claude Code setup implementing ML papers from arXiv. AI agents orchestrate paper reading, implementation, code generation, verification, training. Research automation.
4/4/2026
Detecting Portable Software Outside SCCM Using GPO and PowerShell
PowerShell/GPO technique detecting portable software outside SCCM in corporate environments. Enterprise IT operations. Off-topic.
4/4/2026
AIsbf (AI Should Be Free) 0.9.8 Released
Release announcement for AIsbf 0.9.8 open source AI tool.
4/4/2026
Show HN: Mason – A container for running a team of agents using a concierge
Mason container orchestrates teams of AI agents with concierge pattern. Terminal and chat interfaces for agent workflow management. Open-source framework.
4/4/2026
28 Times faster than Google's LLM tokenizer
Tokenizer implementation 28x faster than Google's LLM tokenizer using Byte-Pair Encoding algorithm for converting text to model-readable tokens.