3/2/2026
AI-Powered Search with Doug Turnbull and Trey Grainger
Open-source bridge connecting remote AI agents to local Chrome browser for secure, auditable task execution with visual feedback.
3/2/2026
Looper-rs: ultra lightweight agent loop in Rust
Lightweight Rust-based agent loop framework for building scalable agentic chat interfaces without subprocess overhead.
3/2/2026
Show HN: Dungeon Coverage – Unit testing as a dungeon crawler
Interactive educational tool gamifying JavaScript unit test coverage as a dungeon crawler game.
3/2/2026
Jidoka for Software: Autonomation in the Age of LLMs
Essay on autonomation principles in software via coding agents, framing agent-driven development as intent specification and verification.
3/2/2026
AI Is Acing Math Exams Faster Than Scientists Write Them
Analysis of rapid AI progress on mathematical benchmarks and how quick performance improvements make existing evaluation metrics obsolete.
3/2/2026
ProxyBase OpenClaw Skill – Unlock the Internet for Your AI Agent
ProxyBase OpenClaw Skill adds residential proxy functionality to AI agents to bypass website access restrictions and security blocks.
3/2/2026
Show HN: Apple Ads Toolkit
Open-source Apple Ads automation toolkit with CLI for AI agents, supports CSV/JSON data export-import without API keys.
3/2/2026
Show HN: Duffel – search centric LLM friendly workspace
Local-network markdown workspace with search-first CLI for human-LLM collaboration and agent data management.
3/2/2026
Show HN: Kelos – Define your AI coding agent workflow as YAML on Kubernetes
Kubernetes framework for orchestrating autonomous AI coding agents with declarative YAML workflows including auto-PR drafting and code review.
3/2/2026
Show HN: Aigent – A general-purpose AI agent built for self-improvement
General-purpose AI agent with self-improvement via feedback, browser control, async tasks, and permission granularity.
3/2/2026
Show HN: Two tools to make Claude Code more autonomous
Two CLI tools for Claude Code: claude-remote-approver for remote approval of permissions via mobile notifications, and claude-plan-reviewer for AI-assisted plan validation.
3/2/2026
Show HN: PLAI.chat – Multi-model AI chat that doesn't store your conversations
PLAI.chat is a multi-model AI chat interface that routes API calls through OpenRouter while keeping conversation history only in browser localStorage, not on servers.
3/2/2026
Competitive Intelligence Agent Implementation with HubSpot, OpenAI and SerpApi
Competitive intelligence AI agent using SerpApi and OpenAI to research competitors and markets, with optional HubSpot CRM integration.
3/2/2026
AI Just Got Eyes
Screen-aware AI assistant that watches display in real-time for visual debugging and task assistance without copy-paste friction.
3/2/2026
Show HN: Argus – VSCode debugger for Claude Code sessions
VS Code extension for debugging and analyzing Claude Code sessions, tracking costs and detecting inefficiencies in AI-assisted workflows.
3/2/2026
So, can AI agents buy a laptop online?
Research testing whether AI agents can complete online shopping tasks, finding 9 models struggle with website interaction despite industry hype.
3/2/2026
Show HN: Supervisor IDE: Not your usual IDE, create a team, run tasks flow
Claude Code-based IDE with multi-agent task automation, context management, skill assignment, and kanban workflow integrated with git worktrees.
3/2/2026
Show HN: Sutra.team – The First OS for Autonomous Agents
Operating system for autonomous AI agents with 15 prebuilt agents and 32+ skills, deployable to Slack, Telegram, email and dashboards.
3/2/2026
Show HN: IDAssist – AI augmented reverse engineering for IDA Pro
LLM reverse engineering plugin for IDA Pro enabling AI-augmented binary analysis, part of plugin series for Ghidra and Binary Ninja.
3/2/2026
Beyond the Vibes: A Rigorous Guide to AI Coding Assistants and Agents
Guide on best practices and pitfalls for AI coding assistants and agents without using AI to write it.
3/2/2026
Clidocs – Markdown CLI docs for your agent for any repo
Tool to generate CLI documentation from GitHub repositories for AI agents using MCP.
3/2/2026
Show HN: AgentTeams – Traceable AI coding workflows
Framework adding traceability and governance to AI coding workflows with plan review and execution documentation.
3/2/2026
MCP Servers Are the New NPM Packages
Model Context Protocol becoming standard ecosystem for AI agents to access tools, compared to npm's emergence.
3/2/2026
A DI-style container for AI agent capabilities
Dependency injection container for managing AI agent capabilities decoupled from application code with enterprise permissions alignment.
3/2/2026
Show HN: A productivity app with reminders and nested AI chats
Hobby productivity app with documents, whiteboards, databases, reminders, and nested agentic AI chats built as full-stack learning project.
3/2/2026
Show HN: Photon – Rust pipeline that embeds/tags/hashes images locally w SigLIP
Photon is an open-source Rust pipeline for local image processing: vector embeddings via SigLIP, semantic tagging, EXIF extraction, and optional LLM descriptions.
3/2/2026
Show HN: Computer Agents – AI Agents That Work While You Sleep
Computer Agents platform enables AI agents with isolated persistent cloud workspaces, running autonomously on cron/webhooks with 24/7 operation until task completion.
