Category 07

AI Agents

Autonomous agents and agent-building platforms.

Standout picks across editions

The current edition's pick, highlighted, plus earlier picks in this category from our backfilled archive — sourced from credible outlets (Hacker News, GitHub, TechCrunch and more) and checked against each product's official site.

This edition's pick · Nov 16–30, 2026
PM

Perplexity Multiagent

Up to 16 AI agents working as one team

Lead agent coordinates up to 16 sub-agents.

Why it matters

Launched Nov 17: a lead agent splitting work across up to 16 model-diverse sub-agents — a high-profile step toward consumer-grade coordinated multi-agent systems.

Nov 1–15, 2026 edition
AI

Agentic Identity Broker

OAuth delegation for AI agents

OAuth delegation so agents get scoped, delegated access.

Why it mattered

OAuth delegation for AI agents, from Zalando's incubator — tackling how agents obtain scoped, delegated access to services on a user's behalf.

Evidence dated 2026-11-06hackernews ↗github ↗
Researched · pending approvalVisit site ↗
Oct 16–31, 2026 edition
C

CVEngine

AI-first attack-surface assessment

AI-first external attack-surface assessment with MCP integration.

Why it mattered

AI-first external attack-surface assessment with continuous discovery and evidence-based vulnerability validation, integrated with developer agents via MCP.

Evidence dated 2026-10-24github ↗
Researched · pending approvalVisit site ↗
Oct 1–15, 2026 edition
A

ARTEX

Autonomous AI penetration-testing system

Autonomous AI system for penetration testing.

ARTEX is a self-hosted, LLM-driven penetration-testing platform where multiple AI agents work together to test targets for vulnerabilities — decomposing goals into executable tasks, running real security tools, and recording evidence that links each finding to captured network traffic. A dual-graph architecture separates what's known about a target (asset graph) from testing progress (exploration graph); a planner agent dispatches work to concurrent worker agents through a recording proxy, producing an auditable chain of reasoning and proof. It's open source under AGPL-3.0 and explicitly restricted to authorized testing — aimed at security professionals doing sanctioned pentests, bug bounties and red-team work.

Why it mattered

An autonomous AI penetration-testing system that drew the fortnight's strongest GitHub momentum for offensive-security agents.

Evidence dated 2026-10-08github ↗
Sep 16–30, 2026 edition
A

Andee

On-device Android agent for any app

On-device Android agent that drives any app.

Andee is an Android agent that runs directly on your phone and automates tasks across any app with no integrations — reading the screen, reasoning about the next action, and tapping, typing and swiping like you would. It's powered by any OpenAI-compatible model you configure (DeepSeek by default), and keeps its notebook, habits and vault strictly on-device; only conversation data goes to your chosen model endpoint, never to Andee's maintainers. It runs on Android 11+ and targets users who want a private, model-agnostic phone agent.

Why it mattered

An on-device Android agent that operates any app like you do — no integrations or root — keeping memory, habits and vault on the phone.

Evidence dated 2026-09-17github ↗
Sep 1–15, 2026 edition
PB

Pizza Bot

An inbox for background AI agents

Inbox for AI agents that work in the background.

Why it mattered

An inbox for AI agents that work in the background — reframing agents as asynchronous workers you triage like email.

Evidence dated 2026-09-15hackernews ↗github ↗
Researched · pending approvalVisit site ↗
Aug 16–31, 2026 edition
T

TabTin

Humans + multiple AI agents, one workspace

Workspace where people and multiple AI agents collaborate.

Why it mattered

A shared workspace where people and multiple AI agents work together — an early take on multi-agent collaboration surfaces.

Evidence dated 2026-08-19github ↗
Researched · pending approvalVisit site ↗
Aug 1–15, 2026 edition
PH

Phone Harness

Let your AI agent control your phone

Agents tap, type and scroll real iOS/Android apps.

Phone Harness lets AI agents operate real iPhones and Android devices — tapping, typing and scrolling through apps exactly as a person would, using visual input and on-screen controls with no jailbreaking or special APIs. Teams can use hosted cloud phones or connect their own device, giving agents genuine mobile-app reach instead of brittle per-app integrations. It targets developers building agents that need to act inside everyday consumer mobile apps.

Why it mattered

Gives agents real tap/type/scroll control of iOS and Android without jailbreaking or special APIs — a concrete step toward agents operating everyday mobile apps.

Evidence dated 2026-08-07github ↗official ↗

How picks are selected

Candidates are scored on market traction, recent momentum, product innovation, community interest, practical usefulness and source credibility. Only researched, fact-checked products are published — if no candidate meets the evidence threshold, we show no pick rather than forcing a weak selection.