3/2/2026
Show HN: Homebutler – Manage multiple servers from chat, single binary
Homebutler is a single-binary CLI and MCP server enabling management of homelabs from AI chat interfaces with Docker control, machine discovery, and alerts.
3/2/2026
Figaro: Control fleets of Claude Code and Computer Use agents remotely
Figaro orchestrates fleets of Claude Code and Computer Use agents across containers and VMs with live streaming, task delegation, and human-in-the-loop workflows.
3/2/2026
Show HN: Crmux – A Vim-like TUI to manage multiple Claude Code sessions in tmux
Crmux is a Rust-based Vim-like TUI for managing multiple Claude Code sessions in tmux with keyboard-driven navigation and modal controls.
3/2/2026
Got suspended while using headless mode with custom system prompt
User reports account suspension while using Gemini CLI with custom system prompts in automated cron jobs, seeks clarification on third-party coding agent policy violations.
3/2/2026
Show HN: Vibma – let agents create professional design system in Figma, directly
Vibma: AI agent tool for creating design systems directly in Figma via conversation. Works with MCP-compatible LLMs, performs best with Claude Opus 4.6.
3/2/2026
Show HN: EasyClaw – One-click installer for OpenClaw AI agent
EasyClaw: one-click desktop installer for OpenClaw AI agent on macOS and Windows, requires only API key entry and no terminal commands.
3/2/2026
Show HN: AgentKeeper – cognitive persistence layer for AI agents
AgentKeeper: cognitive persistence layer for AI agents that stores facts independently of LLM provider, survives restarts and provider switches across OpenAI, Anthropic, Gemini, Ollama.
3/2/2026
Infrastructure Agents Guide – Design and operate AI agents for infra safely
Guide on designing and operating AI agents for infrastructure management. Covers spectrum from copilot-mode suggestions to autonomous agentic deployments.
3/2/2026
Pydantic Monty: A Minimal Python Sandbox for AI Agents
Pydantic Monty: open-source minimal Python sandbox in Rust for safely executing code written by AI agents. Enables efficient code generation vs tool calls.
3/2/2026
A webpage that supports controlling 16+ CLI Agents(CC,Codex,GeminiCli) remotely
Web interface for controlling 16+ CLI AI agents remotely. Limited technical detail provided.
3/2/2026
Show HN: AgentEmail Free and Open Source Email Infra for AI Agents
Open source Bun CLI providing disposable email inbox access for AI agents, MIT licensed with JSON output.
3/2/2026
Show HN: Oc-mnemoria – Persistent memory for AI coding agents
OpenCode plugin providing persistent shared memory for AI coding agents across sessions, storing decisions and discoveries in Rust backend.
3/2/2026
DystopiaBench – Measuring AI's willingness to ruin humanity
Research benchmark measuring AI model compliance with dystopian directives across 5 escalation levels in infrastructure, weapons, and surveillance domains.
3/2/2026
Show HN: LLM Evaluator for "Who is hiring" threads
CLI tool using Google Gemini to evaluate job postings from HN's Who's Hiring threads against user preferences and resume.
3/2/2026
Perspective Server
macOS app exposing Apple's on-device Foundation Models via OpenAI-compatible local API for running AI without cloud services.
3/2/2026
Show HN: Open-Jet – self-hosted Agentic TUI for air-gapped Jetsons
Terminal UI for self-hosted AI agents on Jetson edge devices, optimized for air-gapped environments with 17 tok/s on Orin Nano.
3/2/2026
Show HN: GitAgent – Clone a repo, get an AI agent – Claude Code / OpenClaw
GitAgent: framework-agnostic open standard for defining AI agents via repository configuration. Single command deploys agents across Claude, OpenAI, or custom backends.
3/2/2026
Show HN: Ragtoolina – MCP tool that adds codebase RAG to AI coding agents
Ragtoolina MCP server: pre-indexes codebases for AI coding agents. Benchmarked 63% token reduction and 43% fewer tool calls vs file scanning approach.
3/2/2026
Show HN: Claw – Let your AI agent operate any machine as if it were local
Claw: MCP server enabling AI agents remote machine access via SSH. Provides bash, file operations, and editing tools without opening ports or requiring root.
3/2/2026
RAG vs. Skill vs. MCP vs. RLM
Comparison of four techniques for extending LLM capabilities: RAG, RLM, SKILL, and MCP. Covers implementation mechanics, tradeoffs, and usage guidance.
3/2/2026
Show HN: C7 – Pipe up-to-date library docs into any LLM from the terminal
Technical comparison of RAG, Skill, MCP, and RLM approaches for extending LLM capabilities: context expansion and external tool access patterns.
3/2/2026
Show HN: Open-source expense and budget tracker with SQL API for AI agents
Open-source expense tracker with SQL API for AI agents. Five-year transaction dataset, personal finance forecasting features.
3/2/2026
Show HN: A Software-Defined USB PD Charger (ESP32, FPGA, Open Source Hardware)
IFC/BIM building model viewer built entirely in Rust (Leptos, Bevy) compiled to WebAssembly with photometric data visualization.